CN117808356A - Concrete member quality control method and system based on visual monitoring - Google Patents
Concrete member quality control method and system based on visual monitoring Download PDFInfo
- Publication number
- CN117808356A CN117808356A CN202311845945.9A CN202311845945A CN117808356A CN 117808356 A CN117808356 A CN 117808356A CN 202311845945 A CN202311845945 A CN 202311845945A CN 117808356 A CN117808356 A CN 117808356A
- Authority
- CN
- China
- Prior art keywords
- concrete member
- image data
- module
- concrete
- judging
- 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
- 239000004567 concrete Substances 0.000 title claims abstract description 493
- 238000003908 quality control method Methods 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 title claims abstract description 22
- 230000000007 visual effect Effects 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 71
- 238000012797 qualification Methods 0.000 claims abstract description 53
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims description 25
- 238000012937 correction Methods 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 6
- 229910000831 Steel Inorganic materials 0.000 claims description 4
- 239000010959 steel Substances 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007711 solidification Methods 0.000 claims description 2
- 230000008023 solidification Effects 0.000 claims description 2
- 238000010276 construction Methods 0.000 abstract description 9
- 230000007547 defect Effects 0.000 abstract description 7
- 230000002950 deficient Effects 0.000 abstract description 3
- 239000000463 material Substances 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 8
- 238000005266 casting Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 210000002435 tendon Anatomy 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011178 precast concrete Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention relates to the technical field of building engineering materials, in particular to a concrete member quality control method and system based on visual monitoring, comprising a control terminal, a capturing layer, an analysis layer and an evaluation layer; the control terminal is a main control terminal of the system and is used for sending out an execution command; the invention can provide necessary data support for system operation through uploading the specification parameters of concrete construction and collecting the image data of the concrete construction, thereby continuously judging the qualification of the concrete by combining the specification parameters of the concrete member and the collected image data of the concrete member, ensuring that the concrete member is accurately identified by defects and avoiding the defective concrete member with exposed ribs from being applied to constructional engineering.
Description
Technical Field
The invention relates to the technical field of building engineering materials, in particular to a concrete member quality control method and system based on visual monitoring.
Background
The concrete member refers to a building structural member formed by pouring concrete and steel bars, most of the current concrete members are prefabricated members, and after the pouring forming is completed, the concrete members are transported to the installation position of a construction site for further pouring installation.
The invention patent with application number 201910556744.4 discloses a concrete member pouring quality control method, which is characterized in that: the method comprises the following steps: s1, setting vibration parameters: s2, acquiring hopper weight information, hopper opening information, feeding mode information, concrete temperature information and environment temperature information in real time; s3, calculating the temperature difference between the concrete temperature and the environment temperature, judging whether the temperature difference meets the temperature difference setting range, if not, entering the next step, and if so, turning to S5; s4, adjusting the temperature of the concrete or the ambient temperature to enable the temperature difference to meet the requirement of a temperature difference setting range; s5, calculating flow information of the concrete in each feeding mode; s6, detecting the slump of the concrete: s7, inputting the vibration parameters and the concrete parameters into a neural network for training, obtaining a relation model of flow and slump, and establishing a relation between the flow and the slump of the concrete; s8, adjusting concrete mixing ratio and vibration parameters in real time according to the flow and slump values of the concrete; and S9, calculating the weight difference between the actual feeding amount and the budget feeding amount of the component according to the weight information of the hopper, and adjusting, checking and tracing in real time to realize the pouring quality control of the component.
The application aims at solving the problems: the concrete component with high quality requirement is characterized in that concrete parameters are needed to be mastered at any time in the casting process, the concrete mixing proportion is adjusted at any time, and the rough casting method cannot meet the requirement.
However, in the production process of the precast concrete member, due to various production errors, faults and other problems, the problem of exposed ribs of the ribs inside the concrete member can be caused, the problem can directly lead to the existence of huge defects of the concrete member to be stable, meanwhile, due to the fact that the concrete member is large in size, whether the exposed ribs of the concrete member exist or not is judged manually by observing the surface of the concrete member, the efficiency is poor, negligence is easy to occur, and the exposed ribs of the surface of the concrete member cannot be found.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides a concrete member quality control method and system based on visual monitoring, and solves the technical problems in the background art.
In order to achieve the above purpose, the invention is realized by the following technical scheme:
in the first aspect, the concrete member quality control system based on visual monitoring comprises a control terminal, a capturing layer, an analysis layer and an evaluation layer;
the control terminal is a main control terminal of the system and is used for sending out an execution command;
the method comprises the steps that specification parameters of a concrete member are input through a capturing layer, the capturing layer captures image data of the concrete member based on the specification parameters of the concrete member, and synchronously judges whether the concrete member is qualified or not based on the capturing result of the image data of the concrete member in a preliminary mode, an analysis layer synchronously receives the preliminary qualification judging result of the concrete member, receives the image data of the concrete member corresponding to the qualified concrete member in the capturing layer, analyzes the surface integrity of the concrete member based on the received image data of the concrete member, and an evaluation layer further receives the analysis result of the surface integrity of the concrete member in the analysis layer;
the analysis layer comprises a receiving module, an analysis module and a correction module, wherein the receiving module is used for receiving the corresponding image data of the concrete member with the preliminary judging result being qualified in the capturing layer, the analysis module is used for acquiring the image data of the concrete member received by the receiving module, the image data of the concrete member is applied to analyze the surface integrity of the concrete member, and the correction module is used for receiving the surface integrity of the concrete member analyzed by the analysis module and correcting the analysis result of the surface integrity of the concrete member;
the concrete member surface integrity analysis logic is expressed as:
wherein: k is the surface integrity of the concrete member; n is a set of pixel blocks in the concrete member image data;color feature vectors of the 1 st pixel block in the image data of the concrete member; n is n o The total amount of pixel blocks in the image data of the concrete member; />Is a standard color feature vector; θ is the image accuracy; u is the total amount of the surface of the concrete member on which the image data is not collected; f is the proportion of the concrete member image in the concrete member image data applied in the solving of the surface integrity rate k of the concrete member to the surface area of the concrete member;
wherein u is more than or equal to 1, the image precision theta is set based on the resolution of the image data of the concrete member during acquisition, the value of the image precision theta obeys, the higher the resolution of the image data of the concrete member is, the larger the value of the image precision theta is, otherwise, the smaller the image precision theta is set, the integrity rate k of the surface of the concrete member is used for representing the integrity rate of one surface of the concrete member, and the integrity rate of the surface of the concrete member is that: after k is calculated on all the acquired image data of the concrete member, the obtained value of k is accumulated on all the calculated k, and the standard color feature vector is obtained byIs the color characteristic vector presented by the concrete after solidification.
