CN117077535A - High formwork construction monitoring method based on Gaussian mixture clustering algorithm - Google Patents
High formwork construction monitoring method based on Gaussian mixture clustering algorithm Download PDFInfo
- Publication number
- CN117077535A CN117077535A CN202311115627.7A CN202311115627A CN117077535A CN 117077535 A CN117077535 A CN 117077535A CN 202311115627 A CN202311115627 A CN 202311115627A CN 117077535 A CN117077535 A CN 117077535A
- Authority
- CN
- China
- Prior art keywords
- high formwork
- monitoring
- risk
- gaussian mixture
- divided area
- 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.)
- Pending
Links
- 238000009415 formwork Methods 0.000 title claims abstract description 161
- 238000012544 monitoring process Methods 0.000 title claims abstract description 126
- 239000000203 mixture Substances 0.000 title claims abstract description 90
- 238000010276 construction Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000011156 evaluation Methods 0.000 claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000006073 displacement reaction Methods 0.000 claims description 40
- 239000013598 vector Substances 0.000 claims description 11
- 238000012806 monitoring device Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000003014 reinforcing effect Effects 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 5
- 238000005192 partition Methods 0.000 claims description 5
- 238000009434 installation Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention provides a high formwork construction monitoring method based on a Gaussian mixture clustering algorithm, which comprises the following steps: firstly, dividing construction monitoring and safety early warning monitoring of a high formwork on a construction site into monitoring of each divided area and monitoring of an integral structure; then, respectively obtaining a complete life cycle data set capable of representing each divided region and the whole structure by carrying out engineering mechanics analysis and risk hypothesis evaluation on each divided region and the whole structure of the high formwork; finally, processing the data information through a Gaussian mixture clustering algorithm to obtain posterior probability and cluster division functions of the Gaussian mixture clustering algorithm representing each division area and the overall structure of the high formwork, automatically acquiring high formwork real-time data provided by monitoring equipment through a computer, substituting the real-time data into the corresponding functions, and judging whether the data information has risks or not, namely judging whether the high formwork has risks or not; the method realizes the automatic, real-time and accurate monitoring of the high formwork.
Description
Technical Field
The invention relates to the field of building construction, in particular to a high formwork construction monitoring method based on a Gaussian mixture clustering algorithm.
Background
The high formwork is used as a supporting structure, so that the normal operation of high construction is ensured; the high formwork is formwork supporting operation when the formwork supporting height is more than or equal to 8 m; the high formwork construction operation is used as a comprehensive operation engineering with high construction difficulty, high technical requirement level and strong risk coefficient, is easy to intensively burst safety production accidents, and has the obvious characteristics of occurrence of safety production accidents such as instability, randomness, burstiness and the like; the high formwork safety accident is mainly caused by overlarge deformation or load under the action of load to induce the failure of components in a system or the partial or whole failure of stability, so that the high formwork is partially collapsed or wholly overturned to cause the casualties of operation personnel; therefore, the smooth completion of construction is ensured, and the monitoring of the local part of the high formwork is enhanced, and the monitoring of the whole high formwork is also enhanced.
In the past, when the high formwork is monitored, corresponding monitoring equipment or instruments are installed on a construction site, local or whole conditions of the high formwork are monitored through the instruments, and local and whole conditions are rarely monitored at the same time; how to analyze the collected data is rarely mentioned, or after each data extraction, each element in the data needs to be subjected to independent data analysis, which is troublesome; in existing data analysis, training by using a neural network is common, but when the neural network algorithm assigns data, only two values with risk and no risk can be assigned; the risk degree of the risk data information cannot be reflected; therefore, it is necessary to uniformly analyze the local and the whole of the high formwork by using any method and to analyze the collected data rapidly, accurately and more finely.
Disclosure of Invention
The invention aims to overcome the problems existing in the prior art and greatly improve the technical effect on the basis of the prior art; therefore, the invention provides a high formwork construction monitoring method based on a Gaussian mixture clustering algorithm, which comprises the following steps:
according to the actual condition of the construction site, properly arranging a high formwork on the construction site;
dividing the arranged high formwork into areas, and dividing the high formwork into different areas; the region division includes: randomly dividing the high formwork to obtain different dividing areas; however, the monitoring can be finished by using one set of monitoring equipment for each area after the division;
monitoring of high formwork includes: monitoring each divided area and monitoring the whole high formwork;
the monitoring of each divided area comprises the following steps: respectively installing monitoring equipment in each divided area; the installing the monitoring equipment in each divided area comprises the following steps: an inclination angle sensor, a displacement sensor and a shaft pressure sensor; the monitoring of the high formwork overall comprises the following steps: the monitoring equipment is arranged at a proper position on the periphery of the high formwork and used for monitoring the overall condition of the high formwork; the installation of the monitoring device at the proper position of the periphery of the high formwork comprises the following steps: an inclination sensor and a displacement sensor;
obtaining original information x of each divided area of high formwork through sensor i And overall information X, the original information X i And the whole information X are vectors, wherein the original information X i The vertical displacement, the horizontal displacement, the vertical rod axial force and the vertical rod inclination angle are parameters; the whole information X comprises whole vertical displacement, horizontal displacement and vertical rod inclination angle;
by carrying out engineering mechanical analysis and risk hypothesis evaluation on each divided area and the whole structure of the high formwork, a data set { x ] of each divided area is obtained i1 ,x i2 ,…x in Data set of sum whole structure { X } 1 ,X 2 ,…X m -a }; wherein each element in each dataset represents a vector, x in Representing nth data information corresponding to the ith divided area obtained after engineering mechanical analysis and risk hypothesis evaluation; x is X m The mth data information of the overall structure obtained after engineering mechanics analysis and risk hypothesis evaluation is represented; the risk hypothesis evaluation includes: a hypothetical assessment of when there is no risk and when there is a risk; through evaluation, a series of data sets corresponding to each divided area when no risk exists and each divided area when the risk exists and a series of data sets corresponding to the whole structure when the risk does not exist and the whole structure when the risk exists are respectively obtained;
classifying the data sets of the divided areas by adopting a Gaussian mixture clustering algorithm; the posterior probability and the cluster division function of the Gaussian mixture clustering algorithm are used for respectively obtaining the cluster division probability ranges of the existing risk and the non-existing risk of each division area and the whole structure of the high formwork through whether the risks exist in the cluster division;
the equipment is accessed into a computer, and the computer automatically transmits and acquires the data information of each divided area and the whole structure through the monitoring equipment; then, the computer substitutes the acquired data information of each divided area and the whole structure into a posterior probability algorithm of a Gaussian mixture clustering algorithm, and judges whether each divided area and the whole structure have risks or not through cluster division; if the risk exists, notifying a construction site to suspend construction, notifying maintenance personnel to formulate an effective scheme according to the risk degree, and maintaining and reinforcing the region with the risk.
