CN117152860A - Construction inspection method, system and storage medium - Google Patents
Construction inspection method, system and storage medium Download PDFInfo
- Publication number
- CN117152860A CN117152860A CN202311166340.7A CN202311166340A CN117152860A CN 117152860 A CN117152860 A CN 117152860A CN 202311166340 A CN202311166340 A CN 202311166340A CN 117152860 A CN117152860 A CN 117152860A
- Authority
- CN
- China
- Prior art keywords
- inspection
- data
- bim
- construction
- machine
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 809
- 238000010276 construction Methods 0.000 title claims abstract description 313
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000004891 communication Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 14
- 238000007726 management method Methods 0.000 description 18
- 238000012549 training Methods 0.000 description 15
- 238000003915 air pollution Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 14
- 230000008569 process Effects 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 12
- 238000013461 design Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 230000015654 memory Effects 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 7
- 238000013140 knowledge distillation Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 6
- 239000000523 sample Substances 0.000 description 6
- 238000003062 neural network model Methods 0.000 description 5
- 230000001413 cellular effect Effects 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 241000282472 Canis lupus familiaris Species 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000009423 ventilation Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009430 construction management Methods 0.000 description 2
- 238000004821 distillation Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002779 inactivation Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L67/125—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks involving control of end-device applications over a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
- H04N7/185—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source from a mobile camera, e.g. for remote control
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Architecture (AREA)
- Computational Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Civil Engineering (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Structural Engineering (AREA)
- Medical Informatics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a construction inspection method, a construction inspection system and a storage medium. The construction inspection method comprises the following steps: acquiring BIM inspection model data of a target construction area, wherein the BIM inspection model data comprises a road path and an inspection project, an inspection anchor point is arranged on the road path, the inspection anchor point is used for enabling an inspection machine to stay in an inspection point area of the target construction area for a period of time, and the inspection data of the inspection point area are continuously acquired; transmitting BIM inspection model data to an inspection machine so that the inspection machine moves in a target construction area according to a travelling path, and acquiring inspection data of the target construction area according to an inspection project; receiving inspection data from an inspection machine; and determining the current construction condition of the target construction area according to the inspection data. According to the invention, the inspection machine performs construction inspection according to the BIM inspection model data, the inspection data collected by the inspection machine can be more accurate and complete by the server, and the current construction condition of the target construction area can be more accurately analyzed.
Description
Technical Field
The invention relates to the field of construction inspection, in particular to a construction inspection method, a construction inspection system and a storage medium.
Background
In order to ensure that the construction project can be carried out smoothly, it is necessary to carry out inspection in the construction area to inspect places which do not meet the construction specification.
In the past, manual inspection is mostly adopted, but the manual inspection is more labor-consuming. To save labor, inspection machines (e.g., robots, robot dogs) are used in an increasing number of construction inspection schemes. In the related art, the routing path of the inspection machine is generally formed by simply setting up by constructors based on a third party map in the inspection machine, and when the inspection machine is inspected, the situation that the place needing to be inspected is missed to be inspected or the place needing to be inspected is misinspected is easily generated by the scheme, so that inspection data acquired by the inspection machine are not complete and accurate enough, and finally, the accurate construction condition of the target construction area cannot be obtained.
Disclosure of Invention
Aiming at the technical problems and defects, the invention aims to provide a construction inspection method, a construction inspection system and a storage medium, which can enable an inspection machine to inspect a target construction area according to BIM inspection model data, reduce the condition of missing inspection or false inspection, and enable a server to obtain more complete and accurate inspection data so as to obtain more accurate construction conditions.
In order to achieve the above object, in a first aspect, the present invention provides a construction inspection method, applied to a server of a construction inspection system, the inspection system further including an inspection machine, the construction inspection method including:
acquiring BIM inspection model data of a target construction area, wherein the BIM inspection model data comprises a road path and an inspection project, an inspection anchor point is arranged on the road path, the inspection anchor point is used for enabling an inspection machine to stay in an inspection point area of the target construction area for a period of time, and the inspection data of the inspection point area are continuously acquired;
transmitting BIM inspection model data to an inspection machine so that the inspection machine moves in a target construction area according to a travelling path, and acquiring inspection data of the target construction area according to an inspection project;
receiving inspection data from an inspection machine;
and determining the current construction condition of the target construction area according to the inspection data.
Optionally, before the step of transmitting the BIM inspection model data to the inspection machine, the method further includes:
judging whether BIM inspection model data are correct or not;
if not, correcting the BIM inspection model data.
Optionally, the step of determining whether the BIM inspection model data is correct includes:
Comparing the BIM inspection model data with the historical BIM inspection model data to obtain a comparison result;
and judging whether BIM inspection model data are correct according to the comparison result.
Optionally, an image recognition model is carried in the server, and the step of determining the current construction condition of the target construction area according to the inspection data includes:
identifying and extracting information in the inspection data through an image identification model to obtain identification information;
and determining the current construction condition of the target construction area according to the identification information.
Optionally, the BIM inspection model data further includes standard data corresponding to inspection items, and the step of determining the current construction condition of the target construction area according to the identification information includes:
comparing the identification information with standard data to obtain a comparison result;
and determining the current construction condition of the target construction area according to the comparison result.
Optionally, after the step of determining the current construction condition of the target construction area according to the inspection data, the method further includes:
if the construction condition is not compliant, alarm information is sent to the management unit, wherein the alarm information comprises the type and the position information of the non-compliant inspection items.
Optionally, the route is a circular route at the inspection anchor point.
Optionally, after the step of determining the current construction condition of the target construction area according to the inspection data, the method further includes:
and acquiring a patrol data set of the patrol machine, and storing the patrol data set and BIM patrol model data as historical data.
In a second aspect, the invention provides a construction inspection system, which comprises a server and an inspection machine, wherein the server is in communication connection with the inspection machine, the inspection machine is used for inspecting a target construction area, and the server is used for executing the construction inspection method.
In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the construction inspection method described above.
The beneficial effects of the invention at least comprise: the method comprises the steps that a server sends BIM inspection model data to an inspection machine; the BIM inspection model data comprise a road line and inspection items. And a routing inspection anchor point is further arranged on the road, and is used for enabling the inspection machine to stay for a period of time in the inspection point area of the target construction area and continuously collecting inspection data of the inspection point area, so that the condition of missing inspection or false inspection of the inspection machine can be reduced. The server receives the inspection data collected by the inspection machine, so that the inspection data can be more accurate and complete, and the construction condition of the target construction area can be more accurately analyzed and determined.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention. 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. In the drawings:
FIG. 1 is a schematic view of a inspection route of an inspection machine of the related art;
FIG. 2 is a schematic view of a inspection path of an inspection machine according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an architecture of a construction inspection system according to an embodiment of the present invention;
FIG. 4 is a flowchart of a construction inspection method according to an embodiment of the present invention;
FIG. 5 is a second flowchart of a construction inspection method according to an embodiment of the present invention;
FIG. 6 is a flow chart of a first stage of a construction inspection method in an embodiment of the invention;
FIG. 7 is a flow chart of a second stage of the construction inspection method in an embodiment of the invention;
FIG. 8 is a flow chart of a third stage of the construction inspection method in an embodiment of the invention;
fig. 9 is a schematic diagram of an architecture of an electronic device according to an embodiment of the invention.
Description of the embodiments
The terminology used in the following embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates to the contrary. It should also be understood that the term "and/or" as used in this disclosure refers to and encompasses any or all possible combinations of one or more of the listed items.
The terms "first," "second," and the like, are used below for descriptive purposes only and are not to be construed as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature, and in the description of embodiments of the invention, unless otherwise indicated, the meaning of "a plurality" is two or more.