Further, the capturing layer comprises an uploading module, an acquisition module and a screening module, wherein the uploading module is used for uploading specification parameters of the concrete member, the acquisition module is used for acquiring image data of the concrete member, the screening module is used for receiving the image data of the concrete member acquired by the acquisition module, judging whether the concrete member is qualified or not based on the image shape of the concrete member in the image data of the concrete member, and screening the image data of the concrete member based on a qualified judging result and sending the image data of the concrete member to the analysis layer;
the specification parameters of the concrete member uploaded by the uploading module comprise: the system comprises a concrete member outer surface specification parameter, a concrete inner distributed steel bar distribution position parameter and a specification parameter, wherein an acquisition module is integrated by a plurality of groups of cameras, when each group of acquisition module acquires concrete member image data, the image acquisition view angle edge is tangent to the concrete member image, when the acquisition module acquires the concrete member image data, the image data acquisition direction is perpendicular to the surface of the concrete member, and the number of cameras for integrating the acquisition module obeys:
n 0 ＝n all -n rt -1；
wherein: n is n 0 The number of cameras; n is n all The total amount of the surface of the concrete member; n is n rt The number of the opening surfaces is the number of the surface opening surfaces of the concrete member.
Still further, the concrete member qualification logic in the screening module is expressed as:
wherein: j (i, J) is characteristic information of a pixel block in the image data of the concrete member; alpha is the gray average value of the image data of the concrete member; p (c) is the first-order probability distribution of the image data gray scale of the concrete member; j is; i is the gray level of the image data of the concrete member; j is the gray gradient of the image data of the concrete member; beta 2 Gray variance of image data of the concrete member; x-shaped articles k Kurtosis of image data for the concrete member; x-shaped articles s The degree of deviation of the image data of the concrete member; x-shaped articles m Energy for image data of the concrete member;a conversion coefficient that is entropy of the concrete member image data; x-shaped articles g Entropy of image data of the concrete member;a is the gray level increment of the image data of the concrete member; b is the gray gradient increment of the image data of the concrete member;
wherein J (i+a, j+b) is obtained by adding a, b based on J (i, J).
Further, the concrete member is placed on a solid-color plate surface different from the color of the surface of the concrete member when being processed by the system, the characteristic information J (i, J) of each pixel block in the collected concrete member image data is obtained through a concrete member qualification judging logic, the characteristic information J (i, J) of the solid-color plate surface on which the concrete member is placed is obtained through further application of the concrete member qualification judging logic, the characteristic information J (i, J) of the solid-color plate surface is used for traversing and searching the same item in the characteristic information J (i, J) of each pixel block in the obtained concrete member image data, the number of the searched same item is accumulated, the proportion of the accumulated result to the total number of the pixel blocks in the concrete member image data is obtained, a system end user manually sets a safety proportion judging threshold value based on the surface of the concrete member, and when the obtained proportion is within the safety proportion judging threshold value, the corresponding concrete member image data is judged to be qualified, otherwise, the corresponding proportion is judged to be unqualified;
when the system end user sets the safety proportion judging threshold value, the more the number of the surfaces of the concrete member is, the larger the safety proportion judging threshold value setting range is, and otherwise, the smaller the safety proportion judging threshold value setting range is.
Further, before analyzing the surface integrity of the concrete member, the analysis module performs median filtering processing on the applied concrete member image data, and the processing logic is expressed as:
wherein: h (x, y) is the processed concrete member image data; (i, j) is a pixel point in the original concrete member image data; s is the total amount of pixel points in the original concrete member image data; f (x, y) is original concrete member image data;
wherein a rectangular template of 3×3 is applied when the concrete member image data is subjected to the median filtering process.
Furthermore, the correction result of the concrete member surface integrity in the correction module is obtained by the following formula:
wherein: k' is the surface integrity of the corrected concrete member; k is the surface integrity of the concrete member; f (f) all The total area of the surface is collected for the image data of the concrete member; f (f) on The total surface area of the concrete member; u is the total amount of the surface of the concrete member on which the image data is not collected; n is n rt The number of the opening surfaces on the surface of the concrete member;
the correction module is used for manually controlling whether to participate in the operation of the analysis layer or not based on a user at the system end in the analysis layer.