Further, the actual conditions of the construction of the railway station floor slab include: actual conditions of a construction site and design schemes of the whole construction.
Further, the random division of the high formwork includes: according to the limitation of the monitoring equipment during dividing; after the division of the areas is ensured, each divided area can be monitored safely through a set of monitoring equipment.
Further, the monitoring of each divided area is to monitor each area randomly divided by the high formwork, including monitoring the vertical displacement, horizontal displacement, vertical rod axial force and vertical rod inclination angle of the monitored area; the overall monitoring of the high formwork is to monitor the overall of the high formwork, and comprises monitoring of vertical displacement, horizontal displacement and vertical rod inclination angle of the overall of the high formwork.
Further, the original information x of each divided area of the high formwork is obtained through a sensor i And the overall information X includes: the method comprises the steps that an installed sensor is accessed into a computer, and the computer sends a request for acquiring original information of each divided area and overall information of a high formwork to monitoring equipment; and then the monitoring equipment collects the original information of each divided area and the whole information of the high formwork and feeds the information back to the computer.
Further, the engineering mechanics analysis and risk hypothesis evaluation on each divided area and the whole structure of the high formwork comprise the following steps: data set { x ] of each divided region obtained by carrying out engineering mechanics analysis and risk hypothesis evaluation on each divided region of high formwork i1 ,x i2 ,…x in The data set { X } of the overall structure obtained by carrying out engineering mechanics analysis and risk hypothesis evaluation on the high-formwork overall structure comprises data with risk and data without risk 1 ,X 2 ,…X m The data with risk and the data without risk are included in the }.
Further, classifying the data set of the divided region by adopting a Gaussian mixture clustering algorithm comprises the following steps: the Gaussian mixture clustering algorithm is also called a probability model algorithm, and comprises the following steps: a) Setting the number of Gaussian mixture components as k, and initializing model parameters of Gaussian mixture distribution; b) Preliminary calculation of x by initialized model parameters of Gaussian mixture distribution j Posterior probability gamma of (2) ji The method comprises the steps of carrying out a first treatment on the surface of the c) Continuously updating the model parameters of the Gaussian mixture distribution, and continuously repeating the step b) until a stopping condition is reached; d) Finally determining x through a maximum value function of posterior probability j Cluster division of (a); e) Final output cluster partition c= { C 1 ,C 2 ,…,C k -a }; the reaching stop condition is as follows: if the maximum iteration round number is reached; will history data information set { X ] i By Gaussian mixture polymerizationAfter classification is carried out by the class algorithm, one cluster with the most densely distributed sample data sets is used as a main classification part, and all the rest of sample data sets of other clusters are used as other classification parts.
In the above embodiment, the calculation formula of the posterior probability is:
wherein, gamma ji For posterior probability, α i 、u i Sum sigma i Representing sample x j Parameters of the corresponding ith Gaussian mixture component, α i >0 is the corresponding mixing coefficient, u i Representing the mean vector sum Σ i Representing a covariance matrix; k represents the composition of the Gaussian mixture distribution and k Gaussian mixture components, alpha h 、u h Sum sigma h Parameters indicating any one of the gaussian mixture components in the gaussian mixture distribution.
The cluster division function has the expression:
wherein, gamma ji Representing a sample x determined by the ith Gaussian mixture component j Posterior probability, eta j Representing sample x j Is marked by the final cluster division.
Further, the automatic sending and acquiring, by the computer, the data information of each divided area and the whole structure through the monitoring device includes: continuously sending a request for acquiring the data information of each divided area and the whole structure to the monitoring equipment through the accessed computer, and feeding back the acquired data information to the computer after each monitoring equipment acquires the data information of each divided area and the whole structure of the high formwork; then the computer inputs the received data information into a Gaussian mixture clustering algorithm to obtain cluster division corresponding to the data information; judging whether the input data information has risks or not according to cluster division; if the data information is input into a Gaussian mixture clustering algorithm, dividing the obtained clusters into clusters without risk, and proving that the input data information does not have risk; if the data information is input into a Gaussian mixture clustering algorithm, the obtained clusters are divided into clusters with risks, and the input data information is proved to have risks.
The beneficial effects of the invention are as follows:
the invention provides a high formwork construction monitoring method based on a Gaussian mixture clustering algorithm, which is used for realizing the complete monitoring of the high formwork from local part to whole part during construction and after construction by dividing the construction monitoring of the high formwork on a construction site into monitoring of each divided area and monitoring of the whole structure; carrying out engineering mechanical analysis and risk hypothesis evaluation on each divided area and the whole structure of the high formwork to respectively obtain a complete life cycle data set capable of representing each divided area and the whole structure, wherein the data set comprises a data set when no risk exists and a data set when the risk exists, and a function or model obtained by using the data set can reflect the actual data change condition of the complete life cycle of the high formwork; finally, classifying the data set through a Gaussian mixture clustering algorithm to obtain posterior probability and cluster dividing functions of the Gaussian mixture clustering algorithm representing each dividing area and the whole structure of the high formwork, automatically acquiring high formwork real-time data provided by monitoring equipment through a computer, substituting the real-time data into the posterior probability and cluster dividing functions of the Gaussian mixture clustering algorithm, and judging whether the data information has risks or not, namely judging whether the high formwork has risks or not; the probability of the Gaussian mixture clustering algorithm used by the method can give the risk degree of risk, so that the high-formwork data can be processed rapidly, accurately and more finely, and the high-formwork automation, real-time and accuracy monitoring can be realized.
Drawings
Fig. 1: the invention discloses a flow chart of a high formwork construction monitoring method based on a Gaussian mixture clustering algorithm.
Detailed Description
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the particular embodiments presented herein are illustrative and explanatory only and are not restrictive of the invention.
It should be noted that numerous specific details are set forth in the following description in order to provide a thorough understanding of the present invention, however, that other embodiments of the invention and variations thereof are possible and, therefore, the scope of the invention is not limited by the specific examples disclosed below.
As shown in fig. 1, a high formwork construction monitoring method based on a gaussian mixture clustering algorithm according to an embodiment of the present invention includes: step S100, properly arranging a high formwork on a construction site according to the actual condition of the construction site; step S101, dividing the arranged high formwork into areas, and dividing the high formwork into different areas; the region division includes: randomly dividing the high formwork to obtain different dividing areas; however, the monitoring can be finished by using one set of monitoring equipment for each area after the division; step S102, monitoring the high formwork comprises the following steps: monitoring each divided area and monitoring the whole high formwork; step S103, the monitoring of each divided area includes: respectively installing monitoring equipment in each divided area; the installing the monitoring equipment in each divided area comprises the following steps: an inclination angle sensor, a displacement sensor and a shaft pressure sensor; the monitoring of the high formwork overall comprises the following steps: the monitoring equipment is arranged at a proper position on the periphery of the high formwork and used for monitoring the overall condition of the high formwork; the installation of the monitoring device at the proper position of the periphery of the high formwork comprises the following steps: an inclination sensor and a displacement sensor; step S104, obtaining original information x of each divided area of the high formwork through a sensor i And overall information X, the original information X i And the whole information X are vectors, wherein the original information X i The vertical displacement, the horizontal displacement, the vertical rod axial force and the vertical rod inclination angle are parameters; the whole information X comprises whole vertical displacement, horizontal displacement and vertical rod inclination angle; step S105, obtaining a data set { x } of each divided region by carrying out engineering mechanics analysis and risk hypothesis evaluation on each divided region and the whole structure of the high formwork i1 ,x i2 ,…x in Data set of sum whole structure { X } 1 ,X 2 ,…X m -a }; wherein each element in each dataset represents a vector, x in Representing nth data information corresponding to the ith divided area obtained after engineering mechanical analysis and risk hypothesis evaluation; x is X m The mth data information of the overall structure obtained after engineering mechanics analysis and risk hypothesis evaluation is represented; the risk hypothesis evaluation includes: a hypothetical assessment of when there is no risk and when there is a risk; through evaluation, a series of data sets corresponding to each divided area when no risk exists and each divided area when the risk exists and a series of data sets corresponding to the whole structure when the risk does not exist and the whole structure when the risk exists are respectively obtained; step S106, classifying the data sets of the divided areas by adopting a Gaussian mixture clustering algorithm; the posterior probability and the cluster division function of the Gaussian mixture clustering algorithm are used for respectively obtaining the cluster division probability ranges of the existing risk and the non-existing risk of each division area and the whole structure of the high formwork through whether the risks exist in the cluster division; step S107, the equipment is accessed into a computer, and the computer automatically sends and acquires the data information of each divided area and the whole structure through the monitoring equipment; then, the computer substitutes the acquired data information of each divided area and the whole structure into a posterior probability algorithm of a Gaussian mixture clustering algorithm, and judges whether each divided area and the whole structure have risks or not through cluster division; if the risk exists, notifying a construction site to suspend construction, notifying maintenance personnel to formulate an effective scheme according to the risk degree, and maintaining and reinforcing the region with the risk.
Specifically, the method comprises the steps of firstly dividing construction monitoring of a high formwork on a construction site into monitoring of each divided area and monitoring of an integral structure; then, respectively obtaining a complete life cycle data set capable of representing each divided region and the whole structure by carrying out engineering mechanics analysis and risk hypothesis evaluation on each divided region and the whole structure of the high formwork; finally, through posterior probability and cluster division function of Gaussian mixture clustering algorithm, whether risk exists in each division area of the high formwork and the cluster division probability range of the integral structure with and without risk are obtained respectively; the method comprises the steps of automatically acquiring high-formwork real-time data provided by monitoring equipment through a computer, substituting the real-time data into posterior probability and cluster dividing functions of a Gaussian mixture clustering algorithm, and judging whether data information has risks or not, namely judging whether the high-formwork has risks or not; and (3) according to the risk degree of the risk, timely maintaining and reinforcing the high formwork risk area with the risk.
Step S100, properly arranging a high formwork on a construction site according to the actual condition of the construction site; specifically, the actual condition of construction on the construction site is determined through comprehensive analysis on the construction site, and the high formwork is reasonably arranged on the construction site according to the actual condition.
In the above embodiment, specifically, practical cases of construction on a construction site include: actual conditions of a construction site and design schemes of the whole construction.
Step S101, dividing the arranged high formwork into areas, and dividing the high formwork into different areas; the region division includes: randomly dividing the high formwork to obtain different dividing areas; however, the monitoring can be finished by using one set of monitoring equipment for each area after the division; specifically, the high formwork arranged on the construction site is divided into areas, and the high formwork is divided into different areas by random division, but the principle is to be followed: each divided area can be monitored by using one set of monitoring equipment; the set of monitoring equipment comprises: an inclination sensor, a displacement sensor or an axial pressure sensor.
In the above embodiment, specifically, when the high formwork is arbitrarily divided, the limitation of the monitoring device is adopted; after random area division is carried out on the high formwork, each divided area can be monitored safely through one set of monitoring equipment.
In the above embodiment, preferably, the high formwork may be arbitrarily divided during the construction of the high formwork and during the construction of the railway station floor slab after the construction of the high formwork, so that after division, each divided area is ensured to be monitored by a set of monitoring equipment.
Step S102, monitoring the high formwork comprises the following steps: monitoring each divided area and monitoring the whole high formwork; specifically, after the area division is carried out on the high formwork, the monitoring of the high formwork is divided into the monitoring of each divided area and the monitoring of the whole high formwork; the monitoring of each divided area is to monitor the local part of the high formwork, and the monitoring of the whole high formwork refers to the monitoring of the macroscopic whole high formwork.
In the above embodiment, specifically, the monitoring of each divided area is to monitor each area of the high formwork which is divided randomly, including monitoring the vertical displacement, horizontal displacement, vertical pole shaft force and vertical pole inclination of the monitored area; the overall monitoring of the high formwork is to monitor the overall of the high formwork, and comprises monitoring of vertical displacement, horizontal displacement and vertical rod inclination angle of the overall of the high formwork.
Step S103, the monitoring of each divided area includes: respectively installing monitoring equipment in each divided area; the installing the monitoring equipment in each divided area comprises the following steps: an inclination angle sensor, a displacement sensor and a shaft pressure sensor; the monitoring of the high formwork overall comprises the following steps: the monitoring equipment is arranged at a proper position on the periphery of the high formwork and used for monitoring the overall condition of the high formwork; the installation of the monitoring device at the proper position of the periphery of the high formwork comprises the following steps: an inclination sensor and a displacement sensor.
In the above embodiment, specifically, the monitoring of the local situation of the high formwork is achieved by installing the monitoring device in each divided area of the high formwork, and the monitoring of the overall situation of the high formwork is achieved by installing the monitoring device in the overall periphery of the high formwork.
Step S104, obtaining original information x of each divided area of the high formwork through a sensor i And overall information X, the original information X i And the whole information X are vectors, wherein the original information X i The vertical displacement, the horizontal displacement, the vertical rod axial force and the vertical rod inclination angle are parameters; the whole information X comprises whole vertical displacement, horizontal displacement and vertical rod inclination angle; specifically, the original information x of each divided area of the high formwork is obtained through various sensors i And overall information X; wherein the vertical displacement and the horizontal displacement are obtained by a displacement sensor, the vertical rod axial force is obtained by an axial pressure sensor,the tilt angle of the vertical rod is obtained by a tilt angle sensor.
In the above embodiment, specifically, the installed sensor is accessed to the computer, and the computer sends a request for acquiring the original information of each divided area and the overall information of the high formwork to the monitoring device; and then the monitoring equipment collects the original information of each divided area and the whole information of the high formwork and feeds the information back to the computer.
Step S105, obtaining a data set { x } of each divided region by carrying out engineering mechanics analysis and risk hypothesis evaluation on each divided region and the whole structure of the high formwork i1 ,x i2 ,…x in Data set of sum whole structure { X } 1 ,X 2 ,…X m -a }; wherein each element in each dataset represents a vector, x in Representing nth data information corresponding to the ith divided area obtained after engineering mechanical analysis and risk hypothesis evaluation; x is X m The mth data information of the overall structure obtained after engineering mechanics analysis and risk hypothesis evaluation is represented; the risk hypothesis evaluation includes: a hypothetical assessment of when there is no risk and when there is a risk; through evaluation, a series of data sets corresponding to each divided region when no risk exists and each divided region when the risk exists and a series of data sets corresponding to the whole structure when the risk does not exist and each divided region when the risk exists are obtained respectively.
In the above embodiment, specifically, performing engineering mechanics analysis and risk hypothesis evaluation on each divided region and the overall structure of the high formwork includes: data set { x ] of each divided region obtained by carrying out engineering mechanics analysis and risk hypothesis evaluation on each divided region of high formwork i1 ,x i2 ,…x in The data set { X } of the overall structure obtained by carrying out engineering mechanics analysis and risk hypothesis evaluation on the high-formwork overall structure comprises data with risk and data without risk 1 ,X 2 ,…X m The data with risk and the data without risk are included in the }.
In the above embodiment, preferably, the specific method for performing risk hypothesis assessment on each divided area and the overall structure of the high formwork is as follows: when carrying out risk hypothesis evaluation on a certain divided area, judging that the divided area is in a certain state and is not at risk through hypothesis and mechanical analysis, and extracting data of the divided area at the moment, namely, the data is not at risk; if it is determined that the divided area is at risk in a certain state by hypothesis and mechanical analysis, the data at the time of the divided area is extracted, namely, the risk exists.
Step S106, classifying the data sets of the divided areas by adopting a Gaussian mixture clustering algorithm; the posterior probability and the cluster division function of the Gaussian mixture clustering algorithm are used for respectively obtaining the cluster division probability ranges of the existing risk and the non-existing risk of each division area and the whole structure of the high formwork through whether the risks exist in the cluster division; specifically, the data set obtained in step S105 is classified by a gaussian mixture clustering algorithm, so as to obtain posterior probability and amount cluster partition functions of the gaussian mixture clustering algorithm of each partition area and the overall structure respectively.
In the above embodiment, specifically, classifying the data set in step S105 by using the gaussian mixture clustering algorithm includes: a) Setting the number of Gaussian mixture components as k, and initializing model parameters of Gaussian mixture distribution; b) Preliminary calculation of x by initialized model parameters of Gaussian mixture distribution j Posterior probability gamma of (2) ji The method comprises the steps of carrying out a first treatment on the surface of the c) Continuously updating the model parameters of the Gaussian mixture distribution, and continuously repeating the step b) until a stopping condition is reached; d) Finally determining x through a maximum value function of posterior probability j Cluster division of (a); e) Final output cluster partition c= { C 1 ,C 2 ,…,C k -a }; the reaching stop condition is as follows: if the maximum iteration round number is reached; will history data information set { X ] i After classification by a gaussian mixture clustering algorithm, one cluster with the most densely distributed sample data sets is used as a main classification part, and all the rest sample data sets of other clusters are used as other classification parts.
In the above embodiment, the calculation formula of the posterior probability is:
wherein, gamma ji For posterior probability, α i 、u i Sum sigma i Representing sample x j Parameters of the corresponding ith Gaussian mixture component, α i >0 is the corresponding mixing coefficient, u i Representing the mean vector sum Σ i Representing a covariance matrix; k represents the composition of the Gaussian mixture distribution and k Gaussian mixture components, alpha h 、u h Sum sigma h Parameters indicating any one of the gaussian mixture components in the gaussian mixture distribution.
The cluster division function has the expression:
wherein, gamma ji Representing a sample x determined by the ith Gaussian mixture component j Posterior probability, eta j Representing sample x j Is marked by the final cluster division.
In the above embodiment, specifically, the final output cluster division c= { C 1 ,C 2 ,…,C k A plurality of clusters in the process are divided into clusters without risk, and a plurality of clusters are divided into clusters with risk; classifying each divided area and the whole structure through a Gaussian mixture clustering algorithm, and sequencing clusters in cluster division to obtain a plurality of clusters with no risk in the middle, wherein the clusters with risk in the two ends are safer as the data information is closer to the middle; if the cluster with risk is at the left end, the smaller the posterior probability obtained in the cluster is, the greater the risk degree is; if the cluster with risk is at the right end, the greater the posterior probability is, the greater the risk degree is.
Step S107, the equipment is accessed into a computer, and the computer automatically sends and acquires the data information of each divided area and the whole structure through the monitoring equipment; then, the computer substitutes the acquired data information of each divided area and the whole structure into a posterior probability algorithm of a Gaussian mixture clustering algorithm, and judges whether each divided area and the whole structure have risks or not through cluster division; if the risk exists, notifying a construction site to suspend construction, notifying maintenance personnel to formulate an effective scheme according to the risk degree, and maintaining and reinforcing the region with the risk; specifically, a computer connected with the monitoring equipment is used for continuously sending a request for acquiring the data information of each divided area and the whole structure to the monitoring equipment, and the monitoring equipment directly extracts the data information of each divided area and the whole structure and feeds the data information back to the computer after receiving the request; after obtaining the data information fed back by the monitoring equipment, substituting the data information of each divided area and the whole structure into a posterior probability and a cluster dividing function corresponding to a Gaussian mixture clustering algorithm, and determining the cluster division of the data information of each divided area and the whole structure according to the posterior probability; and determining whether the data information of each divided area and the whole structure is at risk or not and the risk degree of the risk through cluster division.
In the above embodiment, specifically, if the data information of a certain divided area is input into the posterior probability and the cluster division function of the corresponding gaussian mixture clustering algorithm by inputting the data information of each divided area and the data information of the overall structure, and if the result proves that the input data information has no risk, the divided area corresponding to the data information is proved to have no risk; if the result proves that the input data information has risks, the risk of the divided area corresponding to the data information is proved; the characteristics are also provided when the overall structure of the high formwork is monitored and analyzed.
In the above embodiment, specifically, when each divided area and the whole of the high formwork are monitored, the extracted data information of each divided area and the data information of the whole structure are substituted into the corresponding data information of each divided area and the whole structure, and the posterior probability and the cluster division function of the corresponding gaussian mixture clustering algorithm are substituted, so that whether each divided area or the whole structure of the high formwork has risks is judged; it should be noted that when all the high formwork dividing areas and the whole structure are not at risk, the high formwork is not at risk; if the risk exists in the dividing area or the integral structure of the high formwork, the risk exists in the high formwork, timely early warning is needed at the moment, workers on the construction site are informed of stopping construction, the site is far away, and technicians are informed of maintaining and reinforcing according to the risk degree.
Preferably, the method for judging the risk degree is as follows: according to C= { C 1 ,C 2 ,…,C k Sorting according to the historical data information risk degree of each divided area and the whole structure, wherein the sorting criterion is as follows: the risk of intermediate data does not exist, and the risk degree from the middle to the two ends is gradually increased; therefore, if there is a risk in the same cluster and the cluster with the risk belongs to the left end, the smaller the obtained posterior probability is, the larger the risk is in the cluster; similarly, if the right end of the cluster data with risk exists, the larger the posterior probability obtained in the cluster is, the larger the risk is; therefore, if the data information of each divided area and the whole structure is collected, substituting the data information of each divided area and the whole structure into the posterior probability and the cluster dividing function of the corresponding Gaussian mixture clustering algorithm, and obtaining the cluster division of the data information belonging to the left end through calculation, wherein the probability in the cluster is small, and the risk degree is proved to be large; similarly, when the right end cluster is divided, the risk degree corresponding to the data information can be obtained; after determining the risk degree and the risk level, the technician is notified to perform targeted maintenance and reinforcement.
It is to be understood that the above-described embodiments are one or more embodiments of the invention, and that many other embodiments and variations thereof are possible in accordance with the invention; variations and modifications of the invention, which are intended to be within the scope of the invention, will occur to those skilled in the art without any development of the invention.
Claims (8)
1. A high formwork construction monitoring method based on a Gaussian mixture clustering algorithm is characterized by comprising the following steps:
1) According to the actual condition of the construction site, properly arranging a high formwork on the construction site;
2) Dividing the arranged high formwork into areas, and dividing the high formwork into different areas; the region division includes: randomly dividing the high formwork to obtain different dividing areas; however, the monitoring can be finished by using one set of monitoring equipment for each area after the division;
3) Monitoring of high formwork includes: monitoring each divided area and monitoring the whole high formwork;
4) The monitoring of each divided area comprises the following steps: respectively installing monitoring equipment in each divided area; the installing the monitoring equipment in each divided area comprises the following steps: an inclination angle sensor, a displacement sensor and a shaft pressure sensor; the monitoring of the high formwork overall comprises the following steps: the monitoring equipment is arranged at a proper position on the periphery of the high formwork and used for monitoring the overall condition of the high formwork; the installation of the monitoring device at the proper position of the periphery of the high formwork comprises the following steps: an inclination sensor and a displacement sensor;
5) Obtaining original information x of each divided area of high formwork through sensor i And overall information X, the original information X i And the whole information X are vectors, wherein the original information X i The vertical displacement, the horizontal displacement, the vertical rod axial force and the vertical rod inclination angle are parameters; the whole information X comprises whole vertical displacement, horizontal displacement and vertical rod inclination angle;
6) By carrying out engineering mechanical analysis and risk hypothesis evaluation on each divided area and the whole structure of the high formwork, a data set { x ] of each divided area is obtained i1 ,x i2 ,…x in Data set of sum whole structure { X } 1 ,X 2 ,…X m -a }; wherein each element in each dataset represents a vector, x in Representing nth data information corresponding to the ith divided area obtained after engineering mechanical analysis and risk hypothesis evaluation; x is X m The mth data information of the overall structure obtained after engineering mechanics analysis and risk hypothesis evaluation is represented; the risk hypothesis evaluation includes: a hypothetical assessment of when there is no risk and when there is a risk; through evaluation, a series of data sets corresponding to each divided area when no risk exists and each divided area when the risk exists and a series of data sets corresponding to the whole structure when the risk does not exist and the whole structure when the risk exists are respectively obtained;
7) Classifying the data sets of the divided areas by adopting a Gaussian mixture clustering algorithm; the posterior probability and the cluster division function of the Gaussian mixture clustering algorithm are used for respectively obtaining the cluster division probability ranges of the existing risk and the non-existing risk of each division area and the whole structure of the high formwork through whether the risks exist in the cluster division;
8) The equipment is accessed into a computer, and the computer automatically transmits and acquires the data information of each divided area and the whole structure through the monitoring equipment; then, the computer substitutes the acquired data information of each divided area and the whole structure into a posterior probability algorithm of a Gaussian mixture clustering algorithm, and judges whether each divided area and the whole structure have risks or not through cluster division; if the risk exists, notifying a construction site to suspend construction, notifying maintenance personnel to formulate an effective scheme according to the risk degree, and maintaining and reinforcing the region with the risk.
2. The high formwork construction monitoring method based on the Gaussian mixture clustering algorithm according to claim 1, wherein the actual condition of the railway station floor construction comprises the following steps: actual conditions of a construction site and design schemes of the whole construction.
3. The method for monitoring high formwork construction based on the Gaussian mixture clustering algorithm according to claim 1, wherein the randomly dividing the high formwork comprises the following steps: according to the limitation of the monitoring equipment during dividing; after the division of the areas is ensured, each divided area can be monitored safely through a set of monitoring equipment.
4. The high formwork construction monitoring method based on the Gaussian mixture clustering algorithm according to claim 1, wherein the monitoring of each divided area is to monitor each area of the high formwork which is randomly divided, and the monitoring comprises the monitoring of vertical displacement, horizontal displacement, vertical rod axial force and vertical rod inclination angle of the monitored area; the overall monitoring of the high formwork is to monitor the overall of the high formwork, and comprises monitoring of vertical displacement, horizontal displacement and vertical rod inclination angle of the overall of the high formwork.
5. The high formwork construction monitoring method based on the Gaussian mixture clustering algorithm according to claim 1, wherein the original information x of each divided area of the high formwork is obtained through a sensor i And the overall information X includes: the method comprises the steps that an installed sensor is accessed into a computer, and the computer sends a request for acquiring original information of each divided area and overall information of a high formwork to monitoring equipment; and then the monitoring equipment collects the original information of each divided area and the whole information of the high formwork and feeds the information back to the computer.
6. The method for monitoring the construction of the high formwork based on the Gaussian mixture clustering algorithm according to claim 1, wherein the steps of carrying out engineering mechanics analysis and risk hypothesis evaluation on each divided area and the whole structure of the high formwork comprise the following steps: data set { x ] of each divided region obtained by carrying out engineering mechanics analysis and risk hypothesis evaluation on each divided region of high formwork i1 ,x i2 ,…x in The data set { X } of the overall structure obtained by carrying out engineering mechanics analysis and risk hypothesis evaluation on the high-formwork overall structure comprises data with risk and data without risk 1 ,X 2 ,…X m The data with risk and the data without risk are included in the }.
7. The method for monitoring the high formwork construction based on the Gaussian mixture clustering algorithm according to claim 1, wherein the classifying the data set of the divided areas by the Gaussian mixture clustering algorithm comprises the following steps: the Gaussian mixture clustering algorithm is also called a probability model algorithm, and comprises the following steps: a) Setting the number of Gaussian mixture components as k, and initializing model parameters of Gaussian mixture distribution; b) Preliminary calculation of x by initialized model parameters of Gaussian mixture distribution j Posterior probability gamma of (2) ji The method comprises the steps of carrying out a first treatment on the surface of the c) Continuously updating the model parameters of the Gaussian mixture distribution, and continuously repeating the step b) until a stopping condition is reached; d) Finally determining x through a maximum value function of posterior probability j Cluster division of (a); e) Final output cluster partition c= { C 1 ,C 2 ,…,C k -a }; the reaching stop condition is as follows: if the maximum iteration round number is reached; will history data information set { X ] i After classification is carried out through a Gaussian mixture clustering algorithm, one cluster with the most densely distributed sample data sets is used as a main classification part, and all the rest sample data sets of the other clusters are used as other classification parts;
the calculation formula of the posterior probability is as follows:
wherein, gamma ji For posterior probability, α i 、u i Sum sigma i Representing sample x j Parameters of the corresponding ith Gaussian mixture component, α i >0 is the corresponding mixing coefficient, u i Representing the mean vector sum Σ i Representing a covariance matrix; k represents the composition of the Gaussian mixture distribution and k Gaussian mixture components, alpha h 、u h Sum sigma h Parameters representing any one of the gaussian mixture components in the gaussian mixture distribution;
the cluster division function has the expression:
wherein, gamma ji Representing a sample x determined by the ith Gaussian mixture component j Posterior probability, eta j Representing sample x j Is marked by the final cluster division.
8. The method for monitoring high formwork construction based on Gaussian mixture clustering algorithm according to claim 1, wherein the step of automatically sending and acquiring the data information of each divided area and the whole structure by the computer through the monitoring equipment comprises the following steps: continuously sending a request for acquiring the data information of each divided area and the whole structure to the monitoring equipment through the accessed computer, and feeding back the acquired data information to the computer after each monitoring equipment acquires the data information of each divided area and the whole structure of the high formwork; then the computer inputs the received data information into a Gaussian mixture clustering algorithm to obtain cluster division corresponding to the data information; judging whether the input data information has risks or not according to cluster division; if the data information is input into a Gaussian mixture clustering algorithm, dividing the obtained clusters into clusters without risk, and proving that the input data information does not have risk; if the data information is input into a Gaussian mixture clustering algorithm, the obtained clusters are divided into clusters with risks, and the input data information is proved to have risks.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311115627.7A CN117077535A (en) | 2023-08-31 | 2023-08-31 | High formwork construction monitoring method based on Gaussian mixture clustering algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311115627.7A CN117077535A (en) | 2023-08-31 | 2023-08-31 | High formwork construction monitoring method based on Gaussian mixture clustering algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117077535A true CN117077535A (en) | 2023-11-17 |
Family
ID=88716925
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311115627.7A Pending CN117077535A (en) | 2023-08-31 | 2023-08-31 | High formwork construction monitoring method based on Gaussian mixture clustering algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117077535A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110132353A (en) * | 2019-05-15 | 2019-08-16 | 上海荷福人工智能科技(集团)有限公司 | High-supported formwork safety monitoring method and system based on multisensor and artificial intelligence |
CN111428768A (en) * | 2020-03-18 | 2020-07-17 | 电子科技大学 | Hellinger distance-Gaussian mixture model-based clustering method |
CN113487843A (en) * | 2021-07-12 | 2021-10-08 | 苏州思萃融合基建技术研究所有限公司 | Construction site high formwork intelligent monitoring and early warning system based on digital twin technology |
WO2022179241A1 (en) * | 2021-02-24 | 2022-09-01 | 浙江师范大学 | Gaussian mixture model clustering machine learning method under condition of missing features |
CN116070790A (en) * | 2023-03-21 | 2023-05-05 | 中国建筑一局(集团)有限公司 | Prediction method and system for reducing major safety risk hidden danger of construction site |
CN219016814U (en) * | 2022-10-14 | 2023-05-12 | 上海建工集团股份有限公司 | Safety monitoring device for high formwork system |
CN116415161A (en) * | 2023-04-17 | 2023-07-11 | 中交第四航务工程局有限公司 | Fitting complementation method for geological drilling detection and different physical wave detection data of string-shaped karst cave |
-
2023
- 2023-08-31 CN CN202311115627.7A patent/CN117077535A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110132353A (en) * | 2019-05-15 | 2019-08-16 | 上海荷福人工智能科技(集团)有限公司 | High-supported formwork safety monitoring method and system based on multisensor and artificial intelligence |
CN111428768A (en) * | 2020-03-18 | 2020-07-17 | 电子科技大学 | Hellinger distance-Gaussian mixture model-based clustering method |
WO2022179241A1 (en) * | 2021-02-24 | 2022-09-01 | 浙江师范大学 | Gaussian mixture model clustering machine learning method under condition of missing features |
CN113487843A (en) * | 2021-07-12 | 2021-10-08 | 苏州思萃融合基建技术研究所有限公司 | Construction site high formwork intelligent monitoring and early warning system based on digital twin technology |
CN219016814U (en) * | 2022-10-14 | 2023-05-12 | 上海建工集团股份有限公司 | Safety monitoring device for high formwork system |
CN116070790A (en) * | 2023-03-21 | 2023-05-05 | 中国建筑一局(集团)有限公司 | Prediction method and system for reducing major safety risk hidden danger of construction site |
CN116415161A (en) * | 2023-04-17 | 2023-07-11 | 中交第四航务工程局有限公司 | Fitting complementation method for geological drilling detection and different physical wave detection data of string-shaped karst cave |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6937173B2 (en) | Prediction methods and systems for structural repairs in heavy aircraft maintenance | |
CN111625988A (en) | Bridge health management analysis and prediction system and method based on deep learning | |
CN109871975B (en) | Data mining-based fault first-aid repair processing duration prediction method | |
US20110178963A1 (en) | system for the detection of rare data situations in processes | |
CN110865924B (en) | Health degree diagnosis method and health diagnosis framework for internal server of power information system | |
JP2009274588A (en) | Aircraft soundness diagnostic device, method, and program | |
CN110703214A (en) | Weather radar state evaluation and fault monitoring method | |
CN117235655B (en) | Intelligent heat supply abnormal condition identification method and system based on federal learning | |
CN115650006B (en) | Elevator safety monitoring and early warning method and system based on big data | |
CN115098561B (en) | Method for extracting alarm threshold of cultural relic ontology monitoring data | |
CN117111544B (en) | Automatic-adaptation building internet of things monitoring method and system | |
CN115392089A (en) | Intelligent early warning method | |
CN117392815A (en) | Alarm method and system for secondary water supply based on Internet of things | |
CN117077535A (en) | High formwork construction monitoring method based on Gaussian mixture clustering algorithm | |
CN117670028A (en) | Dust removal system risk dynamic assessment and grading early warning method based on Internet of things monitoring | |
CN117807659A (en) | Building structure defect detection and correction method and system | |
CN110414800B (en) | Method and device for evaluating construction accident risk source of super high-rise building | |
CN112598319A (en) | Intelligent bridge operation and maintenance management method and system based on BIM, computer equipment and storage medium | |
CN117236173A (en) | Subway station floor slab high formwork construction monitoring and safety early warning method | |
CN116957534A (en) | Method for predicting replacement number of intelligent electric meter | |
CN111105075A (en) | Tower crane risk accident prediction method and system based on case-based reasoning | |
CN115481815A (en) | Thermal power plant load distribution system and method based on neural network | |
CN113239436B (en) | Steel bridge state grade assessment and prediction method | |
CN106462908B (en) | Maintenance management index calculation device and maintenance management index calculation method | |
CN108985564B (en) | QFD (quad Flat No-lead) and binary semantic-based FMEA (failure mode and effects analysis) 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 |