The construction area needs to be inspected frequently, potential safety hazards are inspected timely, the construction progress is tracked, and the construction can be smoothly carried out according to the expected planning. As shown in fig. 1, in the related art, the routing path of the inspection machine is generally formed by a constructor simply set up in the inspection machine based on a third party map, and such a scheme can easily generate the condition that the place to be inspected is missed to be inspected or the place to be inspected is not mistakenly inspected when the inspection machine is inspecting, so that the inspection data collected by the inspection machine is not complete and accurate enough, and finally the accurate construction condition of the target construction area cannot be obtained.
Therefore, the embodiment of the invention provides a construction inspection method, which is characterized in that BIM (Building Information Modeling, building information model) inspection model data are sent to an inspection machine by a server 1, wherein the BIM inspection model data comprise a road line and an inspection project. As shown in fig. 2, a routing inspection anchor point is further disposed on the routing path, where the routing inspection anchor point is used to enable the routing inspection machine 2 to stay in a check point area of the target construction area for a period of time, and continuously collect routing inspection data of the check point area, so that the occurrence of missing inspection or false inspection of the routing inspection machine can be reduced. The server 1 can be more accurate and complete after receiving the inspection data collected by the inspection machine 2, so that the construction condition of the target construction area can be more accurately analyzed and determined.
The construction inspection method provided by the embodiment is applied to a server 1 of a construction inspection system, as shown in fig. 3, the construction inspection system further comprises an inspection machine 2, and the server 1 is in communication connection with the inspection machine 2. The inspection machine 2 is provided with a plurality of information collecting probes, such as a camera, an air quality detection sensor, a noise detection sensor and the like. The inspection data acquisition can be performed aiming at inspection projects such as construction progress, air quality, noise data, environmental sanitation conditions and the like. The server 1 may be a cloud server 1.
Further, the construction inspection system can further comprise an upper computer 3, BIM design software is loaded on the upper computer 3, and a target construction area can be accurately displayed in a three-dimensional model mode.
The construction inspection method in this embodiment specifically includes the following steps performed by the server 1, as shown in fig. 4:
step 101, BIM inspection model data of a target construction area are obtained, wherein the BIM inspection model data comprise a road line and inspection items.
Wherein the inspection items may include at least one of construction progress, air quality, noise data, and sanitation conditions. Meanwhile, a routing inspection anchor point is arranged on the travelling path, and the routing inspection anchor point can enable the routing inspection machine 2 to stay for a long enough time when moving to a check point area of a target construction area so as to continuously collect routing inspection data of the check point area, so that the condition of missing inspection of the routing inspection machine can be reduced. If the target construction area is a floor in a building, the inspection anchor point can comprise areas such as a corridor, an elevator, doors and windows, a strong electric well, a weak electric well and the like.
BIM inspection model data can be obtained through setting in a BIM model corresponding to a target construction area by the upper computer 3. Specifically, a floor plan of the target construction area is developed in the BIM model, and then the route of the inspection machine 2 and the inspection items are planned in the floor plan, so that BIM inspection model data is generated.
Step 102, transmitting BIM inspection model data to the inspection machine 2, so that the inspection machine 2 moves in the target construction area according to the road path, and collecting inspection data of the target construction area according to the inspection project.
The server 1 and the inspection machine 2 may be connected by wireless communication. The server 1 compresses the BIM inspection model data and then sends the compressed BIM inspection model data to the inspection machine 2 so as to improve the data transmission rate. The inspection machine 2 receives and stores BIM inspection model data, then automatically moves along a path in the BIM inspection model data, and shoots a target construction area according to a set inspection project in the moving process to obtain image and/or video data, wherein the image and video data are inspection data.
Step 103, receiving inspection data from the inspection machine 2.
The inspection data sent by the inspection machine 2 may be continuously received, or the inspection data may be received at intervals.
And 104, determining the current construction condition of the target construction area according to the inspection data.
The server 1 is provided with an image recognition model, specifically, the image recognition model is used for recognizing and extracting information in the inspection data to obtain recognition information, and the recognition information can comprise construction completion degree, environmental sanitation degree and construction potential safety hazard; and then determining the current construction condition of the target construction area according to the identification information.
In the construction inspection method of the embodiment, the routing path of the inspection machine 2 can be accurately planned through BIM design software, so that the inspection machine 2 automatically inspects according to the routing path, and the inspection data with enough quantity stays and collects at the inspection anchor point, thereby reducing the conditions of missing inspection and false inspection. The server 1 can obtain accurate and complete inspection data of the inspection machine 2 in real time, so that the current construction condition of the target construction area can be accurately obtained through analysis, and the inspection efficiency of the target construction area is improved.
In this embodiment, the processing procedure of the image recognition model may be as follows:
1) And carrying out gray scale processing on the original image in the inspection data to obtain a gray scale image.
The method comprises the following steps: the channel values of three channels of each image R, G, B are subjected to weighted average operation, and the operation result is assigned as the gray value of the point.
2) And carrying out sequential filtering processing on the gray scale image to remove noise in the gray scale image.
3) Identifying boundary information in the gray scale map by an edge operator and determining an ROI (Region of Interest ) in the image; in the process of determining the ROI, setting whether the ROI area is in the boundary or out of the boundary according to the identified actual object; the edge operator may be any one of sobel (sobel operator), roberts (Roberts operator), prewitt (pu Li Weite operator), and Canny (edge detection operator).
4) And according to the boundary information in the gray level diagram, a corresponding ROI area is cut out from the original image along the boundary.
5) Scaling the cut ROI area to a fixed size, and then pasting the ROI area into a white blank bottom plate picture with a preset size.
The processing steps can effectively avoid the influence of the background on the image recognition, are beneficial to improving the accuracy and the efficiency of the image recognition, and the image processing method is simpler and has smaller calculated amount. The inspection data collected by the inspection machine can be accurately identified, and the construction conditions such as the construction progress, the construction environmental sanitation degree, the existence of construction potential safety hazards and the like of the target construction area can be accurately identified and judged.
For example, when the inspection machine 2 inspects the ventilation opening of the corridor, the inspection machine is an inspection anchor point, images of the inspection anchor point are shot and uploaded to the server 1, the image recognition model recognizes whether the inspection anchor point is provided with a ventilation window, and if the recognition result is that the ventilation window is not provided, the inspection machine is not matched with the design in the BIM model, and the construction condition is not compliant.
The image recognition model of the embodiment includes a convolutional neural network, which adopts a SimpleCNN (Simple Convolutional Neural Network ) algorithm improved by knowledge distillation, and guides the SimpleCNN algorithm which is not completely trained to train through a VGG (Visual Geometry Group ) network which is already trained, so as to obtain a lightweight neural network model. The training of the simpleCNN network which is not completely trained is guided by the VGG network (which can be particularly a VGG19 network), so that the overfitting of the simpleCNN network can be avoided, the convergence of the simpleCNN network faces the VGG network, the simpleCNN network has the recognition capability of the VGG network, and the light weight of the simpleCNN network is ensured.
Firstly, training a teacher neural network (VGG network in the embodiment) by utilizing a data set, so that the teacher neural network fully learns the knowledge contained in the data; then, when training the student neural network (SimpleCNN in this embodiment) by using the data set, the learned knowledge in the teacher neural network is extracted by a distillation method to guide the training of the student neural network, so that the student neural network is equivalent to acquiring prior information about the data set from the teacher neural network.