Still further, the evaluation layer includes a setting module, a judging module and a feedback module, the setting module is used for setting a qualified judging threshold value of the concrete member, receiving the analysis result of the surface integrity of the concrete member corrected by the correcting module in the evaluation layer, the judging module is used for comparing the correction result of the surface integrity of the concrete member with the qualified judging threshold value of the concrete member, judging whether the correction result of the surface integrity of the concrete member is in the range of the qualified judging threshold value of the concrete member, if yes, the jump capturing layer operates, if no, the feedback module is triggered to operate, the feedback module is used for receiving the corrected surface integrity of the concrete member received by the judging module, synchronously acquiring the correction result of the surface integrity of the concrete member corresponding to the image data of each concrete member based on the corrected surface integrity of the concrete member, comparing the correction result with the qualified judging threshold value of the concrete member, acquiring the surface integrity of the concrete member not in the qualified judging threshold value of the concrete member, and finally acquiring the surface integrity of the concrete member not in the qualified judging threshold value of the concrete member, and controlling the image data of the corresponding concrete member not in the qualified judging threshold value of the concrete member as feedback terminal.
And further, after the feedback module is operated, synchronously executing the jump to the capturing layer for operation again.
Furthermore, the control terminal is electrically connected with an uploading module through a medium, the uploading module is electrically connected with a collecting module and a screening module through the medium, the control terminal and the screening module are electrically connected with a receiving module through the medium, the receiving module is electrically connected with an analyzing module and a correcting module through the medium, the control terminal and the correcting module are electrically connected with a setting module through the medium, and the setting module is electrically connected with a judging module and a feedback module through the medium.
In a second aspect, a method for controlling the quality of a concrete member based on visual monitoring includes the steps of:
step 1: uploading specification parameters of the concrete member, and collecting image data of the concrete member;
step 11: defining specification parameters of the concrete member and defining image data acquisition logic of the concrete member;
step 12: a preliminary qualification judging stage of the concrete member;
step 2: receiving concrete member image data, and analyzing the surface integrity rate of the concrete member based on the concrete member image data;
step 21: a median filtering processing stage of the concrete member image data;
step 22: a screening stage of concrete member image data;
step 3: receiving analysis results of the surface integrity of the concrete member, accumulating the analysis results, setting a qualification judgment threshold value, and comparing the accumulated analysis results with the qualification judgment threshold value to judge whether the concrete member is qualified or not;
step 4: continuing to execute the step 1 when the concrete member qualification judging result is qualified, judging that the judging result is unqualified, acquiring the concrete member image data from each analysis result source in the accumulated analysis results, feeding back the judging result and the acquired concrete member image data to a user side, and executing the step 1 after feeding back.
Compared with the prior art, the technical proposal provided by the invention has the following advantages that
The beneficial effects are that:
1. the invention provides a concrete member quality control system based on visual monitoring, which can provide necessary data support for system operation through uploading specification parameters of concrete construction and collecting image data of the concrete construction in the operation process, so that continuous qualification judgment is carried out on concrete by combining the specification parameters of the concrete member and the collected image data of the concrete member, accurate defect identification of the concrete member is ensured, and defective concrete members with exposed ribs are prevented from being applied to constructional engineering.
2. In the running process of the system, the preliminary qualification judgment is brought to the concrete member through the definition of the image data acquisition logic in the image data acquisition stage of the concrete frame, and the appearance defect of the concrete prefabricated member caused by insufficient mold filling can be effectively eliminated based on the preliminary qualification judgment of the concrete member.
3. When the system in the invention performs the whole rate analysis and calculation on the image data of the concrete member, the system can also perform the median filtering treatment on the image data of the concrete member, so that when the whole rate of the corresponding surface of the image data of the concrete member is calculated through the analysis of the image data of the concrete member, the system can perform the analysis and calculation by using the image with more obvious image characteristics, thereby further ensuring that the analysis and the calculation of the whole rate of the concrete member are more accurate.
4. The system further provides operation jump logic, so that the system has continuous operation conditions, the system operation is more intelligent, and the configuration of the method further maintains the stable operation of the system, and brings operation logic support for the system operation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic structural diagram of a concrete member quality control system based on visual monitoring;
FIG. 2 is a schematic flow chart of a method for controlling the quality of a concrete member based on visual monitoring;
FIG. 3 is a schematic view of the concrete member and the exploded construction of the internal ribs of the concrete member according to the present invention;
FIG. 4 is a schematic view of the view angle of the acquisition module of the present invention when acquiring image data of a concrete member;
reference numerals in the drawings represent respectively: 1. a concrete member; 2. bone tendons; 3. a camera is provided.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention is further described below with reference to examples.
