CN117455321B - Intelligent assessment method and system for performance of fluidized solidified soil - Google Patents
Intelligent assessment method and system for performance of fluidized solidified soil Download PDFInfo
- Publication number
- CN117455321B CN117455321B CN202311798071.6A CN202311798071A CN117455321B CN 117455321 B CN117455321 B CN 117455321B CN 202311798071 A CN202311798071 A CN 202311798071A CN 117455321 B CN117455321 B CN 117455321B
- Authority
- CN
- China
- Prior art keywords
- performance
- fluid
- solidified soil
- soil
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000002689 soil Substances 0.000 title claims abstract description 188
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 67
- 239000012530 fluid Substances 0.000 claims abstract description 53
- 239000000463 material Substances 0.000 claims abstract description 30
- 238000013507 mapping Methods 0.000 claims abstract description 23
- 238000007689 inspection Methods 0.000 claims description 39
- 238000010276 construction Methods 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract description 5
- 238000013461 design Methods 0.000 abstract description 3
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000035699 permeability Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000001932 seasonal effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000003756 stirring Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000005416 organic matter Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000000275 quality assurance Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000010008 shearing Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of backfill engineering, in particular to an intelligent assessment method and system for the performance of fluid solidified soil, wherein the method comprises the following steps: obtaining the performance requirement of the fluid state solidified soil according to the backfill soil quality information; acquiring a plurality of performance indexes of the fluid-state solidified soil, and assigning weights to the performance indexes of the fluid-state solidified soil; acquiring material proportioning information of the fluid solidified soil, and acquiring scheme performance data through the material proportioning information; establishing a multi-dimensional evaluation space, wherein the multi-dimensional evaluation space comprises a multi-dimensional coordinate axis; mapping the performance index and the scheme performance data to each corresponding dimension coordinate axis to obtain a performance mapping result; and calculating and scoring the performance mapping result according to the demand weight result to obtain a performance evaluation result. The invention effectively solves the problem of performance adjustment of the fluid-state solidified soil adapting to different environmental soil properties, and intelligently designs the evaluation method, and provides important evaluation adjustment basis for improving the performance of the fluid-state solidified soil in different soil properties.
Description
Technical Field
The invention relates to the technical field of backfill engineering, in particular to an intelligent assessment method and system for the performance of fluid solidified soil.
Background
Aiming at the pain points such as narrow fertilizer grooves and the like which are difficult to backfill and difficult to guarantee the backfill quality in the traditional backfill engineering, the fluid-state solidified soil backfill technology is developed, the fluid-state solidified soil is prepared by utilizing engineering waste soil, mixing a certain amount of solidified materials which are suitable for the characteristics of rock and soil, and uniformly stirring by specific stirring equipment to form a mixture which can be pumped, self-leveling and self-compacting, so that the construction is convenient, heavy equipment rolling with vibration equipment is not needed, and meanwhile, the fluid-state solidified soil has good volume stability and seepage resistance.
However, due to different factors such as construction environment, soil quality of backfilled soil and the like, the backfilled soil with the same proportion is difficult to match with the backfilled soil quality of various conditions, and the evaluation of the performance of the fluidized solidified soil under the current condition becomes an important basis for adjusting the proportion and improving the performance.
Disclosure of Invention
The invention provides an intelligent assessment method and an intelligent assessment system for the performance of fluid-state solidified soil, which can effectively solve the problems in the background technology.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
an intelligent assessment method for the performance of fluid-state solidified soil, which comprises the following steps:
acquiring backfill soil property information, and acquiring the performance requirement of the fluid state solidified soil according to the backfill soil property information;
obtaining a plurality of performance indexes of the fluid-state solidified soil, and distributing weights to each performance index of the plurality of performance indexes of the fluid-state solidified soil according to the performance requirements of the fluid-state solidified soil to obtain a required weight result;
collecting historical proportioning data comprising various material proportioning schemes used by historical fluid solidified soil projects and corresponding fluid solidified soil performance data, organizing the historical proportioning data into a sequence according to time steps, establishing a long-short-time memory network model for describing the relation between the material proportioning schemes and the fluid solidified soil performance, and introducing an attention mechanism into the long-short-time memory network model;
acquiring material proportioning information of the fluid-state solidified soil, and acquiring scheme performance data through the material proportioning information;
establishing a multidimensional evaluation space, wherein the multidimensional evaluation space comprises multidimensional coordinate axes, and each dimensional coordinate axis corresponds to an evaluation reference of the fluidized solidified soil;
mapping the performance index and the scheme performance data to each corresponding dimension coordinate axis to obtain a performance mapping result;
and calculating and scoring the performance mapping result according to the demand weight result to obtain a performance evaluation result.