In knowledge distillation, the teacher neural network is trained on the data set in advance, and then the training process of the student neural network is guided by the knowledge learned by the teacher neural network, so that the accuracy of the student neural network is improved.
Further, in order to improve the accuracy of the image recognition model, training optimization is required. And taking the image data set as input, distilling the simpleCNN network through the VGG19 network, obtaining different loss functions through setting different distillation temperatures, then carrying out back propagation, and then storing model parameters to obtain the neural network model for identifying the image. The method comprises the following specific steps:
1. The pixel mean of each image in the dataset is calculated and each image is adjusted to 224 x 224 pixels.
2. And subtracting the obtained pixel mean value from the pixel value of each channel of the adjusted image to obtain image processing data.
3. Constructing a knowledge distillation module, wherein the knowledge distillation module consists of a VGG19 network with trained parameters and an untrained simpleCNN network, and the simpleCNN network is guided to train through the VGG19 network; when training simpleCNN, the images are input in batches, and 3D convolution, batch standardization, maximum pooling, reLU (Rectified Linear Activation Function, correction of linear activation function) and 2DLSTM (2D Long Short-Term Memory) operation are carried out on each batch of images to obtain characteristic images.
4. And flattening the characteristic image in a multi-channel manner, removing unnecessary neurons through a Dropout (inactivation) layer, linearly mapping to deepen network depth, and finally classifying and outputting through Softmax (normalized exponential function) to obtain a loss function and characteristic data.
5. And replacing the loss function of the whole network with knowledge distillation of linear weights of each soft target and each hard target, carrying out back propagation on the loss function, and continuously carrying out parameter correction to obtain deep features.
And finally, inputting the verification set image into a neural network, comparing the obtained result with an image label, calculating an error, performing reverse calculation according to the error, updating model parameters, and storing the model parameters to obtain a neural network model for identifying the image.
In one embodiment, the travel route is a circular route at the patrol anchor. Therefore, when the inspection machine 2 moves to the inspection anchor point, the inspection machine can rotate for a circle to carry out 360-degree panoramic shooting and information acquisition on the key area, obtain more specific inspection data of the key area and avoid missing inspection and false inspection.
In order to ensure that the inspection machine 2 can stay for a period of time and rotate when moving to the inspection anchor point, an electronic fence can be arranged at the inspection anchor point, an annular route is defined through the electronic fence, a module which is induced by the electronic fence is arranged on the inspection machine 2, and the electronic fence can limit the inspection machine 2 to move in a key area.
In an embodiment, the electronic fence may also be a virtual electronic fence designed in the BIM model, and the virtual electronic fence defines a circular route of the important inspection area on the path route.
In an embodiment, as shown in fig. 5, the construction inspection method may further specifically include the following steps:
step 201, BIM inspection model data of a target construction area is obtained.
The BIM inspection model data comprise a road path, inspection items and standard data corresponding to the inspection items; the standard data can comprise a standard value of an air pollution index, a standard value of noise decibels and a standard value of construction progress; the routing is provided with the routing anchor point, and the routing anchor point can enable the routing machine 2 to stay for a period of time enough when moving to the check point area of the target construction area so as to continuously collect routing data of the check point area, so that the condition of missing inspection of the routing machine can be reduced.
Step 202, determining whether the BIM inspection model data is correct.
Specifically, firstly, BIM inspection model data and historical BIM inspection model data are compared to obtain a comparison result; and then judging whether BIM inspection model data are correct or not according to the comparison result.
For example, the route in the BIM inspection model data is compared with the route in the historical BIM inspection model data to determine whether the two are consistent or whether the similarity is within a set range. If yes, judging that the path line in the BIM inspection model data is correct. Meanwhile, the inspection items in the BIM inspection model data can be compared with the inspection items in the historical BIM inspection model data to judge whether the two inspection items are consistent or whether the similarity is within a set range; if yes, judging that the inspection items in the BIM inspection model data are correct.
And 203, if not, correcting the BIM inspection model data.
Through the steps, BIM inspection model data transmitted to the inspection machine 2 can be ensured to be correct, and the inspection machine 2 is prevented from inspecting according to a set travelling path. When BIM inspection model data are correct, the BIM inspection model data are directly sent to the inspection machine 2, when errors exist, the BIM inspection model data are corrected, and then the corrected correct BIM inspection model data are sent to the inspection machine 2.
Step 204, transmitting the correct BIM inspection model data to the inspection machine 2, so that the inspection machine 2 moves in the target construction area according to the road path, and collects the inspection data of the target construction area according to the inspection project.
For example, the route in the BIM inspection model data is compared with the route in the historical BIM inspection model data to determine whether the two are consistent or whether the similarity is within a set range. If yes, judging that the path line in the BIM inspection model data is correct. Meanwhile, the inspection items in the BIM inspection model data can be compared with the inspection items in the historical BIM inspection model data to judge whether the two inspection items are consistent or whether the similarity is within a set range; if yes, judging that the inspection items in the BIM inspection model data are correct.
Step 205 receives inspection data from inspection machine 2.
Specifically, the inspection data transmitted by the inspection machine 2 may be received by way of wireless communication. The wireless communication means may employ the following networks or techniques including, but not limited to: cellular networks (e.g., 3G networks, 4G networks, 5G networks, etc.), WLAN wireless local area networks, bluetooth, RFID (radio frequency identification).
The road path is a circular path at the inspection anchor point. Therefore, when the inspection machine 2 moves to the inspection anchor point, the inspection machine can rotate for a circle to carry out 360-degree panoramic shooting and information acquisition on the key area, obtain more specific inspection data of the key area and avoid missing inspection and false inspection.
In order to ensure that the inspection machine 2 can stay for a period of time and rotate when moving to the inspection anchor point, an electronic fence can be arranged at the inspection anchor point, an annular route is defined through the electronic fence, a module which is induced by the electronic fence is arranged on the inspection machine 2, and the electronic fence can limit the inspection machine 2 to move in a key area.
In an embodiment, the electronic fence may also be a virtual electronic fence designed in the BIM model, and the virtual electronic fence defines a circular route of the important inspection area on the path route.
And 206, identifying and extracting information in the inspection data through the image identification model to obtain identification information.
The identification information can include information such as construction completion, environmental sanitation, construction safety hazards and the like. In the embodiment, the image recognition model can adopt a convolutional neural network, and can accurately recognize the characteristics in the image and the video after multiple training optimization.
Step 207, comparing the identification information with the standard data to obtain a comparison result.
The comparison result may be a magnitude relation between the collected value of the inspection item in the identification information and the standard data value.
And step 208, determining the current construction condition of the target construction area according to the comparison result.
For example, comparing the picture of the construction condition at the inspection anchor point shot by the inspection machine 2 with the design in the corresponding BIM model, judging whether the construction condition of the inspection anchor point meets the design requirement in the BIM model, and if so, judging that the construction condition at the inspection anchor point is compliant; if the construction conditions are not in conformity with the inspection anchor points, the construction conditions at the inspection anchor points are judged to be not in compliance.
For another example, the air pollution index collected by the inspection machine 2 is a, the air pollution index standard value set in the server 1 is a, and if a is less than a, the air pollution at the inspection anchor point is judged to be out of standard; if a is more than or equal to A, judging that the air quality at the inspection anchor point reaches the standard. Assuming that the noise decibel number collected by the inspection machine 2 is B, the noise decibel number standard value set in the server 1 is B, and if B is less than B, judging that the noise at the inspection anchor point is compliant; if B is more than or equal to B, the noise at the inspection anchor point is judged to exceed the standard.
Step 209, if it is determined that the construction condition is not compliant, an alarm message is sent to the management unit.