Embodiment one:
the concrete member quality control system based on visual monitoring of the embodiment, as shown in fig. 1, comprises a control terminal, a capturing layer, an analysis layer and an evaluation layer;
the control terminal is a main control terminal of the system and is used for sending out an execution command;
the method comprises the steps that specification parameters of a concrete member are input through a capturing layer, the capturing layer captures image data of the concrete member based on the specification parameters of the concrete member, and synchronously judges whether the concrete member is qualified or not based on the capturing result of the image data of the concrete member in a preliminary mode, an analysis layer synchronously receives the preliminary qualification judging result of the concrete member, receives the image data of the concrete member corresponding to the qualified concrete member in the capturing layer, analyzes the surface integrity of the concrete member based on the received image data of the concrete member, and an evaluation layer further receives the analysis result of the surface integrity of the concrete member in the analysis layer;
the analysis layer comprises a receiving module, an analysis module and a correction module, wherein the receiving module is used for receiving the corresponding image data of the concrete member with the preliminary judging result being qualified in the capturing layer, the analysis module is used for acquiring the image data of the concrete member received by the receiving module, the image data of the concrete member is applied to analyze the surface integrity of the concrete member, and the correction module is used for receiving the surface integrity of the concrete member analyzed by the analysis module and correcting the analysis result of the surface integrity of the concrete member;
the concrete member surface integrity analysis logic is expressed as:
wherein: k is the surface integrity of the concrete member; n is a set of pixel blocks in the concrete member image data;color feature vectors of the 1 st pixel block in the image data of the concrete member; n is n o The total amount of pixel blocks in the image data of the concrete member; />Is a standard color feature vector; θ is the image accuracy; u is the total amount of the surface of the concrete member on which the image data is not collected; f is the proportion of the concrete member image in the concrete member image data applied in the solving of the surface integrity rate k of the concrete member to the surface area of the concrete member;
wherein u is more than or equal to 1, the image precision theta is set based on the resolution of the image data of the concrete member during acquisition, the value of the image precision theta obeys, the higher the resolution of the image data of the concrete member is, the larger the value of the image precision theta is, otherwise, the smaller the image precision theta is set, the integrity rate k of the surface of the concrete member is used for representing the integrity rate of one surface of the concrete member, and the integrity rate of the surface of the concrete member is that: after k is calculated on all collected image data of the concrete member, the calculated k is accumulated to obtain a value, and the standard color feature vectorThe color characteristic vector is presented after the concrete is solidified;
the capturing layer comprises an uploading module, an acquisition module and a screening module, wherein the uploading module is used for uploading specification parameters of the concrete member, the acquisition module is used for acquiring image data of the concrete member, the screening module is used for receiving the image data of the concrete member acquired by the acquisition module, judging whether the concrete member is qualified or not based on the image shape of the concrete member in the image data of the concrete member, and screening the image data of the concrete member based on a qualified judging result and sending the image data of the concrete member to the analysis layer;
the specification parameters of the concrete member uploaded by the uploading module comprise: the system comprises a concrete member outer surface specification parameter, a concrete inner distributed steel bar distribution position parameter and a specification parameter, wherein an acquisition module is integrated by a plurality of groups of cameras, when each group of acquisition module acquires concrete member image data, the image acquisition view angle edge is tangent to the concrete member image, when the acquisition module acquires the concrete member image data, the image data acquisition direction is perpendicular to the surface of the concrete member, and the number of cameras for integrating the acquisition module obeys:
n 0 ＝n all -n rt -1；
wherein: n is n 0 The number of cameras; n is n all The total amount of the surface of the concrete member; n is n rt The number of the opening surfaces on the surface of the concrete member;
the correction result of the concrete member surface integrity in the correction module is obtained by the following formula:
wherein: k' is the surface integrity of the corrected concrete member; k is the surface integrity of the concrete member; f (f) all The total area of the surface is collected for the image data of the concrete member; f (f) on The total surface area of the concrete member; u is the total amount of the surface of the concrete member on which the image data is not collected; n is n rt The number of the opening surfaces on the surface of the concrete member;
the correction module is used for manually controlling whether to participate in the operation of the analysis layer or not based on a system end user in the analysis layer;
the assessment layer comprises a setting module, a judging module and a feedback module, wherein the setting module is used for setting a concrete member qualification judging threshold value, receiving a concrete member surface integrity analysis result corrected by the correcting module in the assessment layer, comparing the concrete member surface integrity correcting result with the concrete member qualification judging threshold value, judging whether the concrete member surface integrity correcting result is within the concrete member qualification judging threshold value range, if so, skipping to capture layer operation, if not, triggering the feedback module to operate, and if not, synchronously acquiring corresponding source concrete member image data based on the corrected concrete member surface integrity, further acquiring the concrete member surface integrity corresponding to each concrete member image data, comparing the concrete member surface integrity not within the concrete member qualification judging threshold value, and taking the finally acquired concrete member surface integrity not within the concrete member qualification judging threshold value as feedback content, and feeding back the corresponding concrete member image data to the control terminal;
after the feedback module is operated, synchronously executing the jump to the capturing layer for operation again;
the control terminal is electrically connected with an uploading module through a medium, the uploading module is electrically connected with a collecting module and a screening module through the medium, the control terminal and the screening module are electrically connected with a receiving module through the medium, the receiving module is electrically connected with an analyzing module and a correcting module through the medium, the control terminal and the correcting module are electrically connected with a setting module through the medium, and the setting module is electrically connected with a judging module and a feedback module through the medium.
In this embodiment, the uploading module operates to upload the specification parameters of the concrete member, the collecting module synchronously collects the image data of the concrete member, the screening module post-operates to receive the image data of the concrete member collected by the collecting module, determine whether the concrete member is qualified based on the image shape of the concrete member in the image data of the concrete member, screen the image data of the concrete member based on the qualification determination result and send the image data of the concrete member to the analyzing layer, the receiving module further operates to receive the image data corresponding to the concrete member whose preliminary determination result is qualified in the capturing layer, the analyzing module post-operates to acquire the image data of the concrete member received by the receiving module, apply the image data of the concrete member to analyze the surface integrity rate of the concrete member, then receive the image data of the concrete member analyzed by the correcting module to correct the surface integrity rate analysis result of the concrete member, finally set the qualification determination threshold of the concrete member by the setting module, receive the corrected concrete member surface integrity rate analysis result by the correcting module in the evaluating layer, further compare the concrete member surface integrity rate correction result with the concrete member qualification determination threshold based on the qualification determination result of the concrete member, determine whether the surface integrity rate correction of the concrete member is in the qualification determination threshold is within a range, the failure rate of the concrete member, the image data corresponding to the image receiving module receives the corrected result based on the image data of the surface integrity rate of the surface of the concrete member, and the image data is further acquired by the correcting module, comparing the surface integrity rate of the concrete member which is not in the concrete member qualification judgment threshold value with the concrete member qualification judgment threshold value, and feeding back corresponding concrete member image data serving as feedback content to a control terminal by using the finally obtained surface integrity rate of the concrete member which is not in the concrete member qualification judgment threshold value;
referring to fig. 3, reference numerals in the drawings correspond to the concrete member 1 and the tendon 2, respectively, and the drawings further illustrate main application scenarios of the system in the present invention;
referring to fig. 4, reference numerals in the drawing correspond to the concrete member 1 and the camera 3, respectively, and the camera further shows the acquisition view angle and logic when the system operates to acquire the image data of the concrete member based on the arrow in the drawing.
Embodiment two:
on the aspect of implementation, on the basis of the embodiment 1, the embodiment further specifically describes a concrete member quality control system based on visual monitoring in the embodiment 1 with reference to fig. 1:
the concrete member qualification judgment logic in the screening module is expressed as:
wherein: j (i, J) is characteristic information of a pixel block in the image data of the concrete member; alpha is the gray average value of the image data of the concrete member; p (c) is the first-order probability distribution of the image data gray scale of the concrete member; j is; i is the gray level of the image data of the concrete member; j is the gray gradient of the image data of the concrete member; beta 2 Gray variance of image data of the concrete member; x-shaped articles k Kurtosis of image data for the concrete member; x-shaped articles s The degree of deviation of the image data of the concrete member; x-shaped articles m Energy for image data of the concrete member;a conversion coefficient that is entropy of the concrete member image data; x-shaped articles g Is coagulationEntropy of the earth member image data; a is the gray level increment of the image data of the concrete member; b is the gray gradient increment of the image data of the concrete member;
wherein J (i+a, j+b) is obtained based on J (i, J) after adding a, b;
when the concrete member is processed by the system, the concrete member is placed on a pure-color plate surface different from the color of the surface of the concrete member, the characteristic information J (i, J) of each pixel block in the collected image data of the concrete member is obtained through a concrete member qualification judging logic, the characteristic information J (i, J) of the pure-color plate surface on which the concrete member is placed is obtained through further application of the concrete member qualification judging logic, the characteristic information J (i, J) of the pure-color plate surface is used for traversing and searching the same item in the characteristic information J (i, J) of each pixel block in the obtained image data of the concrete member, the number of the searched same item is accumulated, the proportion of the accumulated result to the total number of the pixel blocks in the image data of the concrete member is obtained, a system end user manually sets a safety proportion judging threshold value based on the surface of the concrete member, when the obtained proportion is within the safety proportion judging threshold value, the corresponding image data of the concrete member is judged to be qualified, and otherwise, the corresponding image data of the concrete member is judged to be unqualified;
when the system end user sets the safety proportion judging threshold value, the more the number of the surfaces of the concrete member is, the larger the safety proportion judging threshold value setting range is, and otherwise, the smaller the safety proportion judging threshold value setting range is.
Through the formula calculation and the arrangement, the specified logic support is further provided for the qualification judgment of the concrete member by the operation of the screening module, the system is ensured to be capable of carrying out preliminary screening on the concrete member based on the operation logic of the screening module, and the definition is brought to the image data of the concrete member received by the receiving module in the system.
As shown in fig. 1, before analyzing the surface integrity of the concrete member, the analysis module performs median filtering processing on the applied image data of the concrete member, where the processing logic is expressed as:
wherein: h (x, y) is the processed concrete member image data; (i, j) is a pixel point in the original concrete member image data; s is the total amount of pixel points in the original concrete member image data; f (x, y) is original concrete member image data;
wherein a rectangular template of 3×3 is applied when the concrete member image data is subjected to the median filtering process.
According to the formula calculation, further processing can be provided for the concrete member image data before the qualification judgment of the concrete member of a user, so that the qualification judgment of the concrete member is performed by the processed concrete member image data, and the qualification judgment result is more accurate.
Embodiment III:
on the aspect of implementation, on the basis of the embodiment 1, the embodiment further specifically describes a concrete member quality control system based on visual monitoring in the embodiment 1 with reference to fig. 2:
the concrete member quality control method based on visual monitoring comprises the following steps:
step 1: uploading specification parameters of the concrete member, and collecting image data of the concrete member;
step 11: defining specification parameters of the concrete member and defining image data acquisition logic of the concrete member;
step 12: a preliminary qualification judging stage of the concrete member;
step 2: receiving concrete member image data, and analyzing the surface integrity rate of the concrete member based on the concrete member image data;
step 21: a median filtering processing stage of the concrete member image data;
step 22: a screening stage of concrete member image data;
step 3: receiving analysis results of the surface integrity of the concrete member, accumulating the analysis results, setting a qualification judgment threshold value, and comparing the accumulated analysis results with the qualification judgment threshold value to judge whether the concrete member is qualified or not;
step 4: continuing to execute the step 1 when the concrete member qualification judging result is qualified, judging that the judging result is unqualified, acquiring the concrete member image data from each analysis result source in the accumulated analysis results, feeding back the judging result and the acquired concrete member image data to a user side, and executing the step 1 after feeding back.
In summary, in the above embodiment, the system can provide necessary data support for the system operation through uploading the specification parameters of the concrete construction and collecting the image data of the concrete construction in the operation process, so that the concrete is continuously qualified by combining the specification parameters of the concrete member and the collected image data of the concrete member, thereby ensuring accurate defect identification of the concrete member and avoiding the defective concrete member with exposed ribs from being applied to the construction engineering; in the operation process of the system, the preliminary qualification judgment is brought to the concrete member through the definition of image data acquisition logic in the image data acquisition stage of the concrete frame, and the appearance defect of the concrete prefabricated member caused by insufficient mold filling can be effectively eliminated based on the preliminary qualification judgment of the concrete member; meanwhile, when the system performs complete rate analysis and calculation on the image data of the concrete member, median filtering processing can be performed on the image data of the concrete member, so that when the complete rate of the corresponding surface of the image data of the concrete member is calculated through the analysis of the image data of the concrete member, the system can perform analysis and calculation by using images with more obvious image characteristics, and the analysis and the calculation of the complete rate of the concrete member by the system are more accurate; in addition, the system further provides operation jump logic, so that the system has continuous operation conditions, and the system operation is more intelligent.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The concrete member quality control system based on visual monitoring is characterized by comprising a control terminal, a capturing layer, an analysis layer and an evaluation layer;
the control terminal is a main control terminal of the system and is used for sending out an execution command;
the method comprises the steps that specification parameters of a concrete member are input through a capturing layer, the capturing layer captures image data of the concrete member based on the specification parameters of the concrete member, and synchronously judges whether the concrete member is qualified or not based on the capturing result of the image data of the concrete member in a preliminary mode, an analysis layer synchronously receives the preliminary qualification judging result of the concrete member, receives the image data of the concrete member corresponding to the qualified concrete member in the capturing layer, analyzes the surface integrity of the concrete member based on the received image data of the concrete member, and an evaluation layer further receives the analysis result of the surface integrity of the concrete member in the analysis layer;
the analysis layer comprises a receiving module, an analysis module and a correction module, wherein the receiving module is used for receiving the corresponding image data of the concrete member with the preliminary judging result being qualified in the capturing layer, the analysis module is used for acquiring the image data of the concrete member received by the receiving module, the image data of the concrete member is applied to analyze the surface integrity of the concrete member, and the correction module is used for receiving the surface integrity of the concrete member analyzed by the analysis module and correcting the analysis result of the surface integrity of the concrete member;
the concrete member surface integrity analysis logic is expressed as:
wherein: k is the surface integrity of the concrete member; n is a set of pixel blocks in the concrete member image data;color feature vectors of the 1 st pixel block in the image data of the concrete member; n is n o The total amount of pixel blocks in the image data of the concrete member;is a standard color feature vector; θ is the image accuracy; u is the total amount of the surface of the concrete member on which the image data is not collected; f is the proportion of the concrete member image in the concrete member image data applied in the solving of the surface integrity rate k of the concrete member to the surface area of the concrete member;
wherein u is more than or equal to 1, the image precision theta is set based on the resolution of the image data of the concrete member during acquisition, the value of the image precision theta obeys, the higher the resolution of the image data of the concrete member is, the larger the value of the image precision theta is, otherwise, the smaller the image precision theta is set, the integrity rate k of the surface of the concrete member is used for representing the integrity rate of one surface of the concrete member, and the integrity rate of the surface of the concrete member is that: after k is calculated on all the acquired image data of the concrete member, the obtained value of k is accumulated on all the calculated k, and the standard color feature vector is obtained byIs the color characteristic vector presented by the concrete after solidification.
2. The concrete member quality control system based on visual monitoring according to claim 1, wherein the capturing layer comprises an uploading module, an acquisition module and a screening module, wherein the uploading module is used for uploading specification parameters of the concrete member, the acquisition module is used for acquiring image data of the concrete member, the screening module is used for receiving the image data of the concrete member acquired by the acquisition module, judging whether the concrete member is qualified or not based on the shape of the image of the concrete member in the image data of the concrete member, and screening the image data of the concrete member based on a qualified judging result and sending the image data of the concrete member to the analysis layer;
the specification parameters of the concrete member uploaded by the uploading module comprise: the system comprises a concrete member outer surface specification parameter, a concrete inner distributed steel bar distribution position parameter and a specification parameter, wherein an acquisition module is integrated by a plurality of groups of cameras, when each group of acquisition module acquires concrete member image data, the image acquisition view angle edge is tangent to the concrete member image, when the acquisition module acquires the concrete member image data, the image data acquisition direction is perpendicular to the surface of the concrete member, and the number of cameras for integrating the acquisition module obeys:
n 0 ＝n all -n rt -1；
wherein: n is n 0 The number of cameras; n is n all The total amount of the surface of the concrete member; n is n rt The number of the opening surfaces is the number of the surface opening surfaces of the concrete member.
3. The vision-based concrete component quality control system of claim 2, wherein the concrete component qualification decision logic in the screening module is expressed as:
wherein: j (i, J) is characteristic information of a pixel block in the image data of the concrete member; alpha is the gray average value of the image data of the concrete member; p (c) is the first-order probability distribution of the image data gray scale of the concrete member; j is; i is the gray level of the image data of the concrete member; j is the gray gradient of the image data of the concrete member; beta 2 Gray variance of image data of the concrete member; x-shaped articles k Kurtosis of image data for the concrete member; x-shaped articles s The degree of deviation of the image data of the concrete member; x-shaped articles m Energy for image data of the concrete member;a conversion coefficient that is entropy of the concrete member image data; x-shaped articles g Entropy of image data of the concrete member; a is the gray scale of the image data of the concrete memberStage increment; b is the gray gradient increment of the image data of the concrete member;
wherein J (i+a, j+b) is obtained by adding a, b based on J (i, J).
4. A visual monitoring-based concrete member quality control system according to claim 3, wherein the concrete member is placed on a solid-color plate surface different from the color of the surface of the concrete member when processed by the system, the safety proportion determination threshold is manually set by a system end user based on the surface of the concrete member by determining the characteristic information J (i, J) of each pixel block in the collected image data of the concrete member, then further determining the characteristic information J (i, J) of the solid-color plate surface on which the concrete member is placed by applying the concrete member qualification determination logic, traversing the same item in the characteristic information J (i, J) of the solid-color plate surface in the determined characteristic information J (i, J) of each pixel block in the image data of the concrete member, accumulating the number of the searched same item, determining the proportion of the accumulated result to the total amount of the pixel blocks in the image data of the concrete member, and if the determined proportion is within the safety proportion determination threshold, determining the corresponding image data of the concrete member is determined to be unqualified by applying the safety proportion determination threshold;
when the system end user sets the safety proportion judging threshold value, the more the number of the surfaces of the concrete member is, the larger the safety proportion judging threshold value setting range is, and otherwise, the smaller the safety proportion judging threshold value setting range is.
5. The vision-based concrete element quality control system of claim 1, wherein the analysis module performs a median filter process on the applied concrete element image data prior to analyzing the concrete element surface integrity, the processing logic representing:
wherein: h (x, y) is the processed concrete member image data; (i, j) is a pixel point in the original concrete member image data; s is the total amount of pixel points in the original concrete member image data; f (x, y) is original concrete member image data;
wherein a rectangular template of 3×3 is applied when the concrete member image data is subjected to the median filtering process.
6. The concrete member quality control system based on visual monitoring according to claim 1, wherein the concrete member surface integrity correction result in the correction module is obtained by the following formula:
wherein: k' is the surface integrity of the corrected concrete member; k is the surface integrity of the concrete member; f (f) all The total area of the surface is collected for the image data of the concrete member; f (f) on The total surface area of the concrete member; u is the total amount of the surface of the concrete member on which the image data is not collected; n is n rt The number of the opening surfaces on the surface of the concrete member;
the correction module is used for manually controlling whether to participate in the operation of the analysis layer or not based on a user at the system end in the analysis layer.
7. The visual monitoring-based concrete member quality control system according to claim 1, wherein the evaluation layer comprises a setting module, a judging module and a feedback module, the setting module is used for setting a concrete member qualification judging threshold, receiving a concrete member surface integrity analysis result corrected by the correcting module in the evaluation layer, the judging module is used for comparing the concrete member surface integrity correcting result with the concrete member qualification judging threshold, judging whether the concrete member surface integrity correcting result is in a concrete member qualification judging threshold range, judging that the concrete member qualification judging result is yes, skipping to capture layer operation, judging that the concrete member surface integrity is no, triggering the feedback module to operate, and the feedback module is used for receiving the corrected concrete member surface integrity received by the judging module, acquiring corresponding source concrete member image data based on the corrected concrete member surface integrity, further acquiring the concrete member surface integrity corresponding to each concrete member image data, comparing the concrete member surface integrity with the concrete member qualification judging threshold, acquiring the concrete member surface integrity not in the concrete member qualification judging threshold, taking the finally acquired not in the concrete member qualification judging threshold as feedback terminal image data.
8. The system of claim 7, wherein after the feedback module is operated, the feedback module synchronously executes the jump to the capturing layer to operate again.
9. The concrete member quality control system based on visual monitoring of claim 1, wherein the control terminal is electrically connected with an uploading module through a medium, the uploading module is electrically connected with a collecting module and a screening module through a medium, the control terminal and the screening module are electrically connected with a receiving module through a medium, the receiving module is electrically connected with an analyzing module and a correcting module through a medium, the control terminal and the correcting module are electrically connected with a setting module through a medium, and the setting module is electrically connected with a judging module and a feedback module through a medium.
10. A method for controlling the quality of a concrete member based on visual monitoring, which is a method for implementing the concrete member quality control system based on visual monitoring as claimed in any one of claims 1 to 9, and is characterized by comprising the steps of:
step 1: uploading specification parameters of the concrete member, and collecting image data of the concrete member;
step 11: defining specification parameters of the concrete member and defining image data acquisition logic of the concrete member;
step 12: a preliminary qualification judging stage of the concrete member;
step 2: receiving concrete member image data, and analyzing the surface integrity rate of the concrete member based on the concrete member image data;
step 21: a median filtering processing stage of the concrete member image data;
step 22: a screening stage of concrete member image data;
step 3: receiving analysis results of the surface integrity of the concrete member, accumulating the analysis results, setting a qualification judgment threshold value, and comparing the accumulated analysis results with the qualification judgment threshold value to judge whether the concrete member is qualified or not;
step 4: continuing to execute the step 1 when the concrete member qualification judging result is qualified, judging that the judging result is unqualified, acquiring the concrete member image data from each analysis result source in the accumulated analysis results, feeding back the judging result and the acquired concrete member image data to a user side, and executing the step 1 after feeding back.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311845945.9A CN117808356A (en) | 2023-12-29 | 2023-12-29 | Concrete member quality control method and system based on visual monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311845945.9A CN117808356A (en) | 2023-12-29 | 2023-12-29 | Concrete member quality control method and system based on visual monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117808356A true CN117808356A (en) | 2024-04-02 |
Family
ID=90429354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311845945.9A Pending CN117808356A (en) | 2023-12-29 | 2023-12-29 | Concrete member quality control method and system based on visual monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808356A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104278840A (en) * | 2014-09-26 | 2015-01-14 | 济南城建集团有限公司 | Decorating bare concrete construction method and split bolt hole die for same |
| CN105763869A (en) * | 2014-09-30 | 2016-07-13 | 宁波舜宇光电信息有限公司 | Testing and adjusting methods of camera device and adjusting device |
| CN110599481A (en) * | 2019-09-18 | 2019-12-20 | 成都数之联科技有限公司 | Cement prefabricated plate detection system based on image recognition |
| CN111462030A (en) * | 2020-03-27 | 2020-07-28 | 高小翎 | Multi-image fused stereoscopic set vision new angle construction drawing method |
| CN114235825A (en) * | 2022-02-24 | 2022-03-25 | 武汉祥文钢材制品有限公司 | Steel wire rope quality detection method based on computer vision |
| CN115283296A (en) * | 2022-10-08 | 2022-11-04 | 烟台台芯电子科技有限公司 | Visual detection system and method based on IGBT production |
| CN115616975A (en) * | 2022-11-11 | 2023-01-17 | 广东理工学院 | Error detection system for numerical control machining |
| CN115908432A (en) * | 2023-03-13 | 2023-04-04 | 单县龙宇生物科技有限公司 | Material output quality detection system and prediction method |
| CN116452536A (en) * | 2023-04-14 | 2023-07-18 | 中铁十局集团城建工程有限公司 | Concrete member surface damage detection method based on machine learning |
| CN117152163A (en) * | 2023-11-01 | 2023-12-01 | 安徽乾劲企业管理有限公司 | Bridge construction quality visual detection method |
| CN117250200A (en) * | 2023-11-07 | 2023-12-19 | 山东恒业金属制品有限公司 | Square pipe production quality detection system based on machine vision |
-
2023
- 2023-12-29 CN CN202311845945.9A patent/CN117808356A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104278840A (en) * | 2014-09-26 | 2015-01-14 | 济南城建集团有限公司 | Decorating bare concrete construction method and split bolt hole die for same |
| CN105763869A (en) * | 2014-09-30 | 2016-07-13 | 宁波舜宇光电信息有限公司 | Testing and adjusting methods of camera device and adjusting device |
| CN110599481A (en) * | 2019-09-18 | 2019-12-20 | 成都数之联科技有限公司 | Cement prefabricated plate detection system based on image recognition |
| CN111462030A (en) * | 2020-03-27 | 2020-07-28 | 高小翎 | Multi-image fused stereoscopic set vision new angle construction drawing method |
| CN114235825A (en) * | 2022-02-24 | 2022-03-25 | 武汉祥文钢材制品有限公司 | Steel wire rope quality detection method based on computer vision |
| CN115283296A (en) * | 2022-10-08 | 2022-11-04 | 烟台台芯电子科技有限公司 | Visual detection system and method based on IGBT production |
| CN115616975A (en) * | 2022-11-11 | 2023-01-17 | 广东理工学院 | Error detection system for numerical control machining |
| CN115908432A (en) * | 2023-03-13 | 2023-04-04 | 单县龙宇生物科技有限公司 | Material output quality detection system and prediction method |
| CN116452536A (en) * | 2023-04-14 | 2023-07-18 | 中铁十局集团城建工程有限公司 | Concrete member surface damage detection method based on machine learning |
| CN117152163A (en) * | 2023-11-01 | 2023-12-01 | 安徽乾劲企业管理有限公司 | Bridge construction quality visual detection method |
| CN117250200A (en) * | 2023-11-07 | 2023-12-19 | 山东恒业金属制品有限公司 | Square pipe production quality detection system based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| 施亮星;王洁;: "基于像素点的机器视觉***能力评价", 工业工程, no. 02, 15 April 2018 (2018-04-15) * |
| 田宸玮;王雪纯;杨嘉能;钱育蓉;: "织物瑕疵检测方法研究进展", 计算机工程与应用, no. 12 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110310261B (en) | Contact net dropper defect detection model training method and defect detection method | |
| CN110163858A (en) | A kind of aluminium shape surface defects detection and classification method and system | |
| CN113706495B (en) | Machine vision detection system for automatically detecting lithium battery parameters on conveyor belt | |
| CN110648364B (en) | Multi-dimensional space solid waste visual detection positioning and identification method and system | |
| CN106991668B (en) | Evaluation method for pictures shot by skynet camera | |
| JP7104799B2 (en) | Learning data collection device, learning data collection method, and program | |
| CN110560376B (en) | Product surface defect detection method and device | |
| CN114994061A (en) | Machine vision-based steel rail intelligent detection method and system | |
| CN116465315B (en) | Automatic screen quality detection method and system | |
| CN110852164A (en) | YOLOv 3-based method and system for automatically detecting illegal building | |
| CN114462646B (en) | Pole number plate identification method and system based on contact network safety inspection | |
| CN113554004A (en) | Detection method and detection system for material overflow of mixer truck, electronic equipment and mixing station | |
| CN115995056A (en) | Automatic bridge disease identification method based on deep learning | |
| CN115880296A (en) | Machine vision-based prefabricated part quality detection method and device | |
| Murao et al. | Concrete crack detection using uav and deep learning | |
| CN117455917B (en) | Establishment of false alarm library of etched lead frame and false alarm on-line judging and screening method | |
| CN117808374A (en) | Intelligent acceptance management method and system for building engineering quality | |
| CN117808356A (en) | Concrete member quality control method and system based on visual monitoring | |
| CN115019252B (en) | Concrete quality detection method and device and monitoring equipment | |
| CN115147392A (en) | Improved YOLOv 4-based coal gangue detection method and device | |
| CN114049543A (en) | Automatic identification method for scrap steel unloading change area based on deep learning | |
| Senthilnathan et al. | Quality monitoring of Concrete 3D Printed elements using computer vision-based texture extraction technique | |
| CN113657144B (en) | Rapid detection and tracking method for navigation ship in bridge area | |
| CN117649564B (en) | Aircraft cabin assembly deviation recognition device and quantitative evaluation method | |
| CN117830224A (en) | Bridge crack disease diagnosis method and system |
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 |