Further, obtaining the performance evaluation result includes:
obtaining a difference vector formed between the performance index and the scheme performance data on each dimension coordinate axis;
and carrying out weighted calculation on the difference vector on each dimension coordinate axis according to the corresponding demand weight result, and obtaining the performance evaluation result.
Further, establishing the multi-dimensional evaluation space includes:
establishing the multidimensional coordinate axis according to a plurality of performance indexes of the fluidized solidified soil, and determining the unit and the range of the multidimensional coordinate axis;
establishing a historical quality inspection database and establishing a connection with the multidimensional evaluation space;
and establishing an expert system according to the historical quality inspection database, and adjusting the scheme performance data by the expert system according to the historical quality information of the fluidized solidified soil.
Further, establishing an expert system from the historical quality inspection database includes:
the parameter information of the fluid solidified soil in the historical quality inspection database is called;
constructing the expert system based on the machine learning and the retrieved parameter information;
constructing a training set and a testing set for the expert system;
and calibrating the expert system through the training set and the testing set.
Further, the expert system adjusting the project performance data according to the historical quality information of the fluidized solidified soil comprises:
extracting construction characteristic information corresponding to the scheme performance data;
screening data information matched with the construction characteristic information from the historical quality inspection database;
setting a performance interval threshold according to the matched data information;
judging whether the scheme performance data is within the performance interval threshold;
and if not, adjusting the scheme performance data according to the performance interval threshold.
Further, according to the performance interval threshold, the scheme performance data is adjusted to an endpoint value of the performance interval threshold closest to the scheme performance data.
Further, the performance requirements for obtaining a fluidized solidified soil include:
collecting and analyzing the backfill soil texture to obtain the backfill soil texture information;
analyzing backfill characteristics according to the backfill soil quality information;
determining a construction scene, and determining performance influencing factors according to the construction scene;
and obtaining the performance requirement of the fluid solidified soil according to the backfill characteristics and the performance influencing factors.
Further, establishing the historical quality inspection database includes:
collecting related construction logs, and preprocessing data in the construction logs;
classifying the data in the preprocessed construction log;
establishing a structure of the historical quality inspection database;
inputting the classified data into the historical quality inspection database;
and setting constraint conditions according to the classification, and establishing a database index for the expert system to screen and call data.
An intelligent assessment system for fluid-state solidified soil performance, the system comprising:
the performance requirement acquisition module is used for acquiring backfill soil quality information and acquiring the performance requirement of the fluid solidified soil according to the backfill soil quality information;
the demand weight acquisition module is used for acquiring a plurality of performance indexes of the fluid-state solidified soil, distributing weights to the performance indexes of the fluid-state solidified soil according to the performance demands of the fluid-state solidified soil, and acquiring a demand weight result;
the memory network building module is used for collecting historical proportioning data comprising various material proportioning schemes used by historical fluid solidified soil projects and corresponding fluid solidified soil performance data, organizing the historical proportioning data into a sequence according to time steps, building a long-short-time memory network model for describing the relation between the material proportioning schemes and the fluid solidified soil performance, and introducing an attention mechanism into the long-short-time memory network model;
the scheme data acquisition module is used for acquiring material proportioning information of the fluid solidified soil and acquiring scheme performance data through the material proportioning information;
the evaluation space establishing module is used for establishing a multidimensional evaluation space, wherein the multidimensional evaluation space comprises multidimensional coordinate axes, and each dimensional coordinate axis corresponds to an evaluation reference of the fluidized solidified soil;
the performance mapping module maps the performance index and the scheme performance data to each corresponding dimension coordinate axis to obtain a performance mapping result;
and the calculation scoring module is used for calculating and scoring the performance mapping result according to the demand weight result to obtain a performance evaluation result.
Further, the evaluation space establishment module includes:
the coordinate system generating unit is used for establishing the multi-dimensional coordinate axis according to a plurality of performance indexes of the fluid solidified soil and determining the unit and the range of the multi-dimensional coordinate axis;
the database connection unit is used for establishing a historical quality inspection database and establishing a connection with the multidimensional evaluation space;
and the data adjustment unit establishes an expert system according to the historical quality inspection database, and the expert system adjusts the scheme performance data according to the historical quality information of the fluid solidified soil.
By the technical scheme of the invention, the following technical effects can be realized:
the method effectively solves the problem of performance adjustment of the fluid-state solidified soil adapting to different environmental soil properties, and intelligently designs an evaluation method, and provides important evaluation adjustment basis for improving the performance of the fluid-state solidified soil in different soil properties.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent assessment method for the performance of fluidized solidified soil;
FIG. 2 is a schematic flow chart for creating a multidimensional evaluation space;
FIG. 3 is a schematic flow chart of an expert system established according to a historical quality inspection database;
FIG. 4 is a flow chart of adjusting the performance data of the scheme;
FIG. 5 is a schematic flow chart of obtaining the performance requirements of the fluidized solidified soil.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
As shown in fig. 1, the application provides an intelligent assessment method for the performance of fluid-state solidified soil, which comprises the following steps:
s100: acquiring backfill soil property information, and acquiring the performance requirement of the fluid solidified soil according to the backfill soil property information;
specifically, backfill soil property information can include soil type, particle distribution, plasticity index, water content, organic matter content and the like, and knowing and acquiring the soil property information can better obtain the performance requirements of the fluid state solidified soil, such as fluidity, bleeding rate, compressive strength, shear strength, permeability resistance, sinking resistance and the like.
S200: acquiring a plurality of performance indexes of the fluid-state solidified soil, and distributing weights to each performance index of the plurality of performance indexes of the fluid-state solidified soil according to the performance requirements of the fluid-state solidified soil to acquire a required weight result;
specifically, after the performance requirements of the fluid-cured soil in the above steps are determined, a plurality of performance indexes of the fluid-cured soil are obtained, where the performance indexes can be regarded as evaluating the properties of the fluid-cured soil, such as permeability resistance, the degree of stability requirement, and the like, which properties are explicitly required to be evaluated, and weights are assigned to the performance indexes according to the dependence of the soil property requirements of backfill soil and other environmental requirements on different degrees of the properties, and different evaluation criteria can be adopted for the fluid-cured soil in each construction scene to adapt to the current construction project.
S300: collecting historical proportioning data comprising various material proportioning schemes used by historical fluid solidified soil projects and corresponding fluid solidified soil performance data, organizing the historical proportioning data into a sequence according to time steps, establishing a long-short-time memory network model for describing the relation between the material proportioning schemes and the fluid solidified soil performance, and introducing an attention mechanism into the long-short-time memory network model;
the fluidized solidified soil project is usually carried out under different conditions within a certain period of time, and the soil performance can be influenced by various factors, including seasonal changes, climatic conditions, construction methods and the like, and the full utilization of time dimension information in the steps is significant for understanding the dynamic change of the fluidized solidified soil performance; for example, seasonal variations may cause periodic variations in soil performance, and the performance indicators of soil mobility, compaction, etc. may vary from wet season to dry season, and summarizing the historical proportioning data into sequences over time during the above steps may help the model capture and understand the pattern of these seasonal variations. In addition, with the development of engineering practice and technology, new proportioning schemes and construction methods can be introduced, and the data in the time sequence can reflect the changes, so that the model can adapt to engineering practice at different stages, and the performance of the fluid solidified soil can be estimated more accurately; in addition, during the project operation process, some emergencies, such as natural disasters, artificial accidents and the like, can occur, the performance of the solidified soil is influenced, and the influence of the emergencies on the performance can be identified through time series analysis.
For some time steps, the performance of the solidified soil is influenced by the special situation or the change of the proportioning scheme, in the step, the attention degree can be adaptively adjusted by the model through an attention mechanism, key information can be captured more pertinently, the attention mechanism can effectively process information imbalance by giving greater weight to important time steps, and the dependency and importance among different time steps can be modeled through the attention mechanism, so that the model can more accurately understand the time sequence characteristics in the historical data.
In an implementation, the mechanism of attention drawn to the long-short term memory network model may include:
designing a long-short time memory network model structure, which comprises an input layer, a hidden layer and an output layer, and ensuring that the model can capture time sequence information of historical proportioning data; the hidden state of the long-short-time memory network model is used as input to be transmitted to an attention mechanism, and the hidden state comprises the understanding and encoding of the long-short-time memory network model to the historical proportioning data; the calculation method of defining the attention mechanism can generally calculate the attention weight of each time step by introducing an attention weight matrix and an activation function, such as softmax, and in this embodiment, the calculation of the attention weight can be adjusted according to the performance of the model in the historical proportioning data; the historical proportioning data is weighted and averaged by using the calculated attention weight to obtain a weighted historical information vector, and the vector should reflect the contribution of each time step to the performance; fusing the weighted historical information vector with the hidden state of the long-short-time memory network model, which can be realized by means of simple splicing, weighted summation and the like; the fused vector becomes a new input and is transmitted to the long-short time memory network model for the calculation of the next time step.
S400: obtaining pre-use material proportioning information of the fluid solidified soil, and obtaining scheme performance data through the pre-use material proportioning information;
specifically, the ratio information of the pre-used material for obtaining the fluid-state solidified soil can come from a plurality of channels, can be the ratio information of the pre-set fluid-state solidified soil for the backfill soil of the project, and can also be obtained according to the matching degree of the backfill soil project and the current construction project in the past.
S500: establishing a multidimensional evaluation space, wherein the multidimensional evaluation space comprises multidimensional coordinate axes, and each dimensional coordinate axis corresponds to an evaluation reference of the fluid solidified soil;
s600: mapping the performance index and the scheme performance data to each corresponding dimension coordinate axis to obtain a performance mapping result;
s700: and calculating and scoring the performance mapping result according to the demand weight result to obtain a performance evaluation result.
Specifically, the performance index is obtained according to the requirement of backfill soil quality, the scheme performance data is obtained according to the preset material proportioning information, the dimension coordinate axes of the scheme performance data and the material proportioning information are mapped to the multidimensional evaluation space, the information of each attribute or parameter on a single dimension, namely the difference of the reaction on the single attribute or parameter, the difference reaction is the deviation between the requirement performance and the preset scheme, the mapping result on each dimension coordinate axis is subjected to further calculation scoring through the requirement weight result to obtain the performance evaluation result, the performance of the scheme can be clearly known through mapping the performance data to the multidimensional evaluation space, visual evaluation is facilitated for engineers, the advantages and the disadvantages of the scheme can be better known based on the multidimensional evaluation result, the quantitative performance evaluation result is provided according to the scoring result, and objective decision of engineers is facilitated.
According to the technical scheme, the problem of performance adjustment of the fluid-state solidified soil adapting to different environmental soil properties is effectively solved, the intelligent design is carried out on an evaluation method, and important evaluation adjustment basis is provided for improving the performance of the fluid-state solidified soil in different soil properties.
On the basis of the above embodiment, obtaining the performance evaluation result includes:
obtaining a difference vector formed between the performance index and the scheme performance data on each dimension coordinate axis;
and carrying out weighted calculation on the difference vectors on each dimension coordinate axis according to the corresponding demand weight result, and obtaining a performance evaluation result.
Specifically, a difference vector with a direction is formed between the position and coordinate point of the performance index and the performance data of the scheme on the dimension coordinate axis, the direction represents the deviation direction of parameters or attributes, for example, the shearing strength preset scheme is used for determining the direction and the value to be adjusted according to whether the deviation tendency of the performance index is too large or too small, wherein the performance index needs to be noticed that quantization processing is required to be carried out on the attributes when the corresponding multidimensional coordinate axis is determined in terms of performance, and enlargement and reduction processing is required to be carried out on each coordinate axis so as to facilitate unified quantization processing when the weighting calculation is carried out on each dimension coordinate axis, the relative importance of each performance index is more comprehensively considered by weighting the performance difference vector according to the required weight, the performance of the fluid-state solidified soil scheme is more objectively and comprehensively evaluated, the importance of each performance index is accurately reflected, and a clear performance evaluation result is provided.
Further, as shown in fig. 2, establishing the multidimensional evaluation space includes:
s510: establishing a multi-dimensional coordinate axis according to a plurality of performance indexes of the fluidized solidified soil, and determining a unit and a range of the multi-dimensional coordinate axis;
s520: establishing a historical quality inspection database and establishing a connection with a multidimensional evaluation space;
s530: and establishing an expert system according to the historical quality inspection database, and adjusting the performance data of the scheme according to the historical quality information of the fluid solidified soil.
Specifically, for each performance index, a dimension coordinate axis is created, the unit length and the range (minimum value to maximum value) adopted in the dimension are determined, the dimension coordinate axes are combined into a multi-dimensional evaluation space, historical quality inspection data of past fluid curing geotechnical engineering projects are collected, so that a relation between a historical quality inspection database and the multi-dimensional evaluation space is established, the data in the multi-dimensional evaluation space come from the historical quality inspection database, an expert system is established through data information provided by the historical quality inspection database, the system can adjust the performance data of the scheme based on the historical quality inspection data and experience rules, and parameters of a proposal or a modification scheme can be provided according to successful cases and failed cases in the historical data to optimize the performance. The expert system uses historical experience to guide engineers to make reasonable decisions, so that accuracy and reliability of performance evaluation are improved, time can be saved, trial-and-error cost can be reduced, and efficiency of engineering projects is improved.
Further, as shown in fig. 3, building an expert system from the historical quality assurance database includes:
s501: the parameter information of the fluid solidified soil in the historical quality inspection database is called;
s502: constructing an expert system based on the machine learning and the called parameter information;
s503: constructing a training set and a testing set for the expert system;
s504: the expert system is calibrated by the training set and the test set.
Specifically, the parameter information of the fluid-state solidified soil is retrieved from a historical quality inspection database, wherein the parameter information comprises performance data, soil types, curing agent consumption, proportioning information and the like of different engineering projects, an expert system model is built by utilizing a machine learning algorithm (such as a decision tree, a random forest, a neural network and the like), the model can predict relevant parameters of the fluid-state solidified soil according to the input parameter information, the expert system can automatically learn modes and relations in the historical data so as to predict the performance of a new scheme, the machine learning model can perform complex calculation according to a large amount of input parameter information, so that the accuracy of performance prediction is improved, and data is segmented from the historical quality inspection database, one part of the model is used as a training set for training the model, the other part of the model is used as a test set for verification of the model; training the expert system model by using the training set, and optimizing parameters of the model. Through the calibration process, the expert system can better predict the performance of the fluid-state solidified soil scheme, improve the accuracy and the reliability of the model, and also can identify and correct the possible deviation and error of the model.
On the basis of the above embodiment, as shown in fig. 4, the expert system adjusts the pattern performance data according to the historical quality information of the fluidized solidified soil, including:
s531: extracting construction characteristic information corresponding to scheme performance data;
s532: screening data information matched with construction characteristic information of a historical quality inspection database;
s533: setting a performance interval threshold according to the matched data information;
s534: judging whether the scheme performance data is within a performance interval threshold value or not;
s535: and if not, adjusting the scheme performance data according to the performance interval threshold.
Further, the solution performance data is adjusted to an endpoint value of the performance interval threshold nearest to the solution performance data according to the performance interval threshold.
Specifically, the expert system can extract data in construction engineering with higher matching degree with the construction engineering through a historical quality inspection database as a reference for adjusting the performance data of the fluid curing soil project, so that the matching data information is ensured to have similarity with the current project, a threshold value of related attributes is set according to feedback obtained by historical quality, two end point values of the threshold value are also set according to the historical quality inspection feedback of the fluid curing soil of the reference historical engineering, if the judgment of the performance data of the project is within the performance interval threshold value, the performance interval threshold value meets the standard, and if the performance interval threshold value is outside, the embodiment provides the end point value for adjusting the performance data of the project to the closest performance interval threshold value, so that the simplest and automatic adjustment mode is ensured, and the controllability and the performance stability of the fluid curing soil project are improved.
On the basis of the above embodiment, as shown in fig. 5, the performance requirements for obtaining the fluidized solidified soil include:
s110: collecting and analyzing backfill soil to obtain backfill soil information;
s120: analyzing backfill characteristics according to the backfill soil information;
s130: determining a construction scene, and determining performance influencing factors according to the construction scene;
s140: and obtaining the performance requirement of the fluid solidified soil according to the backfill soil characteristics and the performance influencing factors.
Specifically, the soil quality of backfill soil is collected and analyzed by materials, different collection points can be additionally arranged in the collection process, differentiation of soil in a fixed area and other positions is avoided, relatively accurate backfill soil quality information is obtained, however, for construction sites of different scenes, some characteristic changes of the soil, including strength and permeability, can be caused, the selection and proportioning of a curing agent are directly affected, the curing time is affected, scene factors are considered, the performance requirement of the fluid-state cured soil can be more accurately obtained, and accordingly accurate basis is provided for subsequent weight distribution and multidimensional evaluation space.
Further, establishing the historical quality inspection database includes:
collecting related construction logs, and preprocessing data in the construction logs;
classifying the data in the preprocessed construction log;
establishing a structure of a historical quality inspection database;
inputting the classified data into a historical quality inspection database;
and setting constraint conditions according to the classification, and establishing a database index for the expert system to screen and call the data.
Specifically, the construction data under various construction scenes or environmental conditions before are collected, wherein the construction data mainly comprises soil information of backfill soil, proportioning information of fluid solidified soil and final quality detection result feedback, the collected data information is classified according to the construction environment, proportioning information and quality feedback result, the collected data also need to be cleaned before being input into a database, some noise in the data is eliminated, and the usability of the data is improved.
Example two
Based on the same inventive concept as the intelligent assessment method for the performance of the fluid-state solidified soil in the previous embodiment, the invention also provides an intelligent assessment system for the performance of the fluid-state solidified soil, which comprises:
the performance requirement acquisition module is used for acquiring backfill soil quality information and acquiring the performance requirement of the fluid state solidified soil according to the backfill soil quality information;
the demand weight acquisition module is used for acquiring a plurality of performance indexes of the fluid-state solidified soil, distributing weights to the performance indexes of the plurality of performance indexes of the fluid-state solidified soil according to the performance demands of the fluid-state solidified soil, and acquiring a demand weight result;
the memory network building module is used for collecting historical proportioning data comprising various material proportioning schemes used by historical fluid solidified soil projects and corresponding fluid solidified soil performance data, organizing the historical proportioning data into a sequence according to time steps, building a long-short-time memory network model for describing the relation between the material proportioning schemes and the fluid solidified soil performance, and introducing an attention mechanism into the long-short-time memory network model;
the scheme data acquisition module is used for acquiring material proportioning information of the fluid-state solidified soil and acquiring scheme performance data through the material proportioning information;
the evaluation space establishing module is used for establishing a multidimensional evaluation space, wherein the multidimensional evaluation space comprises multidimensional coordinate axes, and each dimensional coordinate axis corresponds to an evaluation reference of the fluidized solidified soil;
the performance mapping module maps the performance index and the scheme performance data to each corresponding dimension coordinate axis to obtain a performance mapping result;
and the calculation scoring module is used for calculating and scoring the performance mapping result according to the demand weight result to obtain a performance evaluation result.
The adjusting system can effectively realize the intelligent evaluation method of the performance of the fluid solidified soil, and has the technical effects as described in the embodiment, and the detailed description is omitted here.
Further, the evaluation space creation module includes:
the coordinate system generating unit establishes a multi-dimensional coordinate axis according to a plurality of performance indexes of the fluid solidified soil, and determines a unit and a range of the multi-dimensional coordinate axis;
the database connection unit is used for establishing a historical quality inspection database and establishing a connection with the multidimensional evaluation space;
and the data adjustment unit establishes an expert system according to the historical quality inspection database, and the expert system adjusts the pattern performance data according to the historical quality information of the fluid solidified soil.
Similarly, the above-mentioned optimization schemes of the system may also respectively correspond to the optimization effects corresponding to the methods in the first embodiment, which are not described herein again.
Although the present application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary illustrations of the application as defined in the appended claims and are to be construed as covering any and all modifications, variations, combinations, or equivalents that are within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (10)
1. An intelligent assessment method for the performance of fluid-state solidified soil is characterized by comprising the following steps:
acquiring backfill soil property information, and acquiring the performance requirement of the fluid state solidified soil according to the backfill soil property information;
obtaining a plurality of performance indexes of the fluid-state solidified soil, and distributing weights to each performance index of the plurality of performance indexes of the fluid-state solidified soil according to the performance requirements of the fluid-state solidified soil to obtain a required weight result;
collecting historical proportioning data comprising various material proportioning schemes used by historical fluid solidified soil projects and corresponding fluid solidified soil performance data, organizing the historical proportioning data into a sequence according to time steps, establishing a long-short-time memory network model for describing the relation between the material proportioning schemes and the fluid solidified soil performance, and introducing an attention mechanism into the long-short-time memory network model;
the pre-use material proportioning information of the fluid-state solidified soil is obtained, and proportioning scheme performance data is obtained through prediction of the long-short-term memory network model;
establishing a multidimensional evaluation space, wherein the multidimensional evaluation space comprises multidimensional coordinate axes, and each dimensional coordinate axis corresponds to an evaluation reference of the fluidized solidified soil;
mapping the performance index and the performance data of the proportioning scheme to each corresponding dimension coordinate axis to obtain a performance mapping result;
and calculating and scoring the performance mapping result according to the demand weight result to obtain a performance evaluation result.
2. The intelligent assessment method for the performance of the fluid-state solidified soil according to claim 1, wherein obtaining the performance assessment result comprises:
obtaining a difference vector formed between the performance index and the scheme performance data on each dimension coordinate axis;
and carrying out weighted calculation on the difference vector on each dimension coordinate axis according to the corresponding demand weight result, and obtaining the performance evaluation result.
3. The intelligent assessment method for the performance of the fluid-state solidified soil according to claim 1 or 2, wherein establishing a multidimensional assessment space comprises:
establishing the multidimensional coordinate axis according to a plurality of performance indexes of the fluidized solidified soil, and determining the unit and the range of the multidimensional coordinate axis;
establishing a historical quality inspection database and establishing a connection with the multidimensional evaluation space;
and establishing an expert system according to the historical quality inspection database, and adjusting the scheme performance data by the expert system according to the historical quality information of the fluidized solidified soil.
4. A method for intelligently evaluating the performance of fluid-state solidified soil according to claim 3, wherein the step of establishing an expert system according to the historical quality inspection database comprises the steps of:
the parameter information of the fluid solidified soil in the historical quality inspection database is called;
constructing the expert system based on the machine learning and the retrieved parameter information;
constructing a training set and a testing set for the expert system;
and calibrating the expert system through the training set and the testing set.
5. A method of intelligently evaluating the performance of a fluidized solidified soil according to claim 3, wherein the expert system adjusting the project performance data based on historical quality information of the fluidized solidified soil comprises:
extracting construction characteristic information corresponding to the scheme performance data;
screening data information matched with the construction characteristic information from the historical quality inspection database;
setting a performance interval threshold according to the matched data information;
judging whether the scheme performance data is within the performance interval threshold;
and if not, adjusting the scheme performance data according to the performance interval threshold.
6. The intelligent assessment method according to claim 5, wherein the project performance data is adjusted to an endpoint value of the performance interval threshold closest to the project performance data according to the performance interval threshold.
7. The intelligent assessment method for the performance of the fluid-state solidified soil according to claim 1, wherein obtaining the performance requirement of the fluid-state solidified soil comprises:
collecting and analyzing the backfill soil texture to obtain the backfill soil texture information;
analyzing backfill characteristics according to the backfill soil quality information;
determining a construction scene, and determining performance influencing factors according to the construction scene;
and obtaining the performance requirement of the fluid solidified soil according to the backfill characteristics and the performance influencing factors.
8. A method for intelligently evaluating the performance of fluid-state solidified soil according to claim 3, wherein establishing a historical quality inspection database comprises:
collecting related construction logs, and preprocessing data in the construction logs;
classifying the data in the preprocessed construction log;
establishing a structure of the historical quality inspection database;
inputting the classified data into the historical quality inspection database;
and setting constraint conditions according to the classification, and establishing a database index for the expert system to screen and call data.
9. An intelligent assessment system for the performance of fluidized solidified soil, which is characterized by comprising:
the performance requirement acquisition module is used for acquiring backfill soil quality information and acquiring the performance requirement of the fluid solidified soil according to the backfill soil quality information;
the demand weight acquisition module is used for acquiring a plurality of performance indexes of the fluid-state solidified soil, distributing weights to the performance indexes of the fluid-state solidified soil according to the performance demands of the fluid-state solidified soil, and acquiring a demand weight result;
the memory network building module is used for collecting historical proportioning data comprising various material proportioning schemes used by historical fluid solidified soil projects and corresponding fluid solidified soil performance data, organizing the historical proportioning data into a sequence according to time steps, building a long-short-time memory network model for describing the relation between the material proportioning schemes and the fluid solidified soil performance, and introducing an attention mechanism into the long-short-time memory network model;
the scheme data acquisition module is used for acquiring material proportioning information of the fluid solidified soil and acquiring scheme performance data through the material proportioning information;
the evaluation space establishing module is used for establishing a multidimensional evaluation space, wherein the multidimensional evaluation space comprises multidimensional coordinate axes, and each dimensional coordinate axis corresponds to an evaluation reference of the fluidized solidified soil;
the performance mapping module maps the performance index and the scheme performance data to each corresponding dimension coordinate axis to obtain a performance mapping result;
and the calculation scoring module is used for calculating and scoring the performance mapping result according to the demand weight result to obtain a performance evaluation result.
10. The intelligent assessment system according to claim 9, wherein the assessment space establishment module comprises:
the coordinate system generating unit is used for establishing the multi-dimensional coordinate axis according to a plurality of performance indexes of the fluid solidified soil and determining the unit and the range of the multi-dimensional coordinate axis;
the database connection unit is used for establishing a historical quality inspection database and establishing a connection with the multidimensional evaluation space;
and the data adjustment unit establishes an expert system according to the historical quality inspection database, and the expert system adjusts the scheme performance data according to the historical quality information of the fluid solidified soil.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311798071.6A CN117455321B (en) | 2023-12-26 | 2023-12-26 | Intelligent assessment method and system for performance of fluidized solidified soil |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311798071.6A CN117455321B (en) | 2023-12-26 | 2023-12-26 | Intelligent assessment method and system for performance of fluidized solidified soil |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117455321A CN117455321A (en) | 2024-01-26 |
| CN117455321B true CN117455321B (en) | 2024-02-23 |
Family
ID=89595268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311798071.6A Active CN117455321B (en) | 2023-12-26 | 2023-12-26 | Intelligent assessment method and system for performance of fluidized solidified soil |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117455321B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997061A (en) * | 2022-06-14 | 2022-09-02 | 扬州阿鲁达环境科技有限公司 | Machine learning-based sludge solidification method and system |
| CN115860592A (en) * | 2023-03-03 | 2023-03-28 | 一夫科技股份有限公司 | Quality detection and evaluation method and system for gypsum building blocks |
| CN116596408A (en) * | 2023-07-14 | 2023-08-15 | 今创集团股份有限公司 | Energy storage container temperature control capability evaluation method and system |
| CN116756466A (en) * | 2023-06-20 | 2023-09-15 | 贵州省公路工程集团有限公司 | Superfluid concrete evaluation method and superfluid concrete evaluation system for steel truss-concrete combined arch bridge |
| CN116949940A (en) * | 2023-08-03 | 2023-10-27 | 德通智能科技股份有限公司 | Construction method for backfilling back of bridge abutment with fluid-state solidified soil |
-
2023
- 2023-12-26 CN CN202311798071.6A patent/CN117455321B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997061A (en) * | 2022-06-14 | 2022-09-02 | 扬州阿鲁达环境科技有限公司 | Machine learning-based sludge solidification method and system |
| CN115860592A (en) * | 2023-03-03 | 2023-03-28 | 一夫科技股份有限公司 | Quality detection and evaluation method and system for gypsum building blocks |
| CN116756466A (en) * | 2023-06-20 | 2023-09-15 | 贵州省公路工程集团有限公司 | Superfluid concrete evaluation method and superfluid concrete evaluation system for steel truss-concrete combined arch bridge |
| CN116596408A (en) * | 2023-07-14 | 2023-08-15 | 今创集团股份有限公司 | Energy storage container temperature control capability evaluation method and system |
| CN116949940A (en) * | 2023-08-03 | 2023-10-27 | 德通智能科技股份有限公司 | Construction method for backfilling back of bridge abutment with fluid-state solidified soil |
Non-Patent Citations (1)
| Title |
|---|
| 预拌流态固化土技术在地下综合管廊基槽回填工程中的应用;刘旭东;工程技术;20180228;第45卷(第4期);61-62 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117455321A (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7457735B2 (en) | Method and system for automatic water distribution model calibration | |
| CN102867110A (en) | Rainstorm disaster risk evaluation method for foundation slope of transmission line tower | |
| CN111914457B (en) | Power transmission line foundation slope stability judging method and device and storage medium | |
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| CN114741987B (en) | Flood probability prediction model considering absolute error fitting residual distribution of flood prediction model | |
| CN110751176A (en) | Lake water quality prediction method based on decision tree algorithm | |
| CN108388703A (en) | For non-linear and random process flexible measurement method | |
| CN115204533A (en) | Oil-gas yield prediction method and system based on multivariable weighted combination model | |
| CN116720139A (en) | Mine paste slurry yield stress prediction method and system | |
| CN116341078A (en) | Intelligent design and construction cloud platform for assembled building and application | |
| CN110260914B (en) | Engineering safety monitoring system region division method based on measuring point space-time characteristics | |
| CN117455321B (en) | Intelligent assessment method and system for performance of fluidized solidified soil | |
| CN117132169B (en) | Electric power artificial intelligent model calling evaluation method and system | |
| CN117891702A (en) | Method for determining performance index weight of embedded computing platform based on maximum entropy model | |
| CN112396312B (en) | Open caisson sinking construction automatic decision-making method and system | |
| CN114065639A (en) | Closed-loop real-time inversion method for construction parameters of dredger | |
| CN111222669A (en) | Overhead line cost prediction method and device | |
| CN117709488A (en) | Dam seepage prediction method based on RUN-XGBoost | |
| CN117196507A (en) | Intelligent management method and system for assembled building construction based on digital twinning | |
| CN116663402A (en) | Mixing station concrete quality prediction method based on digital twin | |
| CN111767649B (en) | Soft foundation area transformer substation geological deformation safety assessment method | |
| CN115358454A (en) | Coal and gas outburst prediction method based on extension-fuzzy hierarchical analysis theory | |
| Teegavarapu et al. | Fuzzy set based error measure for hydrologic model evaluation | |
| CN110453654B (en) | Optimization method for blending parameters in construction of core-wall rock-fill dam | |
| CN112183978A (en) | Oil-gas pipeline soil corrosion grading evaluation method based on correction entropy weight method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |