CN115545500B - Reinforcing steel bar engineering quality detection method and system for engineering supervision - Google Patents
Reinforcing steel bar engineering quality detection method and system for engineering supervision Download PDFInfo
- Publication number
- CN115545500B CN115545500B CN202211254740.9A CN202211254740A CN115545500B CN 115545500 B CN115545500 B CN 115545500B CN 202211254740 A CN202211254740 A CN 202211254740A CN 115545500 B CN115545500 B CN 115545500B
- Authority
- CN
- China
- Prior art keywords
- index
- steel bar
- structural
- engineering
- mechanical property
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 151
- 229910001294 Reinforcing steel Inorganic materials 0.000 title description 24
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 150
- 239000010959 steel Substances 0.000 claims abstract description 150
- 230000011218 segmentation Effects 0.000 claims abstract description 96
- 239000000463 material Substances 0.000 claims abstract description 37
- 238000010276 construction Methods 0.000 claims abstract description 19
- 230000002787 reinforcement Effects 0.000 claims description 62
- 238000003466 welding Methods 0.000 claims description 51
- 238000000034 method Methods 0.000 claims description 30
- 230000007797 corrosion Effects 0.000 claims description 27
- 238000005260 corrosion Methods 0.000 claims description 27
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 230000005856 abnormality Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims 2
- 238000003908 quality control method Methods 0.000 abstract description 7
- 238000007726 management method Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 239000011150 reinforced concrete Substances 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000005452 bending Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000004567 concrete Substances 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 230000003014 reinforcing effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
Images
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
- G06Q10/06395—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
- 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
- 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
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Working Measures On Existing Buildindgs (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a steel bar engineering quality detection method and system for engineering supervision, which relate to the field of intelligent construction sites and comprise the following steps: performing structure segmentation on a steel bar project to be detected, generating a steel bar structure segmentation result, and clustering the steel bar structure segmentation result by matching a steel bar material grade set to generate a steel bar structure clustering result; the quality detection indexes comprise mechanical property indexes and structural size indexes; constructing a quality detection model; evaluating the clustering result of the steel bar structure according to the mechanical property index and the structural dimension index to generate a mechanical property index characteristic value and a structural dimension index characteristic value; inputting the mechanical property index characteristic value and the structural dimension index characteristic value into a quality detection model, generating a disqualified index, and sending the disqualified index to an engineering supervision and management terminal. The technical problem of low treatment efficiency caused by the fact that quality control needs to compare and screen each index one by one in the prior art is solved.
Description
Technical Field
The invention relates to the technical field of intelligent construction sites, in particular to a steel bar engineering quality detection method and system for engineering supervision.
Background
The engineering supervision plays a vital role in the work of controlling the engineering quality, and the quality control of the reinforced bar engineering is an important link of the whole engineering project in the building engineering, along with the development of an intelligent construction site, a plurality of links of the engineering face the necessary requirement of improving the efficiency, and the traditional engineering supervision mode and the advanced construction mode generate contradiction difficult to reconcile, so that the improvement of the efficiency of the engineering supervision is the current primary task.
At present, the quality control process of the steel bar engineering mainly detects various performances of a material sample, evaluates an engineering structure and judges whether the material sample meets the unified engineering standard, the mode can be processed when facing smaller engineering projects, but multi-position multi-thread evaluation is required for each index when facing larger and more complex engineering projects, and the efficiency is low.
In summary, in the prior art, as quality control needs to compare and screen each index one by one, the technical problem of lower treatment efficiency exists.
Disclosure of Invention
The method and the system for detecting the quality of the reinforced bar engineering for engineering supervision solve the technical problem that in the prior art, as quality control needs to compare and screen each index one by one, the processing efficiency is low.
In view of the above problems, embodiments of the present application provide a method and a system for detecting quality of a reinforcement project for project supervision.
In a first aspect, the present application provides a method for detecting quality of a reinforced concrete bar project for project supervision, where the method applies a reinforced concrete bar project quality detection system for project supervision, the system includes a project supervision management terminal, and the method includes: carrying out structure segmentation on the steel bar project to be detected to generate a steel bar structure segmentation result; traversing the reinforcement structure segmentation result and matching reinforcement material grade sets; clustering the steel bar structure segmentation results according to the steel bar material grade set to generate a steel bar structure clustering result; obtaining quality detection indexes, wherein the quality detection indexes comprise mechanical property indexes and structural size indexes; constructing a quality detection model according to the mechanical property index and the structural size index; evaluating the clustering result of the steel bar structure according to the mechanical property index and the structural dimension index to generate a mechanical property index characteristic value and a structural dimension index characteristic value; inputting the mechanical property index characteristic value and the structural dimension index characteristic value into the quality detection model, generating a disqualification index, and sending the disqualification index to an engineering supervision management terminal.
On the other hand, the application provides a steel bar engineering quality detection system for engineering supervision, wherein the system comprises an engineering supervision management terminal, and the system comprises: the structure segmentation module is used for carrying out structure segmentation on the steel bar project to be detected and generating a steel bar structure segmentation result; the grade matching module is used for traversing the segmentation result of the reinforced bar structure and matching grade sets of reinforced bar materials; the structure clustering module is used for clustering the steel bar structure segmentation results according to the steel bar material grade set to generate a steel bar structure clustering result; the quality index determining module is used for obtaining quality detection indexes, wherein the quality detection indexes comprise mechanical property indexes and structural size indexes; the model construction module is used for constructing a quality detection model according to the mechanical property index and the structural size index; the characteristic value evaluation module is used for evaluating the clustering result of the steel bar structure according to the mechanical property index and the structural size index to generate a mechanical property index characteristic value and a structural size index characteristic value; and the quality detection module is used for inputting the mechanical property index characteristic value and the structural dimension index characteristic value into the quality detection model, generating a disqualification index and sending the disqualification index to the engineering supervision and management terminal.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the steel bar construction method is characterized in that the steel bar construction method is divided into a plurality of steel bar structure categories according to the structural differences of the steel bar engineering; matching reinforcing steel bar material grade sets for various reinforcing steel bar structure types; reclustering a plurality of reinforcement structure categories according to the brands to obtain clustering results representing the same structure and the same composition brands; constructing an anomaly detection model according to the quality detection index; traversing the clustering result to evaluate the quality detection index to obtain an index characteristic value; inputting the index characteristic value into an anomaly detection model to obtain a disqualified index, and sending the disqualified index to a technical scheme of an engineering supervision and management terminal, wherein the reinforced engineering is classified according to the structure and the brand to be treated in a classified and unified way; by using the abnormal detection model, unqualified indexes in each category can be rapidly identified, and the technical effect of improving the quality detection efficiency of the steel bar engineering is achieved.
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
Fig. 1 is a schematic flow chart of a method for detecting quality of a reinforcement engineering for engineering supervision according to an embodiment of the present application;
fig. 2 is a schematic diagram of a reinforcement structure segmentation flow in a reinforcement engineering quality detection method for engineering supervision according to an embodiment of the present application;
fig. 3 is a schematic diagram of a screening flow of unqualified indexes in a steel bar project quality detection method for project supervision according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a steel reinforcement engineering quality detection system for engineering supervision according to an embodiment of the present application.
Reference numerals illustrate: the system comprises an engineering supervision and management terminal 001, a structure segmentation module 11, a brand matching module 12, a structure clustering module 13, a quality index determining module 14, a model building module 15, a characteristic value evaluation module 16 and a quality detection module 17.
Detailed Description
The technical scheme provided by the application has the following overall thought:
the embodiment of the application provides a steel bar engineering quality detection method and system for engineering supervision. The steel bar construction method is characterized in that the steel bar construction method is divided into a plurality of steel bar structure categories according to the structural differences of the steel bar engineering; matching reinforcing steel bar material grade sets for various reinforcing steel bar structure types; reclustering a plurality of reinforcement structure categories according to the brands to obtain clustering results representing the same structure and the same composition brands; constructing an anomaly detection model according to the quality detection index; traversing the clustering result to evaluate the quality detection index to obtain an index characteristic value; inputting the index characteristic value into an anomaly detection model to obtain a disqualified index, and sending the disqualified index to a technical scheme of an engineering supervision and management terminal, wherein the reinforced engineering is classified according to the structure and the brand to be treated in a classified and unified way; by using the abnormal detection model, unqualified indexes in each category can be rapidly identified, and the technical effect of improving the quality detection efficiency of the steel bar engineering is achieved.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a method for detecting quality of a reinforced bar project for project supervision, where the method applies a reinforced bar project quality detection system for project supervision, the system includes a project supervision management terminal, and the method includes the steps of:
s100: carrying out structure segmentation on the steel bar project to be detected to generate a steel bar structure segmentation result;
further, as shown in fig. 2, based on the structural division of the reinforcement engineering to be detected, a reinforcement structure division result is generated, and step S100 includes the steps of:
s110: acquiring a reinforcement cage project and a reinforcement welding net project according to the reinforcement project to be detected;
s120: acquiring structural features of the steel reinforcement framework engineering through an image acquisition device to obtain framework structural features, wherein the framework structural features comprise framework size features and framework shape features;
s130: performing structure segmentation on the steel reinforcement framework project according to the framework size characteristics and the framework shape characteristics to generate a framework structure segmentation result;
s140: the structural feature acquisition is carried out on the steel bar welding net engineering through the image acquisition device, and welding net structural features are generated, wherein the welding net structural features comprise welding net size features and welding net shape features;
s150: carrying out structural segmentation on the steel bar welded mesh engineering according to the welded mesh size characteristics and the welded mesh shape characteristics to generate a welded mesh structural segmentation result;
s160: and merging the framework structure segmentation result and the welding net structure segmentation result to generate the steel bar structure segmentation result.
Further, the step S160 includes the steps of:
s161: traversing the framework structure segmentation result and matching the framework structure distribution position parameters;
s162: traversing the welding net structure segmentation result and matching the welding net structure distribution position parameters;
s163: and solving a distribution position intersection of the skeleton structure distribution position parameter and the welding net structure distribution position parameter to generate the steel bar structure segmentation result.
Specifically, the reinforcement engineering to be detected, i.e. the reinforcement engineering in the engineering area where the supervision unit needs to perform quality control, and the content of the quality control includes, but is not limited to: mechanical property quality evaluation of the reinforced bar material, mechanical property evaluation of the reinforced bar structure, appearance size index evaluation of the reinforced bar material, appearance size index evaluation of the reinforced bar structure and the like.
In order to improve the quality detection efficiency of the reinforcement engineering, the structures of different areas of the reinforcement engineering are required to be divided into different categories, so that the subsequent unified processing is facilitated; the steel bar structure segmentation result refers to a result obtained by classifying the steel bar structures at different positions of the steel bar engineering to be detected according to the structural difference. The steel bar structure division result has a plurality of groups of data, and the steel bar engineering data of different areas with the same steel bar structure are stored in the same group of data. The determination process of the reinforcement structure segmentation result is preferably as follows:
the steel bar framework engineering and the steel bar welding net engineering are extracted from the steel bar engineering to be detected, the steel bar engineering is formed by welding single steel bar materials into a steel bar framework structure, and the steel bar framework structure is further welded into a steel bar welding net structure, so that structural segmentation is required according to the steel bar framework engineering and the steel bar welding net engineering, and the process is preferably as follows:
building a structural feature extraction model: based on big data acquisition reinforcing bar engineering information, reinforcing bar engineering information includes: reinforcing steel bar structure image information and reinforcing steel bar structure characteristic parameters: shape features and size features; according to the reinforcing steel bar structure image information and the reinforcing steel bar structure characteristic parameters: training a structural feature extraction model by using shape features and size features, wherein the training mode is as follows: constructing a convolutional neural network model frame, taking the image information of the reinforcement structure as input data, taking the shape characteristics and the size characteristics as output identification data, performing supervised training on the convolutional neural network model frame, and when the difference between the shape characteristics and the size characteristics output by training data of a continuous preset group of the convolutional neural network model frame and the output identification data is smaller than or equal to a preset value, regarding model convergence to generate a structural characteristic extraction model.
Carrying out structural segmentation according to the reinforcement cage engineering: the image acquisition device, preferably a high-definition camera, is used for acquiring images of the steel reinforcement framework engineering to obtain a steel reinforcement framework image acquisition result; inputting the image acquisition result of the steel reinforcement framework into a structural feature extraction model to obtain framework size features and framework shape features. And carrying out structural segmentation on the steel reinforcement framework engineering according to the framework size characteristics and the framework shape characteristics to obtain framework structure segmentation results representing a plurality of groups of segmentation results, wherein the same group of segmentation results have the same framework size characteristics and framework shape characteristics, and when the quality detection is carried out later, the steel reinforcement frameworks in the same group can be regarded as having the same detection standard, so that unified detection is facilitated.
Carrying out structural segmentation according to the steel bar welded mesh engineering: the image acquisition device, preferably a high-definition camera, is used for acquiring images of the steel bar welding net engineering to obtain a steel bar welding net image acquisition result; and inputting the image acquisition result of the steel bar welded mesh into a structural feature extraction model to obtain the size features and the shape features of the welded mesh. And carrying out structural segmentation on the steel bar welded mesh engineering according to the welded mesh size characteristics and the welded mesh shape characteristics to obtain welded mesh structure segmentation results representing a plurality of groups of segmentation results, wherein the same group of segmentation results have the same welded mesh size characteristics and welded mesh shape characteristics, and when the quality is detected in a later step, the same group of steel bar welded meshes can be regarded as having the same detection standard, so that unified detection is facilitated.
Further, the skeleton structure distribution position parameter refers to the geographical distribution position of the skeleton structure, namely geographical position coordinates; the distribution position parameters of the welding net structure refer to geographic distribution information, namely geographic position coordinates, of the welding net structure; according to the intersection of the geographic position coordinates, the framework structure segmentation result and the welding net structure segmentation result are fused to obtain a steel bar structure segmentation result, and in any group of data of the steel bar structure segmentation result, the same welding net structure is provided, so that the framework structures forming the welding net structure are also the same, and further the framework structures can be regarded as having uniform quality evaluation standards, and uniform rapid processing can be performed. Lays a foundation for improving the quality detection efficiency of the reinforcement engineering.
S200: traversing the reinforcement structure segmentation result and matching reinforcement material grade sets;
specifically, the brand of the reinforcing steel bar material refers to identification data representing information such as specification, diameter, grade, delivery date, manufacturer, qualification certificate and the like, and the brand specification of the reinforcing steel bar manufacturer is specifically required to be used. The concrete material data of the single steel bars forming the steel bar structure can be determined according to the brand of the steel bar materials, so that whether the single materials meet the index specified by the quality detection is conveniently analyzed. Even if the same reinforcement structure is segmented, different areas may still have different reinforcement brands, and then the reinforcement structure segmentation results can be further divided to obtain division results with the same brands, the same reinforcement framework structure and the same reinforcement welding net structure, and the refinement degree of the reinforcement engineering quality detection is improved on the premise of ensuring uniform treatment. The reinforcing steel bar brands of different reinforcing steel bar structures are provided with backup records during construction, so that reinforcing steel bar material brands can be directly matched with a reinforcing steel bar material brands set to be placed in a state to be responded, and the reinforcing steel bar brands are used in a later step.
S300: clustering the steel bar structure segmentation results according to the steel bar material grade set to generate a steel bar structure clustering result;
specifically, when the reinforcement material grade set is set in a state to be responded, the reinforcement material grade and the reinforcement structure segmentation result are all processed, and further structure clustering can be started. The clustering result of the steel bar structure is a result of further clustering the segmentation result of the steel bar structure by calling the reinforcement material grade set, and the clustering is performed according to the material grades of different structures aiming at the same segmentation result in the segmentation result of the steel bar structure, wherein the structures of the same grade are clustered to be the same type, and the materials of different grades are clustered to be different types. Any one of the categories in the reinforced structure clustering result represents the same material mark, the same reinforced skeleton structure and the same reinforced welded mesh structure, and the same category has the same material and structure so as to have similar mechanical properties and appearance indexes, so any one of the structures in the same category can represent the reinforced structure of the whole category, thereby being convenient for uniform and efficient processing and improving the efficiency of reinforced engineering quality detection.
S400: obtaining quality detection indexes, wherein the quality detection indexes comprise mechanical property indexes and structural size indexes;
specifically, the quality detection index refers to an index dimension set by a supervision unit, which needs to control the reinforcement engineering: the mechanical performance index refers to the mechanical performance index that needs to be met by the steel bar engineering structure, and is exemplified as follows: the specific clustering results of the steel bar structure are as follows: yield strength, tensile strength, and flexural strength of the rebar material; yield strength, tensile strength, and bending strength of the rebar framework; yield strength, tensile strength, bending strength, etc. of the rebar welded mesh. Structural dimension index refers to the apparent feature size that the rebar engineering structure needs to meet, such as, for example: shape characteristics, length characteristics, thickness characteristics, width characteristics, height characteristics, gap distance characteristics and the like, and clustering results of concrete reinforcing steel bar structures are as follows: shape characteristics, length characteristics, thickness characteristics, width characteristics, height characteristics and the like of the reinforcing steel bar material; shape characteristics, length characteristics, thickness characteristics, width characteristics, height characteristics, gap distance characteristics and the like of the reinforcement cage; shape characteristics, length characteristics, thickness characteristics, width characteristics, height characteristics, gap distance characteristics and the like of the steel bar welded mesh. And the index set to be detected is determined, so that the quality detection model is constructed by collecting data in the later step, and the quality detection model is used for rapidly evaluating the quality of the steel bar engineering.
S500: constructing a quality detection model according to the mechanical property index and the structural size index;
further, according to the mechanical performance index and the structural dimension index, a quality detection model is constructed, and step S500 includes the steps of:
s510: matching steel bar engineering statistical data according to the mechanical property index and the structural size index, wherein the steel bar engineering statistical data comprises a stability period parameter, a mechanical property index recording parameter and a structural size index recording parameter;
s520: adding the mechanical property index recording parameters and the structural size index recording parameters, of which the stability period parameters meet the preset period, into a quality detection reference parameter set, wherein any one of the mechanical property index recording parameters or the structural size index recording parameters occurs at least twice;
s530: and constructing the quality detection model according to the quality detection reference parameter set.
Specifically, the quality detection model is an intelligent model constructed based on an anomaly detection isolated forest, and the anomaly detection principle of the anomaly detection isolated forest is as follows: and the number of any one characteristic value is 2, wherein the characteristic value sets are matched with the standard value of the index, namely, the characteristic values of each index cannot cause great influence on the steel bar structure. When abnormality detection is performed, index data to be evaluated is added to a standard value of an index, and then an isolated tree is randomly divided a plurality of times, one index corresponding to each tree. If the index data to be evaluated is abnormal, the number of the index data is 1 independently, the index data is necessarily located on a certain leaf node of the isolated tree after multiple times of division, the division times can be set in a self-defined mode according to the total data quantity, and the average times of the abnormality is divided according to the optimized use history. If the index data to be evaluated is normal, the index data belongs to one of standard values of the index, the set division times are divided, and the index data is still difficult to divide, and is the normal index. Because different actual construction conditions in engineering have larger influence on indexes, the unified use standard indexes are low in adaptability, the data similar to the actual construction process are adopted for carrying out abnormality judgment, the applicability is higher, abnormal and normal indexes can be rapidly screened out in an isolated tree mode, and efficient quality detection is realized. The specific implementation process is as follows:
the steel bar engineering statistical data refers to a historical construction data set in the engineering which is counted according to the mechanical property index and the structural dimension index and is the same as the clustering result of the steel bar structure, and due to the universality of engineering construction and the standardization of the engineering, the data are widely and relatively recorded, so that the data are easy to collect.
The steel bar engineering statistics include: the stability period parameter, the mechanical property index recording parameter and the structural dimension index recording parameter, wherein the mechanical property index recording parameter refers to a detection result of mechanical property in a corresponding reinforcing steel bar structure; the structural dimension index recording parameters refer to the recording data of the structural dimension characteristics in the corresponding reinforcing steel bar structure; the stability period parameter refers to the stability period record data estimated by a supervision unit of the reinforcement engineering under the corresponding mechanical property index record parameter and structure size index record parameter, namely the predicted service life.
The quality detection reference parameter set is a characteristic value set of a quality index for representing the normal of the steel bar engineering. In the embodiment of the application, the quality detection reference parameter set is screened by using the stability age parameter, and the preset age refers to the shortest stability time of the preset screening quality detection reference parameter set; and adding mechanical property index recording parameters and structural size index recording parameters with stable age parameters meeting preset ages into quality detection reference parameter sets, wherein the number of the quality detection reference parameter sets of any one index is at least 2, if the number of the quality detection reference parameters of a certain index is 1 as a statistical result, copying the same data, and increasing the number by 2. The construction of the later step isolation tree is convenient, and the situation that convergence cannot be achieved is avoided. And constructing a quality detection model based on the abnormal detection isolated forest according to the quality detection reference parameter set, and waiting for the later step.
Further, according to the mechanical performance index and the structural dimension index, the step S510 further includes the steps of:
s511: performing corrosion characteristic extraction by traversing the clustering result of the steel bar structure to generate corrosion characteristic parameters, wherein the corrosion characteristic parameters comprise corrosion area quantity characteristics and corrosion area characteristics;
s512: and matching the mechanical property index and the structural dimension index with the steel bar engineering statistical data according to the number characteristics of the corrosion areas and the area characteristics of the corrosion areas.
Specifically, in order to ensure further refinement of each quality detection, corrosion characteristics in the clustering result, including the number characteristics of corrosion areas and the area characteristics of the corrosion areas, are collected and recorded as corrosion characteristic parameters. And further clustering the steel bar structure clustering results according to the number features and the area features of the corrosion areas to obtain clustering results with the same corrosion feature parameters, the same brands, the same frameworks and the same welding net, and collecting the steel bar engineering statistical data representing the mechanical property indexes and the structural dimension indexes according to the clustering results, thereby improving the refinement degree of quality detection.
S600: evaluating the clustering result of the steel bar structure according to the mechanical property index and the structural dimension index to generate a mechanical property index characteristic value and a structural dimension index characteristic value;
specifically, the mechanical property index characteristic value refers to a result obtained by sampling, mechanical analysis and evaluation of a reinforcing steel bar structure clustering result according to the mechanical property index, and as the same clustering can be uniformly processed, the sampling and analysis efficiency is higher, the mechanical analysis process is the traditional detection of stretching, bending resistance and the like, and the detection items correspond to the mechanical property indexes one by one; the structural size index refers to the result obtained by retrieving and storing the structural size of the material, the structural size of the framework and the structural size of the welding net in the clustering process. And storing the mechanical property index characteristic values and the structural dimension index characteristic values in groups according to the clustering result of the steel bar structure, and setting the mechanical property index characteristic values and the structural dimension index characteristic values in a state to be responded and waiting for later steps.
S700: inputting the mechanical property index characteristic value and the structural dimension index characteristic value into the quality detection model, generating a disqualification index, and sending the disqualification index to an engineering supervision management terminal.
Further, as shown in fig. 3, the step S700 of inputting the mechanical performance index feature value and the structural dimension index feature value into the quality detection model to generate a failure index includes the steps of:
s710: acquiring the quality detection reference parameter set according to the quality detection model;
s720: adding the mechanical property index characteristic value and the structural dimension index characteristic value into the quality detection reference parameter set to generate a data set to be detected;
s730: randomly dividing the data set to be detected for multiple times to generate an abnormal detection tree, and stopping when single data appear on leaf nodes of the abnormal detection tree or the preset dividing times are met;
s740: and adding the index corresponding to the single data into the unqualified index.
Further, the step S730 includes the steps of:
s731: performing cluster analysis on the data set to be detected according to the index type to generate a first cluster result and a second cluster result until an Nth cluster result;
s732: traversing the first clustering result to construct a first anomaly detection tree;
s733: traversing the N clustering result to construct an N abnormal detection tree;
s734: adding the first abnormality detection tree to the nth abnormality detection tree into the abnormality detection tree.
Specifically, the unqualified index refers to an index of unqualified quality detection, which is obtained by inputting a mechanical performance index characteristic value and a structural dimension index characteristic value into a quality detection model and performing anomaly evaluation according to an anomaly detection isolated forest, and comprises an unqualified position and an unqualified index type. The detection process is as follows:
adding the mechanical property index characteristic value and the structural dimension index characteristic value of any one cluster into the quality detection reference parameters of the corresponding cluster to generate a data set to be detected; performing cluster analysis on the data set to be detected according to the index type to obtain a first cluster result, and representing a characteristic value set of one index in any one cluster result from a second cluster result to an N cluster result; the first anomaly detection tree is a decision tree constructed by randomly dividing the characteristic value set of the first clustering result for a plurality of times according to an anomaly detection isolated forest, and the convergence condition is as follows: and converging when the number of data with 1 appears on a certain leaf node alone or the preset dividing times are met. And traversing the second clustering result to the N clustering result in sequence, constructing a second anomaly detection tree to the N anomaly detection tree, and forming an anomaly detection isolated forest. If the convergence condition of the data with the number of 1 appears in a certain leaf node alone, the index is abnormal and is marked as a disqualification index. The abnormal indexes are rapidly screened through abnormal detection of the isolated forest, and the quality detection efficiency of the steel bar engineering is improved.
In summary, the method and the system for detecting the quality of the steel bar project for project supervision provided by the embodiment of the application have the following technical effects:
1. the steel bar construction method is characterized in that the steel bar construction method is divided into a plurality of steel bar structure categories according to the structural differences of the steel bar engineering; matching reinforcing steel bar material grade sets for various reinforcing steel bar structure types; reclustering a plurality of reinforcement structure categories according to the brands to obtain clustering results representing the same structure and the same composition brands; constructing an anomaly detection model according to the quality detection index; traversing the clustering result to evaluate the quality detection index to obtain an index characteristic value; inputting the index characteristic value into an anomaly detection model to obtain a disqualified index, and sending the disqualified index to a technical scheme of an engineering supervision and management terminal, wherein the reinforced engineering is classified according to the structure and the brand to be treated in a classified and unified way; by using the abnormal detection model, unqualified indexes in each category can be rapidly identified, and the technical effect of improving the quality detection efficiency of the steel bar engineering is achieved.
Example two
Based on the same inventive concept as the method for detecting the quality of a reinforced concrete bar project used for project supervision in the foregoing embodiments, as shown in fig. 4, an embodiment of the present application provides a system for detecting the quality of a reinforced concrete bar project used for project supervision, where the system includes a project supervision management terminal 001, and the system includes:
the structure segmentation module 11 is used for carrying out structure segmentation on the steel bar engineering to be detected and generating a steel bar structure segmentation result;
the brand matching module 12 is used for traversing the division result of the reinforced bar structure and matching a reinforced bar material brand set;
the structure clustering module 13 is used for clustering the steel bar structure segmentation results according to the reinforced material grade set to generate a steel bar structure clustering result;
a quality index determination module 14 for obtaining quality detection indexes, wherein the quality detection indexes comprise mechanical performance indexes and structural size indexes;
the model construction module 15 is configured to construct a quality detection model according to the mechanical performance index and the structural dimension index;
the characteristic value evaluation module 16 is configured to evaluate the clustering result of the steel bar structure according to the mechanical performance index and the structural size index, and generate a mechanical performance index characteristic value and a structural size index characteristic value;
the quality detection module 17 is configured to input the mechanical performance index feature value and the structural dimension index feature value into the quality detection model, generate a failure index, and send the failure index to the engineering supervision and management terminal 001.
Further, the structure dividing module 11 performs the steps of:
acquiring a reinforcement cage project and a reinforcement welding net project according to the reinforcement project to be detected;
acquiring structural features of the steel reinforcement framework engineering through an image acquisition device to obtain framework structural features, wherein the framework structural features comprise framework size features and framework shape features;
performing structure segmentation on the steel reinforcement framework project according to the framework size characteristics and the framework shape characteristics to generate a framework structure segmentation result;
the structural feature acquisition is carried out on the steel bar welding net engineering through the image acquisition device, and welding net structural features are generated, wherein the welding net structural features comprise welding net size features and welding net shape features;
carrying out structural segmentation on the steel bar welded mesh engineering according to the welded mesh size characteristics and the welded mesh shape characteristics to generate a welded mesh structural segmentation result;
and merging the framework structure segmentation result and the welding net structure segmentation result to generate the steel bar structure segmentation result.
Further, the structure dividing module 11 performs the steps of:
traversing the framework structure segmentation result and matching the framework structure distribution position parameters;
traversing the welding net structure segmentation result and matching the welding net structure distribution position parameters;
and solving a distribution position intersection of the skeleton structure distribution position parameter and the welding net structure distribution position parameter to generate the steel bar structure segmentation result.
Further, the model building module 15 performs the steps of:
matching steel bar engineering statistical data according to the mechanical property index and the structural size index, wherein the steel bar engineering statistical data comprises a stability period parameter, a mechanical property index recording parameter and a structural size index recording parameter;
adding the mechanical property index recording parameters and the structural size index recording parameters, of which the stability period parameters meet the preset period, into a quality detection reference parameter set, wherein any one of the mechanical property index recording parameters or the structural size index recording parameters occurs at least twice;
and constructing the quality detection model according to the quality detection reference parameter set.
Further, the quality detection module 17 performs the steps of:
acquiring the quality detection reference parameter set according to the quality detection model;
adding the mechanical property index characteristic value and the structural dimension index characteristic value into the quality detection reference parameter set to generate a data set to be detected;
randomly dividing the data set to be detected for multiple times to generate an abnormal detection tree, and stopping when single data appear on leaf nodes of the abnormal detection tree or the preset dividing times are met;
and adding the index corresponding to the single data into the unqualified index.
Further, the quality detection module 17 performs the steps of:
performing cluster analysis on the data set to be detected according to the index type to generate a first cluster result and a second cluster result until an Nth cluster result;
traversing the first clustering result to construct a first anomaly detection tree;
traversing the N clustering result to construct an N abnormal detection tree;
adding the first abnormality detection tree to the nth abnormality detection tree into the abnormality detection tree.
Further, the model building module 15 performs the steps of:
performing corrosion characteristic extraction by traversing the clustering result of the steel bar structure to generate corrosion characteristic parameters, wherein the corrosion characteristic parameters comprise corrosion area quantity characteristics and corrosion area characteristics;
and matching the mechanical property index and the structural dimension index with the steel bar engineering statistical data according to the number characteristics of the corrosion areas and the area characteristics of the corrosion areas.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any of the methods to implement embodiments of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. 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 (7)
1. A method for detecting the quality of a reinforced bar project for project supervision, characterized in that the method applies a reinforced bar project quality detection system for project supervision, the system comprises a project supervision management terminal, the method comprises:
carrying out structure segmentation on the steel bar project to be detected to generate a steel bar structure segmentation result;
traversing the reinforcement structure segmentation result and matching reinforcement material grade sets;
clustering the steel bar structure segmentation results according to the steel bar material grade set to generate a steel bar structure clustering result;
obtaining quality detection indexes, wherein the quality detection indexes comprise mechanical property indexes and structural size indexes;
constructing a quality detection model according to the mechanical property index and the structural size index;
evaluating the clustering result of the steel bar structure according to the mechanical property index and the structural dimension index to generate a mechanical property index characteristic value and a structural dimension index characteristic value;
inputting the mechanical property index characteristic value and the structural dimension index characteristic value into the quality detection model to generate a disqualification index, and sending the disqualification index to an engineering supervision management terminal;
the method for carrying out structural segmentation on the steel bar engineering to be detected to generate a steel bar structure segmentation result comprises the following steps:
acquiring a reinforcement cage project and a reinforcement welding net project according to the reinforcement project to be detected;
acquiring structural features of the steel reinforcement framework engineering through an image acquisition device to obtain framework structural features, wherein the framework structural features comprise framework size features and framework shape features;
performing structure segmentation on the steel reinforcement framework project according to the framework size characteristics and the framework shape characteristics to generate a framework structure segmentation result;
the structural feature acquisition is carried out on the steel bar welding net engineering through the image acquisition device, and welding net structural features are generated, wherein the welding net structural features comprise welding net size features and welding net shape features;
carrying out structural segmentation on the steel bar welded mesh engineering according to the welded mesh size characteristics and the welded mesh shape characteristics to generate a welded mesh structural segmentation result;
and merging the framework structure segmentation result and the welding net structure segmentation result to generate the steel bar structure segmentation result.
2. The method of claim 1, wherein the merging the skeleton-structure segmentation result and the welded-mesh-structure segmentation result to generate the rebar-structure segmentation result comprises:
traversing the framework structure segmentation result and matching the framework structure distribution position parameters;
traversing the welding net structure segmentation result and matching the welding net structure distribution position parameters;
and solving a distribution position intersection of the skeleton structure distribution position parameter and the welding net structure distribution position parameter to generate the steel bar structure segmentation result.
3. The method of claim 1, wherein said constructing a quality inspection model based on said mechanical property index and said structural dimension index comprises:
matching steel bar engineering statistical data according to the mechanical property index and the structural size index, wherein the steel bar engineering statistical data comprises a stability period parameter, a mechanical property index recording parameter and a structural size index recording parameter;
adding the mechanical property index recording parameters and the structural size index recording parameters, of which the stability period parameters meet the preset period, into a quality detection reference parameter set, wherein any one of the mechanical property index recording parameters or the structural size index recording parameters occurs at least twice;
and constructing the quality detection model according to the quality detection reference parameter set.
4. The method of claim 3, wherein said inputting the mechanical property index feature value and the structural dimension index feature value into the quality inspection model to generate a failure index comprises:
acquiring the quality detection reference parameter set according to the quality detection model;
adding the mechanical property index characteristic value and the structural dimension index characteristic value into the quality detection reference parameter set to generate a data set to be detected;
randomly dividing the data set to be detected for multiple times to generate an abnormal detection tree, and stopping when single data appear on leaf nodes of the abnormal detection tree or the preset dividing times are met;
and adding the index corresponding to the single data into the unqualified index.
5. The method of claim 4, wherein the randomly dividing the data set to be detected a plurality of times to generate an anomaly detection tree comprises:
performing cluster analysis on the data set to be detected according to the index type to generate a first cluster result and a second cluster result until an Nth cluster result;
traversing the first clustering result to construct a first anomaly detection tree;
traversing the N clustering result to construct an N abnormal detection tree;
adding the first abnormality detection tree to the nth abnormality detection tree into the abnormality detection tree.
6. The method of claim 3, wherein matching rebar engineering statistics based on the mechanical property index and the structural dimension index, further comprises:
performing corrosion characteristic extraction by traversing the clustering result of the steel bar structure to generate corrosion characteristic parameters, wherein the corrosion characteristic parameters comprise corrosion area quantity characteristics and corrosion area characteristics;
and matching the mechanical property index and the structural dimension index with the steel bar engineering statistical data according to the number characteristics of the corrosion areas and the area characteristics of the corrosion areas.
7. A steel bar project quality detection system for project supervision, the system comprising a project supervision management terminal, the system comprising:
the structure segmentation module is used for carrying out structure segmentation on the steel bar project to be detected and generating a steel bar structure segmentation result;
the grade matching module is used for traversing the segmentation result of the reinforced bar structure and matching grade sets of reinforced bar materials;
the structure clustering module is used for clustering the steel bar structure segmentation results according to the steel bar material grade set to generate a steel bar structure clustering result;
the quality index determining module is used for obtaining quality detection indexes, wherein the quality detection indexes comprise mechanical property indexes and structural size indexes;
the model construction module is used for constructing a quality detection model according to the mechanical property index and the structural size index;
the characteristic value evaluation module is used for evaluating the clustering result of the steel bar structure according to the mechanical property index and the structural size index to generate a mechanical property index characteristic value and a structural size index characteristic value;
the quality detection module is used for inputting the mechanical property index characteristic value and the structural dimension index characteristic value into the quality detection model, generating a disqualification index and sending the disqualification index to the engineering supervision and management terminal;
the structure segmentation module executing steps comprise:
acquiring a reinforcement cage project and a reinforcement welding net project according to the reinforcement project to be detected;
acquiring structural features of the steel reinforcement framework engineering through an image acquisition device to obtain framework structural features, wherein the framework structural features comprise framework size features and framework shape features;
performing structure segmentation on the steel reinforcement framework project according to the framework size characteristics and the framework shape characteristics to generate a framework structure segmentation result;
the structural feature acquisition is carried out on the steel bar welding net engineering through the image acquisition device, and welding net structural features are generated, wherein the welding net structural features comprise welding net size features and welding net shape features;
carrying out structural segmentation on the steel bar welded mesh engineering according to the welded mesh size characteristics and the welded mesh shape characteristics to generate a welded mesh structural segmentation result;
and merging the framework structure segmentation result and the welding net structure segmentation result to generate the steel bar structure segmentation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211254740.9A CN115545500B (en) | 2022-10-13 | 2022-10-13 | Reinforcing steel bar engineering quality detection method and system for engineering supervision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211254740.9A CN115545500B (en) | 2022-10-13 | 2022-10-13 | Reinforcing steel bar engineering quality detection method and system for engineering supervision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115545500A CN115545500A (en) | 2022-12-30 |
| CN115545500B true CN115545500B (en) | 2023-05-30 |
Family
ID=84732923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211254740.9A Active CN115545500B (en) | 2022-10-13 | 2022-10-13 | Reinforcing steel bar engineering quality detection method and system for engineering supervision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115545500B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115907569B (en) * | 2023-03-02 | 2023-05-09 | 昆山市恒达精密机械工业有限公司 | Plastic product safety monitoring method and system based on Internet of things |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101274053B1 (en) * | 2011-04-07 | 2013-06-14 | 주식회사 싸이픽소프트 | Method for analyzing drawing file to estimate the amount of material for reinforced concrete frame construction |
| RU2467318C1 (en) * | 2011-06-16 | 2012-11-20 | ООО "Технологический институт энергетических обследований, диагностики и неразрушающего контроля "ВЕМО" | Method of multi-parameter control of building structures (transport tunnels, buildings, structures) |
| CN105372168B (en) * | 2015-12-08 | 2018-03-23 | 清华大学 | A kind of construction method of concrete pore three-dimensional structure |
| JP2019200120A (en) * | 2018-05-16 | 2019-11-21 | 公益財団法人鉄道総合技術研究所 | Performance evaluation method of reinforced concrete structure and performance evaluation system of reinforced concrete structure |
| CN108827855B (en) * | 2018-06-19 | 2020-08-11 | 青岛理工大学 | Porous concrete pore structure parameter obtaining and analyzing method |
| US10810734B2 (en) * | 2018-07-02 | 2020-10-20 | Sri International | Computer aided rebar measurement and inspection system |
| CN112033789A (en) * | 2020-09-02 | 2020-12-04 | 张海军 | Method and system for detecting strength of building material |
| CN112630270A (en) * | 2020-12-28 | 2021-04-09 | 青岛理工大学 | Method for detecting state of reinforcing steel bar in concrete structure |
| CN114331188A (en) * | 2021-12-31 | 2022-04-12 | 南通专猎网络科技有限公司 | Project value evaluation reference method and system based on big data |
-
2022
- 2022-10-13 CN CN202211254740.9A patent/CN115545500B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115545500A (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115545500B (en) | Reinforcing steel bar engineering quality detection method and system for engineering supervision | |
| CN115293463B (en) | Glass lens processing supervision method and system based on cutting quality prediction | |
| CN115511398B (en) | Welding quality intelligent detection method and system based on time sensitive network | |
| CN112766550A (en) | Power failure sensitive user prediction method and system based on random forest, storage medium and computer equipment | |
| CN109409780B (en) | Change processing method, device, computer equipment and storage medium | |
| CN112906738A (en) | Water quality detection and treatment method | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| CN116805203B (en) | Construction management method and system based on Internet of things | |
| CN113592314A (en) | Silk making process quality evaluation method based on sigma level | |
| CN107357941A (en) | A kind of system and method that watermark protocol data can be tested in real time | |
| CN109740890A (en) | A kind of influencing factors of quality correlation analysis | |
| CN115689320A (en) | Health management method and device for base station operation and computer readable storage medium | |
| CN116384781A (en) | Intelligent engineering construction data analysis system and method based on BIM technology | |
| CN112150098A (en) | Electric power facility anti-terrorism security supervision method and system | |
| CN108062603A (en) | Based on distribution power automation terminal life period of an equipment life-span prediction method and system | |
| CN114912678A (en) | Online automatic detection and early warning method and system for abnormal operation of power grid regulation and control | |
| CN117273550B (en) | Information management method of intelligent laboratory for food detection | |
| CN117375234B (en) | Automatic acceptance method and system for monitoring information of transformer substation | |
| CN116308293B (en) | Intelligent agricultural equipment management system and method based on digital platform | |
| CN111062827B (en) | Engineering supervision method based on artificial intelligence mode | |
| TW569373B (en) | Method for analyzing defect inspection parameters | |
| CN116910655A (en) | Intelligent ammeter fault prediction method based on device measurement data | |
| CN115311611A (en) | Steel bar counting method for production of prefabricated components of prefabricated building | |
| CN115879680A (en) | Steel surface defect judgment rule management system | |
| CN117787879B (en) | Full-cycle manufacturing management system of wet mixing granulation combined production line |
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 |