The alert information includes category and location information for non-compliant inspection items. Specifically, alarm information can be sent to a management unit through modes such as APP message pushing or short messages, and the management unit is reminded to carry out rectification on places and projects which are not in compliance in a construction area.
Step 210, acquiring a patrol data set of the patrol machine, and storing the patrol data set and the BIM patrol model data as historical data.
On one hand, the historical data can be used as a training sample of the image recognition model so as to further improve the accuracy of the image recognition model. On the other hand, the historical data can facilitate the data retrieval of each inspection at the later time, and the traceability of the construction project data is improved.
In the construction inspection method of the present embodiment, inspection model data is sent to an inspection machine by a server 1, wherein the BIM inspection model data includes a route and an inspection item. As shown in fig. 2, a routing inspection anchor point is further disposed on the routing path, where the routing inspection anchor point is used to enable the routing inspection machine 2 to stay in a check point area of the target construction area for a period of time, and continuously collect routing inspection data of the check point area, so that the occurrence of missing inspection or false inspection of the routing inspection machine can be reduced. The server 1 can be more accurate and complete after receiving the inspection data collected by the inspection machine 2, so that the construction condition of the target construction area can be more accurately analyzed and determined.
According to which the profile data includes the course and corresponding standard data, e.g. emphasis of the target construction area
In an embodiment, after the inspection machine 2 reaches the target construction area, a self-inspection program is started first, the inspection machine 2 starts a pre-inspection program to scan the target construction area, and the coordinate system of the target construction area is matched with the coordinate system of the BIM inspection model, so that the inspection machine 2 can move in the target construction area according to the path in the BIM inspection model data. Therefore, the condition that inspection omission and false inspection occur in the inspection process of the inspection machine can be prevented.
The construction inspection method of the embodiment can be divided into three stages.
The first stage is a patrol configuration stage, in which the upper computer 3 is loaded with BIM design software, in which a patrol machine setting plug-in is integrated, through which BIM patrol model data can be set in a BIM model of a target construction area, and the specific flow is as follows, as shown in fig. 6:
s101, starting BIM design software on the upper computer 3.
S102, importing a BIM model of the target construction area into BIM design software.
S103, developing a floor plan of the target construction area in BIM design software.
S104, opening a setting plug-in corresponding to the inspection machine in BIM design software.
S105, setting a route and a routing inspection anchor point by setting a plug-in.
The inspection anchor point can be formed by arranging an electronic fence. The inspection anchor point can enable the inspection machine 2 to stay for a period of time enough to continuously collect inspection data of an inspection point area when moving to the inspection point area of a target construction area, so that the occurrence of the condition of inspection omission of the inspection machine can be reduced.
S106, setting inspection items and corresponding standard values in the setting plug-in.
Wherein the inspection items may include at least one of construction progress, air quality, noise data, and sanitation conditions.
S107, the upper computer 3 packs and compresses BIM inspection model data and transmits the BIM inspection model data to the server 1.
The upper computer 3 and the server 1 can be in communication connection in a wireless communication mode, so that data information interaction is realized. The wireless communication means may employ the following networks or techniques including, but not limited to: cellular networks (e.g., 3G networks, 4G networks, 5G networks, etc.), WLAN wireless local area networks, bluetooth, RFID (radio frequency identification).
S108, the server 1 compares BIM inspection model data based on the history file.
S109, judging whether BIM inspection model data are correct or not; if yes, the server 1 directly issues to the corresponding inspection machine 2.
For example, the route in the BIM inspection model data is compared with the route in the historical BIM inspection model data to determine whether the two are consistent or whether the similarity is within a set range. If yes, judging that the path line in the BIM inspection model data is correct. Meanwhile, the inspection items in the BIM inspection model data can be compared with the inspection items in the historical BIM inspection model data to judge whether the two inspection items are consistent or whether the similarity is within a set range; if yes, judging that the inspection items in the BIM inspection model data are correct.
If not, S110, the server 1 corrects the BIM inspection model number by error correction and then sends the BIM inspection model number to the inspection machine 2.
Through the steps, BIM inspection model data transmitted to the inspection machine 2 can be ensured to be correct, and the inspection machine 2 is prevented from inspecting according to a set travelling path. When BIM inspection model data are correct, the BIM inspection model data are directly sent to the inspection machine 2, when errors exist, the BIM inspection model data are corrected, and then the corrected correct BIM inspection model data are sent to the inspection machine 2.
The second stage is a patrol implementation stage, as shown in fig. 7, the main flow is as follows:
s201, the inspection machine 2 arrives at the target construction area site.
The inspection machine 2 may be moved to the site of the target construction area, or the inspection machine 2 may be brought to the site of the target construction area by a management unit via a transportation means.
S202, the inspection machine 2 starts a pre-inspection program to scan the target construction area.
S203, the inspection machine 2 performs matching synchronization on the coordinate system of the target construction area and the coordinate system of the BIM inspection model.
In this way, the inspection machine 2 can move in the target construction area according to the path line in the BIM inspection model data; the condition that inspection machine is missed in inspection and false inspection in the inspection process is prevented.
S204, the inspection machine 2 performs mobile inspection along the travelling path.
The moving speed of the inspection machine 2 can be set to be 0.2m/S to 1m/S, so that the inspection machine can carry out careful inspection on a construction area along a road, and sufficient inspection data can be shot and collected.
S205, the inspection machine 2 enters an inspection anchor point and moves along a circular route under the guidance of the electronic fence.
S206, the inspection machine 2 comprehensively scans key areas at the inspection anchor points.
The moving time step of the inspection machine 2 at the inspection anchor point is less than 5 seconds, so that sufficient shooting and information acquisition can be carried out on the heavy point area, and the conditions of missing inspection and false inspection are avoided.
S207, the inspection machine 2 uploads the collected inspection data to the server 1.
The inspection machine 2 and the server 1 also adopt a wireless communication connection mode to perform data interaction.
S208, the server 1 analyzes and processes the patrol data.
Wherein, the server 1 recognizes and extracts information in the inspection data through the image recognition model to obtain recognition information. The image recognition model is a convolutional neural network, a simpleCNN algorithm with improved knowledge distillation is adopted, and the simpleCNN algorithm which is not completely trained is guided to be trained through the trained VGG network, so that a lightweight neural network model is obtained. The training of the incompletely trained simpleCNN network is guided by the trained VGG network, so that the overfitting of the simpleCNN network can be avoided, the convergence of the simpleCNN network faces the VGG network, the simpleCNN network has the recognition capability of the VGG network, and the light weight of the simpleCNN network is ensured. Therefore, the processing process of the image recognition model is simpler, the calculated amount is smaller, and the accurate recognition of the inspection data collected by the inspection machine is facilitated.
S209, the server 1 determines the current construction status of the target construction area.
Through the image recognition network, accurate recognition and judgment can be made on the construction progress of the construction area, the sanitation degree of the construction environment and whether construction potential safety hazards exist.
For example, comparing the picture of the construction condition at the inspection anchor point shot by the inspection machine 2 with the design in the corresponding BIM model, judging whether the construction condition of the inspection anchor point meets the design requirement in the BIM model, and if so, judging that the construction condition at the inspection anchor point is compliant; if the construction conditions are not in conformity with the inspection anchor points, the construction conditions at the inspection anchor points are judged to be not in compliance.
For another example, the air pollution index collected by the inspection machine 2 is a, the air pollution index standard value set in the server 1 is a, and if a is less than a, the air pollution at the inspection anchor point is judged to be out of standard; if a is more than or equal to A, judging that the air quality at the inspection anchor point reaches the standard. Assuming that the noise decibel number collected by the inspection machine 2 is B, the noise decibel number standard value set in the server 1 is B, and if B is less than B, judging that the noise at the inspection anchor point is compliant; if B is more than or equal to B, the noise at the inspection anchor point is judged to exceed the standard.
S210, if the current construction condition is not in compliance, alarm information is pushed to a management unit.
The alert information includes category and location information for non-compliant inspection items. Specifically, alarm information can be sent to a management unit through modes such as APP message pushing or short messages, and the management unit is reminded to carry out rectification on places and projects which are not in compliance in a construction area.
The third stage is a data archiving stage, as shown in fig. 8, after the inspection is completed, the main flow is as follows:
s301, the inspection machine 2 transmits all the inspection data acquired at this time to the upper computer 3.
Specifically, the collected inspection data is uploaded to the upper computer in the mode of an inspection data set. The transmission mode may be a wireless communication mode or a transmission mode transmitted through a data line.
S302, the upper computer 3 outputs a construction inspection result of the target construction area according to the inspection data and the construction schedule.
The management unit can accurately study and judge the current construction condition of the target construction area according to the construction inspection result, and make targeted formulation and adjustment for the next construction plan.
S303, uploading the BIM inspection model data and the inspection data set to the server 1 by the upper computer 3.
S304, the server 1 files the BIM inspection model data and the inspection data set of the current time as historical data.
On one hand, the historical data can be used as a training sample of the image recognition model so as to further improve the accuracy of the image recognition model. On the other hand, the historical data can facilitate the data retrieval of each inspection at the later time, and the traceability of the construction project data is improved.
By adopting the construction inspection method of the embodiment, BIM inspection model data of a target construction area are firstly obtained, the BIM inspection model data comprises a road path and inspection items, an inspection anchor point is arranged on the road path, the inspection anchor point is used for enabling an inspection machine to stay for a period of time in an inspection point area of the target construction area, and the inspection data of the inspection point area are continuously collected; transmitting BIM inspection model data to an inspection machine so that the inspection machine moves in a target construction area according to a travelling path, and collecting inspection data of the target construction area according to inspection items; then receiving inspection data from an inspection machine; and finally, determining the current construction condition of the target construction area according to the inspection data.
The management unit can directly carry out relevant parameterization setting, inspection anchor points and travelling routes of inspection in a plane layout diagram in BIM design software, so that operation steps are simplified, and the synergy of BIM and inspection is improved. According to the embodiment, the front-edge machine dog equipment can be adopted as the inspection machine 2, the automation of inspection on the construction site is realized, the conditions of missing inspection and false inspection are reduced, and the accuracy and the integrity of inspection data are improved. The current site construction progress is automatically compared and generated through the inspection data, so that timeliness is improved. The historical data of patrolling and examining archives the structure clear, and the accessible time axis carries out data and consults, has improved the traceability of project.
The embodiment of the invention also provides a construction inspection system, which is shown in fig. 3 and comprises an inspection machine 2 and a server 1. The server 1 is in communication connection with the inspection machine 2, the inspection machine 2 is used for performing inspection in a target construction area, and the server 1 is used for executing the construction inspection method.
The inspection machine 2 is provided with a plurality of information collecting probes, such as a camera, an air quality detection sensor, a noise detection sensor and the like. The inspection data acquisition can be performed aiming at inspection projects such as construction progress, air quality, noise data, environmental sanitation conditions and the like. The server 1 may be a cloud server 1.
Further, the construction inspection system of the embodiment may further include an upper computer 3, where the upper computer 3 is loaded with BIM design software, and can accurately display the target construction area in a three-dimensional model form. Firstly, a BIM model of a target construction area is opened on an upper computer 3 through BIM design software, and then a path route and a patrol project of a patrol machine 2 are set in the BIM model.
In an embodiment, the target construction area may be a floor in a building, first, a floor plan of the floor is displayed in the BIM design software of the upper computer 3, and then, a route and an inspection project of the inspection machine 2 are planned in the floor plan of the BIM design software, so as to generate BIM inspection model data. Wherein, the routing inspection anchor point can be set on the path line. The inspection items may be at least one of construction progress, air quality, noise data, and environmental sanitation.
And then the upper computer 3 compresses and packages BIM inspection model data and transmits the BIM inspection model data to the server 1. The server 1 judges whether BIM inspection model data are correct or not, compares the BIM inspection model data with historical BIM inspection model data to obtain a comparison result, and judges whether the BIM inspection model data are correct or not according to the comparison result. For example, the route in the BIM inspection model data is compared with the route in the historical BIM inspection model data to determine whether the two are consistent or whether the similarity is within a set range. If yes, judging that the path line in the BIM inspection model data is correct. Meanwhile, the inspection items in the BIM inspection model data can be compared with the inspection items in the historical BIM inspection model data to judge whether the two inspection items are consistent or whether the similarity is within a set range; if yes, judging that the inspection items in the BIM inspection model data are correct. And correcting the BIM inspection model data with errors.
The server 1 sends correct or corrected BIM inspection model data to the robot dog through wireless communication.
When the inspection machine 2 arrives at the target construction area, the inspection machine 2 scans the target construction area through a pre-inspection program, and matches the coordinate system of the target construction area with the coordinate system of the BIM inspection model, so that the inspection machine 2 can move in the target construction area according to the BIM inspection model, and acquire real-time data of inspection items to obtain inspection data. The collected inspection data are transmitted to a server 1, the server 1 analyzes and processes the data collected by the inspection machine 2 based on the BIM design model corresponding to the target construction area, and whether the construction progress and the construction condition of the current target construction area are matched with the BIM design model or not is judged; if yes, indicating that the construction progress of the target construction area is normal, and the construction condition is compliant; if not, the target construction area is indicated to have an inconsistent place, the construction progress deviates from the expected planning, and alarm information can be sent to a construction management unit, so that the construction management unit can process as soon as possible, and construction accidents and faults are avoided.
In the embodiment, the server sends BIM inspection model data to an inspection machine; the BIM inspection model data comprise a road line and inspection items. And a routing inspection anchor point is further arranged on the road, and is used for enabling the inspection machine to stay for a period of time in the inspection point area of the target construction area and continuously collecting inspection data of the inspection point area, so that the condition of missing inspection or false inspection of the inspection machine can be reduced. The server can more accurately and completely receive the inspection data collected by the inspection machine, so that the construction condition of the target construction area can be more accurately analyzed and determined
The construction inspection system of the embodiment adopts the construction inspection method provided by the embodiment, and the work flow is as follows:
s101, starting BIM design software on the upper computer 3.
S102, importing a BIM model of the target construction area into BIM design software.
S103, developing a floor plan of the target construction area in BIM design software.
S104, opening a setting plug-in corresponding to the inspection machine in BIM design software.
S105, setting a route and a routing inspection anchor point by setting a plug-in.
The inspection anchor point can be formed by arranging an electronic fence. The inspection anchor point can enable the inspection machine 2 to stay for a period of time enough to continuously collect inspection data of an inspection point area when moving to the inspection point area of a target construction area, so that the occurrence of the condition of inspection omission of the inspection machine can be reduced.
S106, setting inspection items and corresponding standard values in the setting plug-in.
Wherein the inspection items may include at least one of construction progress, air quality, noise data, and sanitation conditions.
S107, the upper computer 3 packs and compresses BIM inspection model data and transmits the BIM inspection model data to the server 1.
The upper computer 3 and the server 1 can be in communication connection in a wireless communication mode, so that data information interaction is realized. The wireless communication means may employ the following networks or techniques including, but not limited to: cellular networks (e.g., 3G networks, 4G networks, 5G networks, etc.), WLAN wireless local area networks, bluetooth, RFID (radio frequency identification).
S108, the server 1 compares BIM inspection model data based on the history file.
S109, judging whether BIM inspection model data are correct or not; if yes, the server 1 directly issues to the corresponding inspection machine 2.
For example, the route in the BIM inspection model data is compared with the route in the historical BIM inspection model data to determine whether the two are consistent or whether the similarity is within a set range. If yes, judging that the path line in the BIM inspection model data is correct. Meanwhile, the inspection items in the BIM inspection model data can be compared with the inspection items in the historical BIM inspection model data to judge whether the two inspection items are consistent or whether the similarity is within a set range; if yes, judging that the inspection items in the BIM inspection model data are correct.
If not, S110, the server 1 corrects the BIM inspection model number by error correction and then sends the BIM inspection model number to the inspection machine 2.
Through the steps, BIM inspection model data transmitted to the inspection machine 2 can be ensured to be correct, and the inspection machine 2 is prevented from inspecting according to a set travelling path. When BIM inspection model data are correct, the BIM inspection model data are directly sent to the inspection machine 2, when errors exist, the BIM inspection model data are corrected, and then the corrected correct BIM inspection model data are sent to the inspection machine 2.
S201, the inspection machine 2 arrives at the target construction area site.
The inspection machine 2 may be moved to the site of the target construction area, or the inspection machine 2 may be brought to the site of the target construction area by a management unit via a transportation means.
S202, the inspection machine 2 starts a pre-inspection program to scan the target construction area.
S203, the inspection machine 2 performs matching synchronization on the coordinate system of the target construction area and the coordinate system of the BIM inspection model.
In this way, the inspection machine 2 can move in the target construction area according to the path line in the BIM inspection model data; the condition that inspection machine is missed in inspection and false inspection in the inspection process is prevented.
S204, the inspection machine 2 performs mobile inspection along the travelling path.
The moving speed of the inspection machine 2 can be set to be 0.2m/S to 1m/S, so that the inspection machine can carry out careful inspection on a construction area along a road, and sufficient inspection data can be shot and collected.
S205, the inspection machine 2 enters an inspection anchor point and moves along a circular route under the guidance of the electronic fence.
S206, the inspection machine 2 comprehensively scans key areas at the inspection anchor points.
The moving time step of the inspection machine 2 at the inspection anchor point is less than 5 seconds, so that sufficient shooting and information acquisition can be carried out on the heavy point area, and the conditions of missing inspection and false inspection are avoided.
S207, the inspection machine 2 uploads the collected inspection data to the server 1.
The inspection machine 2 and the server 1 also adopt a wireless communication connection mode to perform data interaction.
S208, the server 1 analyzes and processes the patrol data.
Wherein, the server 1 recognizes and extracts information in the inspection data through the image recognition model to obtain recognition information. The image recognition model is a convolutional neural network, a simpleCNN algorithm with improved knowledge distillation is adopted, and the simpleCNN algorithm which is not completely trained is guided to be trained through the trained VGG network, so that a lightweight neural network model is obtained. The training of the incompletely trained simpleCNN network is guided by the trained VGG network, so that the overfitting of the simpleCNN network can be avoided, the convergence of the simpleCNN network faces the VGG network, the simpleCNN network has the recognition capability of the VGG network, and the light weight of the simpleCNN network is ensured. Therefore, the processing process of the image recognition model is simpler, the calculated amount is smaller, and the accurate recognition of the inspection data collected by the inspection machine is facilitated.
S209, the server 1 determines the current construction status of the target construction area.
Through the image recognition network, accurate recognition and judgment can be made on the construction progress of the construction area, the sanitation degree of the construction environment and whether construction potential safety hazards exist.
For example, comparing the picture of the construction condition at the inspection anchor point shot by the inspection machine 2 with the design in the corresponding BIM model, judging whether the construction condition of the inspection anchor point meets the design requirement in the BIM model, and if so, judging that the construction condition at the inspection anchor point is compliant; if the construction conditions are not in conformity with the inspection anchor points, the construction conditions at the inspection anchor points are judged to be not in compliance.
For another example, the air pollution index collected by the inspection machine 2 is a, the air pollution index standard value set in the server 1 is a, and if a is less than a, the air pollution at the inspection anchor point is judged to be out of standard; if a is more than or equal to A, judging that the air quality at the inspection anchor point reaches the standard. Assuming that the noise decibel number collected by the inspection machine 2 is B, the noise decibel number standard value set in the server 1 is B, and if B is less than B, judging that the noise at the inspection anchor point is compliant; if B is more than or equal to B, the noise at the inspection anchor point is judged to exceed the standard.
S210, if the current construction condition is not in compliance, alarm information is pushed to a management unit.
The alert information includes category and location information for non-compliant inspection items. Specifically, alarm information can be sent to a management unit through modes such as APP message pushing or short messages, and the management unit is reminded to carry out rectification on places and projects which are not in compliance in a construction area.
S301, the inspection machine 2 transmits all the inspection data acquired at this time to the upper computer 3.
Specifically, the collected inspection data is uploaded to the upper computer in the mode of an inspection data set. The transmission mode may be a wireless communication mode or a transmission mode transmitted through a data line.
S302, the upper computer 3 outputs a construction inspection result of the target construction area according to the inspection data and the construction schedule.
The management unit can accurately study and judge the current construction condition of the target construction area according to the construction inspection result, and make targeted formulation and adjustment for the next construction plan.
S303, uploading the BIM inspection model data and the inspection data set to the server 1 by the upper computer 3.
S304, the server 1 files the BIM inspection model data and the inspection data set of the current time as historical data.
On one hand, the historical data can be used as a training sample of the image recognition model so as to further improve the accuracy of the image recognition model. On the other hand, the historical data can facilitate the data retrieval of each inspection at the later time, and the traceability of the construction project data is improved.
By adopting the method, the construction inspection system of the embodiment can accurately plan the path of the inspection machine 2 through BIM design software, so that the inspection machine 2 automatically inspects according to the path, inspection data of the inspection machine 2 are obtained in real time, and inspection efficiency of a target construction area is improved.
The embodiment of the invention provides a construction inspection device, which is applied to a server 1, and adopts the construction inspection method provided by the embodiment, and comprises the following steps:
the BIM inspection model data comprises a road path and an inspection project;
the transmission module is used for transmitting BIM inspection model data to the inspection machine 2 so that the inspection machine 2 moves in a target construction area according to the travelling path and acquires inspection data of the target construction area according to an inspection project;
a receiving module for receiving inspection data from the inspection machine 2;
and the judging module is used for judging whether the construction condition of the target construction area is in compliance or not according to the inspection data.
The construction inspection module of the embodiment adopts the construction inspection method provided by the embodiment, and the specific workflow steps are as follows:
step 201, BIM inspection model data of a target construction area is obtained.
The BIM inspection model data comprise a road path, inspection items and standard data corresponding to the inspection items; the standard data can comprise a standard value of an air pollution index, a standard value of noise decibels and a standard value of construction progress; the routing is provided with the routing anchor point, and the routing anchor point can enable the routing machine 2 to stay for a period of time enough when moving to the check point area of the target construction area so as to continuously collect routing data of the check point area, so that the condition of missing inspection of the routing machine can be reduced.
Step 202, determining whether the BIM inspection model data is correct.
Specifically, firstly, BIM inspection model data and historical BIM inspection model data are compared to obtain a comparison result; and then judging whether BIM inspection model data are correct or not according to the comparison result.
For example, the route in the BIM inspection model data is compared with the route in the historical BIM inspection model data to determine whether the two are consistent or whether the similarity is within a set range. If yes, judging that the path line in the BIM inspection model data is correct. Meanwhile, the inspection items in the BIM inspection model data can be compared with the inspection items in the historical BIM inspection model data to judge whether the two inspection items are consistent or whether the similarity is within a set range; if yes, judging that the inspection items in the BIM inspection model data are correct.
And 203, if not, correcting the BIM inspection model data.
Through the steps, BIM inspection model data transmitted to the inspection machine 2 can be ensured to be correct, and the inspection machine 2 is prevented from inspecting according to a set travelling path. When BIM inspection model data are correct, the BIM inspection model data are directly sent to the inspection machine 2, when errors exist, the BIM inspection model data are corrected, and then the corrected correct BIM inspection model data are sent to the inspection machine 2.
Step 204, transmitting the correct BIM inspection model data to the inspection machine 2, so that the inspection machine 2 moves in the target construction area according to the road path, and collects the inspection data of the target construction area according to the inspection project.
For example, the route in the BIM inspection model data is compared with the route in the historical BIM inspection model data to determine whether the two are consistent or whether the similarity is within a set range. If yes, judging that the path line in the BIM inspection model data is correct. Meanwhile, the inspection items in the BIM inspection model data can be compared with the inspection items in the historical BIM inspection model data to judge whether the two inspection items are consistent or whether the similarity is within a set range; if yes, judging that the inspection items in the BIM inspection model data are correct.
Step 205 receives inspection data from inspection machine 2.
Specifically, the inspection data transmitted by the inspection machine 2 may be received by way of wireless communication. The wireless communication means may employ the following networks or techniques including, but not limited to: cellular networks (e.g., 3G networks, 4G networks, 5G networks, etc.), WLAN wireless local area networks, bluetooth, RFID (radio frequency identification).
The road path is a circular path at the inspection anchor point. Therefore, when the inspection machine 2 moves to the inspection anchor point, the inspection machine can rotate for a circle to carry out 360-degree panoramic shooting and information acquisition on the key area, obtain more specific inspection data of the key area and avoid missing inspection and false inspection.
In order to ensure that the inspection machine 2 can stay for a period of time and rotate when moving to the inspection anchor point, an electronic fence can be arranged at the inspection anchor point, an annular route is defined through the electronic fence, a module which is induced by the electronic fence is arranged on the inspection machine 2, and the electronic fence can limit the inspection machine 2 to move in a key area.
In an embodiment, the electronic fence may also be a virtual electronic fence designed in the BIM model, and the virtual electronic fence defines a circular route of the important inspection area on the path route.
And 206, identifying and extracting information in the inspection data through the image identification model to obtain identification information.
The identification information can include information such as construction completion, environmental sanitation, construction safety hazards and the like. In the embodiment, the image recognition model can adopt a convolutional neural network, and can accurately recognize the characteristics in the image and the video after multiple training optimization.
Step 207, comparing the identification information with the standard data to obtain a comparison result.
The comparison result may be a magnitude relation between the collected value of the inspection item in the identification information and the standard data value.
And step 208, determining the current construction condition of the target construction area according to the comparison result.
For example, comparing the picture of the construction condition at the inspection anchor point shot by the inspection machine 2 with the design in the corresponding BIM model, judging whether the construction condition of the inspection anchor point meets the design requirement in the BIM model, and if so, judging that the construction condition at the inspection anchor point is compliant; if the construction conditions are not in conformity with the inspection anchor points, the construction conditions at the inspection anchor points are judged to be not in compliance.
For another example, the air pollution index collected by the inspection machine 2 is a, the air pollution index standard value set in the server 1 is a, and if a is less than a, the air pollution at the inspection anchor point is judged to be out of standard; if a is more than or equal to A, judging that the air quality at the inspection anchor point reaches the standard. Assuming that the noise decibel number collected by the inspection machine 2 is B, the noise decibel number standard value set in the server 1 is B, and if B is less than B, judging that the noise at the inspection anchor point is compliant; if B is more than or equal to B, the noise at the inspection anchor point is judged to exceed the standard.
Step 209, if it is determined that the construction condition is not compliant, an alarm message is sent to the management unit.
The alert information includes category and location information for non-compliant inspection items. Specifically, alarm information can be sent to a management unit through modes such as APP message pushing or short messages, and the management unit is reminded to carry out rectification on places and projects which are not in compliance in a construction area.
Step 210, acquiring a patrol data set of the patrol machine, and storing the patrol data set and the BIM patrol model data as historical data.
On one hand, the historical data can be used as a training sample of the image recognition model so as to further improve the accuracy of the image recognition model. On the other hand, the historical data can facilitate the data retrieval of each inspection at the later time, and the traceability of the construction project data is improved.
In this embodiment, the inspection model data is sent to the inspection machine by the server 1, wherein the BIM inspection model data includes a route of travel and an inspection item. And a routing inspection anchor point is further arranged on the road, and is used for enabling the inspection machine 2 to stay for a period of time in the inspection point area of the target construction area and continuously collecting inspection data of the inspection point area, so that the condition of missing inspection or false inspection of the inspection machine can be reduced. The server 1 can be more accurate and complete after receiving the inspection data collected by the inspection machine 2, so that the construction condition of the target construction area can be more accurately analyzed and determined.
Fig. 9 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
It should be noted that, the computer system of the electronic device shown in fig. 9 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present invention.
As shown in fig. 9, the computer system includes a central processing unit (Central Processing Unit, CPU) 1801, which can perform various appropriate actions and processes, such as performing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 1802 or a program loaded from a storage section 1808 into a random access Memory (Random Access Memory, RAM) 1803. In the RAM 1803, various programs and data required for system operation are also stored. The CPU 1801, ROM 1802, and RAM 1803 are connected to each other via a bus 1804. An Input/Output (I/O) interface 1805 is also connected to the bus 1804.
The following components are connected to the I/O interface 1805: an input section 1806 including a keyboard, a mouse, and the like; an output portion 1807 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and a speaker, etc.; a storage section 1808 including a hard disk or the like; and a communication section 1809 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 1809 performs communication processing via a network such as the internet. The drive 1810 is also connected to the I/O interface 1805 as needed. Removable media 1811, such as magnetic disks, optical disks, magneto-optical disks, semiconductor memory, and the like, is installed as needed on drive 1810 so that a computer program read therefrom is installed as needed into storage portion 1808.
In particular, according to embodiments of the present invention, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 1809, and/or installed from the removable medium 1811. When executed by a Central Processing Unit (CPU) 1801, performs various functions defined in the system of the present invention.
It should be noted that, the computer readable medium shown in the embodiments of the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present invention may be implemented by software, or may be implemented by hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
Specifically, the electronic device of the present embodiment includes a processor and a memory, where a computer program is stored in the memory, and when the computer program is executed by the processor, the construction inspection method provided in the foregoing embodiment is implemented.
Through the electronic equipment of the embodiment, BIM inspection model data of a target construction area are obtained, wherein the BIM inspection model data comprises a travelling path and an inspection project, and an inspection anchor point is further arranged on the travelling path; then transmitting BIM inspection model data to an inspection machine 2 so that the inspection machine 2 moves in a target construction area according to a travelling path, and collecting inspection data of the target construction area according to inspection items; then receiving inspection data from the inspection machine 2; and finally judging whether the construction condition of the target construction area is compliant according to the inspection data. By adopting the method, the server 1 sends BIM inspection model data to the inspection machine 2; the BIM inspection model data comprise a road line and inspection items. And a routing inspection anchor point is further arranged on the road, and is used for enabling the inspection machine to stay for a period of time in the inspection point area of the target construction area and continuously collecting inspection data of the inspection point area, so that the condition of missing inspection or false inspection of the inspection machine can be reduced. The server receives the inspection data collected by the inspection machine, so that the inspection data can be more accurate and complete, and the construction condition of the target construction area can be more accurately analyzed and determined.
As another aspect, the present invention also provides a computer-readable storage medium that may be contained in the electronic device described in the above-described embodiment; or may exist alone without being incorporated into the electronic device. The storage medium carries one or more computer programs which, when executed by a processor of the electronic device, cause the electronic device to implement the methods provided in the embodiments described above.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the invention. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server 1, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present invention.
Specifically, by the storage medium of the present embodiment, the method shown in the above embodiment may be implemented. The method specifically comprises the following steps: acquiring BIM inspection model data of a target construction area, wherein the BIM inspection model data comprises a travelling path and an inspection project, and an inspection anchor point is further arranged on the travelling path; then transmitting BIM inspection model data to an inspection machine 2 so that the inspection machine 2 moves in a target construction area according to a travelling path, and collecting inspection data of the target construction area according to inspection items; then receiving inspection data from the inspection machine 2; and finally judging whether the construction condition of the target construction area is compliant according to the inspection data. By adopting the method, the server 1 sends BIM inspection model data to the inspection machine 2; the BIM inspection model data comprise a road line and inspection items. And a routing inspection anchor point is further arranged on the road, and is used for enabling the inspection machine to stay for a period of time in the inspection point area of the target construction area and continuously collecting inspection data of the inspection point area, so that the condition of missing inspection or false inspection of the inspection machine can be reduced. The server receives the inspection data collected by the inspection machine, so that the inspection data can be more accurate and complete, and the construction condition of the target construction area can be more accurately analyzed and determined.
The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the above description, numerous specific details are provided to give a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the invention.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains.
It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. The construction inspection method is characterized by being applied to a server of a construction inspection system, wherein the inspection system further comprises an inspection machine, and the construction inspection method comprises the following steps:
acquiring BIM inspection model data of a target construction area, wherein the BIM inspection model data comprises a road path and an inspection project, the road path is provided with an inspection anchor point, and the inspection anchor point is used for enabling the inspection machine to stay in an inspection point area of the target construction area for a period of time and continuously collecting the inspection data of the inspection point area;
Transmitting the BIM inspection model data to the inspection machine so that the inspection machine moves in the target construction area according to the travelling path, and collecting inspection data of the target construction area according to the inspection project;
receiving the inspection data from the inspection machine;
and determining the current construction condition of the target construction area according to the inspection data.
2. The construction inspection method of claim 1, further comprising, prior to the step of transmitting the BIM inspection model data to the inspection machine:
judging whether the BIM inspection model data is correct or not;
and if not, correcting the BIM inspection model data.
3. The construction inspection method according to claim 2, wherein the step of determining whether the BIM inspection model data is correct includes:
comparing the BIM inspection model data with historical BIM inspection model data to obtain a comparison result;
and judging whether the BIM inspection model data is correct or not according to the comparison result.
4. The construction inspection method according to claim 1, wherein the server is provided with an image recognition model, and the step of determining the current construction condition of the target construction area according to the inspection data comprises the steps of:
Identifying and extracting information in the inspection data through the image identification model to obtain identification information;
and determining the current construction condition of the target construction area according to the identification information.
5. The construction inspection method according to claim 4, wherein the BIM inspection model data further includes standard data corresponding to the inspection item, and the step of determining the current construction condition of the target construction area according to the identification information includes:
comparing the identification information with the standard data to obtain a comparison result;
and determining the current construction condition of the target construction area according to the comparison result.
6. The construction inspection method according to any one of claims 1 to 5, further comprising, after the step of determining the current construction condition of the target construction area from the inspection data:
and if the construction condition is not compliant, sending alarm information to a management unit, wherein the alarm information comprises the type and the position information of the non-compliant inspection items.
7. The construction inspection method of claim 1, wherein the path is a circular path at the inspection anchor point.
8. The construction inspection method according to claim 1, further comprising, after the step of determining the current construction condition of the target construction area from the inspection data:
and acquiring a patrol data set of the patrol machine, and storing the patrol data set and the BIM patrol model data as historical data.
9. A construction inspection system, comprising a server and an inspection machine, wherein the server is in communication connection with the inspection machine, the inspection machine is used for inspecting a target construction area, and the server is used for executing the construction inspection method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when executed by a processor, implements the construction inspection method of any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311166340.7A CN117152860A (en) | 2023-09-11 | 2023-09-11 | Construction inspection method, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311166340.7A CN117152860A (en) | 2023-09-11 | 2023-09-11 | Construction inspection method, system and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117152860A true CN117152860A (en) | 2023-12-01 |
Family
ID=88909762
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311166340.7A Pending CN117152860A (en) | 2023-09-11 | 2023-09-11 | Construction inspection method, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117152860A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117765434A (en) * | 2023-12-14 | 2024-03-26 | 提书工程科技(上海)有限公司 | On-site video image processing method and system for constructional engineering |
-
2023
- 2023-09-11 CN CN202311166340.7A patent/CN117152860A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117765434A (en) * | 2023-12-14 | 2024-03-26 | 提书工程科技(上海)有限公司 | On-site video image processing method and system for constructional engineering |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11341626B2 (en) | Method and apparatus for outputting information | |
CN112102646B (en) | Parking lot entrance positioning method and device in parking positioning and vehicle-mounted terminal | |
EP3506158A1 (en) | Method, apparatus, and device for determining lane line on road | |
US11880943B2 (en) | Photogrammetry of building using machine learning based inference | |
US20240210330A1 (en) | Systems and methods for artificial intelligence powered inspections and predictive analyses | |
CN117152860A (en) | Construction inspection method, system and storage medium | |
KR102346676B1 (en) | Method for creating damage figure using the deep learning-based damage image classification of facility | |
CN114798495B (en) | Sheet metal stamping part sorting method, device, equipment and medium based on quality detection | |
CN113361539A (en) | Instrument reading method and device of underground inspection robot and electronic equipment | |
CN115995056A (en) | Automatic bridge disease identification method based on deep learning | |
CN116385421A (en) | Photovoltaic panel detection method, unmanned aerial vehicle and computer readable storage medium | |
CN117152094A (en) | Method, device and system for analyzing surface defects of steel plate based on computer vision | |
CN113569801A (en) | Distribution construction site live equipment and live area identification method and device thereof | |
CN117649207A (en) | Building construction management system | |
CN115730236B (en) | Medicine identification acquisition method, equipment and storage medium based on man-machine interaction | |
CN115660495A (en) | Comprehensive evaluation system for endowment-husbandry public service facilities | |
CN115438945A (en) | Risk identification method, device, equipment and medium based on power equipment inspection | |
CN115546099A (en) | Forging flaw detection defect detection method and device based on convolutional neural network | |
CN115482277A (en) | Social distance risk early warning method and device | |
CN114169404A (en) | Method for intelligently acquiring quantitative information of slope diseases based on images | |
CN116543327A (en) | Method, device, computer equipment and storage medium for identifying work types of operators | |
CN112686162A (en) | Method, device, equipment and storage medium for detecting clean state of warehouse environment | |
CN114419080B (en) | Curtain wall inspection system and method | |
CN118051062B (en) | Intelligent inspection method and system for construction site tower crane based on BIM and unmanned aerial vehicle | |
CN116030418B (en) | Automobile lifting line state monitoring system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |