CN213843125U - Active safety detection system for service state of glass curtain wall based on intelligent vision and big data - Google Patents
Active safety detection system for service state of glass curtain wall based on intelligent vision and big data Download PDFInfo
- Publication number
- CN213843125U CN213843125U CN202022972553.7U CN202022972553U CN213843125U CN 213843125 U CN213843125 U CN 213843125U CN 202022972553 U CN202022972553 U CN 202022972553U CN 213843125 U CN213843125 U CN 213843125U
- Authority
- CN
- China
- Prior art keywords
- glass curtain
- curtain wall
- lens
- sub
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model provides an active safety detection system for service state of glass curtain wall, which comprises a detection device, wherein the detection device comprises a camera, a laser stroboscopic illumination box, a laser controller, an electronic control box, an industrial personal computer, piezoelectric ceramics, a first lens, a second lens, a beam splitter prism, a first reflecting mirror, a second reflecting mirror and a third lens; the first reflector and the optical axis form a certain small included angle; the electronic control box outputs a sine signal modulation signal to generate ultrasonic waves to excite the wall body, so that the glass curtain wall to be tested arranged on the wall body vibrates; the laser controller is used for controlling the laser stroboscopic illumination box to generate stroboscopic light with the same frequency as the vibration formed on the glass curtain wall to be tested so as to illuminate the glass curtain wall to be tested; light reflected by the glass curtain wall to be tested is incident to the beam splitting prism through a 4f system formed by the first lens and the second lens and then is divided into two first sub-beams and two second sub-beams; the first and second sub-beams are reflected by the first and second reflectors, respectively, and are converged and interfered by the third lens.
Description
Technical Field
The utility model relates to a detect technical field, especially relate to an initiative safety inspection system of glass curtain wall state of active service.
Background
The glass curtain wall is a building external protective structure or a decorative structure which has a certain displacement capacity relative to the main structure by a supporting structure system and does not bear the action of the main structure. The wall body has two types of single-layer glass and double-layer glass. At present, glass curtain walls are adopted in many high-rise buildings.
However, there are many potential safety hazards to these glass curtain walls, and a technology capable of performing safety detection on the glass curtain wall is needed at present.
SUMMERY OF THE UTILITY MODEL
A brief summary of the present invention is provided below in order to provide a basic understanding of some aspects of the present invention. It should be understood that this summary is not an exhaustive overview of the invention. It is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is discussed later.
The utility model provides an initiative safety inspection system of glass curtain wall state of service to solve the above-mentioned problem among the prior art at least.
The utility model provides an active safety detection system for the service state of a glass curtain wall, which comprises a detection device, wherein the detection device comprises a camera, a laser stroboscopic illumination box, a laser controller, an electronic control box, an industrial personal computer, piezoelectric ceramics, a first lens, a second lens, a beam splitter prism, a first reflector, a second reflector and a third lens; the electronic control box is used for outputting a sine signal modulation signal to generate ultrasonic waves to excite the wall body, so that the glass curtain wall to be tested arranged on the wall body is vibrated; the laser controller is used for controlling the laser stroboscopic illumination box to generate stroboscopic light with the same frequency as vibration formed on the glass curtain wall to be tested so as to illuminate the glass curtain wall to be tested; the first lens and the second lens form a 4f system, so that light reflected by the glass curtain wall to be detected is incident to the light splitting prism after passing through the 4f system and then is divided into a first sub-beam and a second sub-beam; the first sub-beam is reflected by a light splitting surface of the light splitting prism and then enters the first reflector along a direction forming a preset included angle with the normal direction of the mirror surface of the first reflector; the second sub-beam is transmitted through the light splitting surface of the light splitting prism and then enters the second reflecting mirror along the normal direction of the mirror surface of the second reflecting mirror; the piezoelectric ceramic is used for being connected with the second reflector so as to control the second reflector to generate preset positive displacement or negative displacement along the direction of an optical axis; the first sub-beam reflected from the first reflector is transmitted by the light splitting prism and then is output to the camera through the third lens; and the second sub-beam reflected back from the second reflecting mirror is reflected by the beam splitter prism, is output to the camera through the third lens, is converged with the first sub-beam output to the camera and interferes with the first sub-beam, and the camera receives a corresponding interference image so as to send the interference image to an industrial personal computer through the camera.
Preferably, the preset included angle is an angle greater than 0 and less than 30 degrees; the preset included angle is 2 degrees, 5 degrees or 10 degrees.
Preferably, the detection device further comprises a sound controller and a transmitter; the electronic control box is connected with the sound controller and controls the generated ultrasonic waves to excite the wall body through the sound controller and the transmitter.
Preferably, the detection device further comprises an infrared heat sensing device for sensing the glass curtain wall to be detected to obtain heat sensing data.
Preferably, the active safety detection system comprises a plurality of detection devices, and the detection devices are used for being arranged at a plurality of detection points to obtain detection data of the glass curtain wall corresponding to the detection points, wherein the detection data at least comprises corresponding interference images.
The utility model discloses a glass curtain wall state of service initiative safety inspection system can measure the region as far as possible on the detection of building glass curtain wall state of service, helps discovering the vibration distribution of large tracts of land unusual (usually corresponding to the defect), has also improved scanning speed simultaneously, increases substantially work efficiency, measures required time shorter for traditional time averaging.
The utility model discloses glass curtain wall state of service's initiative safety detection system, its integrated 4f system, simple structure, light path are stable, the angle of vision is big, can more be applicable to building glass curtain wall state of service initiative safety detection system.
These and other advantages of the present invention will become more apparent from the following detailed description of the preferred embodiments of the invention, which is to be read in connection with the accompanying drawings.
Drawings
The invention may be better understood by referring to the following description in conjunction with the accompanying drawings, in which like reference numerals are used to designate like or similar parts throughout the figures thereof. The accompanying drawings, which are incorporated in and form a part of this specification, illustrate preferred embodiments of the present invention and, together with the detailed description, serve to explain the principles and advantages of the invention. Wherein:
fig. 1 is a schematic diagram showing an exemplary structure of an active safety detection system for a service state of a glass curtain wall according to the present invention;
fig. 2 is a schematic diagram showing another exemplary structure of the active safety detection system for the service state of the glass curtain wall of the present invention;
fig. 3 is a schematic structural diagram illustrating an example of an active safety detection system for a service state of a glass curtain wall according to the present invention;
FIG. 4 is a schematic illustration of laser strobe illumination;
FIG. 5 is an image of an object under test;
FIG. 6 is an interferogram obtained;
FIG. 7 is a real-time subtractive fringe pattern;
fig. 8 is a schematic diagram showing a 4f optical system composed of a first lens and a second lens;
fig. 9 is a schematic view illustrating the field angle principle of the active safety detection system according to the service state of the glass curtain wall of the present invention.
Skilled artisans appreciate that elements in the figures are illustrated for simplicity and clarity and have not necessarily been drawn to scale. For example, the dimensions of some of the elements in the figures may be exaggerated relative to other elements to help improve the understanding of the embodiments of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described hereinafter with reference to the accompanying drawings. In the interest of clarity and conciseness, not all features of an actual implementation are described in the specification. It will of course be appreciated that in the development of any such actual embodiment, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which will vary from one implementation to another. Moreover, it will be appreciated that such a development effort might be complex and time-consuming, but would nevertheless be a routine undertaking for those of ordinary skill in the art having the benefit of this disclosure.
It should be noted that, in order to avoid obscuring the present invention with unnecessary details, only the device structures and/or processing steps closely related to the solution according to the present invention are shown in the drawings, and other details not relevant to the present invention are omitted.
The utility model provides an initiative safety inspection system of glass curtain wall state of active service.
An example of an active safety detection system for the service condition of a glass curtain wall is described below with reference to fig. 1.
The utility model discloses to present existing glass curtain wall state of service safety inspection current situation, provided a glass curtain wall state of service initiative safety inspection system, the interference image that this system can obtain the effective information of glass curtain wall state of service through follow-up analysis, whether safe etc. whether have damage etc. realizes safety inspection.
As shown in fig. 1, the active safety detection system for the service state of the glass curtain wall comprises a detection device.
The detection device shown in fig. 1 is a device for obtaining an interference image of the service state of the glass curtain wall.
The detection device may be configured, for example, as shown in fig. 1, and includes a camera 1, a laser strobe illumination box 2, a laser controller 3, an electronic control box 4, an industrial personal computer 5, a piezoelectric ceramic 10, a first lens 11, a second lens 12, a beam splitter prism 13, a first reflecting mirror 14, a second reflecting mirror 15, and a third lens 16.
The electronic control box 4 is used for outputting a sine signal modulation signal to generate ultrasonic waves to excite the wall 9, so that the glass curtain wall 8 to be tested installed on the wall 9 vibrates.
The laser controller 3 is used for controlling the laser stroboscopic illumination box 2 to generate stroboscopic light with the same frequency as the vibration formed on the glass curtain wall 8 to be tested so as to illuminate the glass curtain wall 8 to be tested; the first lens 11 and the second lens 12 form a 4f system, so that light reflected by the glass curtain wall 8 to be measured passes through the 4f system and then enters the beam splitter prism 13 to be divided into a first sub-beam and a second sub-beam.
The first sub-beam is reflected by the beam splitting surface of the beam splitting prism 13 and then enters the first reflecting mirror 14 along a direction forming a predetermined included angle with the normal direction of the mirror surface of the first reflecting mirror 14.
The second sub-beam is transmitted through the splitting surface of the beam splitter prism 13 and then enters the second reflecting mirror 15 along the normal direction of the second reflecting mirror 15.
The piezoelectric ceramic 10 is used to connect the second mirror 15 to control the second mirror 15 to generate a predetermined positive displacement or negative displacement along the optical axis.
The first sub-beam reflected from the first mirror 14 is transmitted through the beam splitter prism 13, and then is output to the camera 1 through the third lens 16.
The second sub-beam reflected from the second reflecting mirror 15 is reflected by the beam splitter prism 13, is output to the camera 1 through the third lens 16, is converged with the first sub-beam output to the camera 1, interferes with the first sub-beam, and receives a corresponding interference image by the camera 1, so that the interference image is transmitted to the industrial personal computer 5 through the camera 1.
The preset included angle may be an angle greater than 0 and less than 30 degrees.
For example, the predetermined included angle is 2 degrees, 5 degrees, 10 degrees, or the like.
In one example, the detection means may further comprise an acoustic controller 6 and a transmitter 7.
As shown in fig. 2, the electronic control box 4 is connected with a sound controller 6, and the electronic control box 4 controls the generated ultrasonic wave to excite the wall 9 through the sound controller 6 and the transmitter 7.
Thus, the industrial personal computer 5 may perform preprocessing (for example, denoising, filtering, or other preprocessing) on the obtained interference image, and then recognize and analyze the preprocessed interference image by using a pre-constructed glass curtain wall detection data recognition algorithm model.
The glass curtain wall detection data recognition algorithm model can be obtained by obtaining a large amount of training data in advance and training the model through a neural network.
In one example, the detection device may further comprise an infrared heat sensing device. The infrared heat sensing device can be used for sensing the glass curtain wall 8 to be measured to obtain sensing data (such as infrared imaging, radiation, spectrum measurement and the like).
In another example, the system may include a plurality of detection devices as shown in fig. 1 (optionally, one or more infrared heat sensing devices may be correspondingly disposed in each of the devices shown in fig. 1). Thus, the device is arranged at a plurality of preset places in a city, for example, the data acquisition and communication among the preset places can be realized by utilizing the internet of things, and therefore, the relevant data (corresponding interference images, sensing data and the like) of the glass curtain walls of the preset places can be obtained. Thus, the obtained training data has corresponding labels, such as the type of loss and the grade of the loss, for example, the type of loss can be classified into cracks, pits, scratches, crumbles, stains, etc., and the grade can be classified according to the severity, for example, each loss can be classified into 0 grade, 1 grade, 2 grade, and 3 grade, 0 grade indicates no loss, and 1-3 grades indicate that the loss is more and more severe.
Therefore, the big data are collected in the early stage and screened in the early stage through technologies such as a sensor network, the Internet of things, data preprocessing and big data management.
Next, a preferred embodiment of the present invention is described.
When the training data are obtained, the training data under the complex interference conditions of haze, variable illumination, shielding and the like can be obtained, the glass curtain wall detection data recognition algorithm model under the complex environment is obtained, the detection and risk assessment of the service state of the glass curtain wall are realized through a deep learning algorithm, all glass curtain walls of a building are regularly detected and subjected to data analysis, the big data safety of all building curtain walls of a city is realized, and the active safety detection and prediction of the service state of the building glass curtain walls are realized.
Because the glass curtain wall of the building has a large area, the problems of the field angle and the laser stroboscopic illumination energy need to be considered when the glass curtain wall is used for large-area vibration measurement. The existing measuring devices are subject to the construction and dimensions of the device, and the angle of view is relatively small, which limits the working distance, and usually does not exceed a maximum angle of view of 28 °.
In addition to the field angle problem, the large area vibration measurement also requires attention to the illumination energy problem. On one hand, since the exposure of the digital camera is reduced by illumination with strobe light, a laser is required to provide sufficient illumination energy; on the other hand, since the area of the target to be measured is large, the laser is also required to provide sufficient illumination energy. These two factors promote that large-area measurement requires high-power laser for illumination, and simultaneously, the laser has better temporal coherence and spatial coherence.
In this way, quantitative measurement of the vibration amplitude spatial gradient can be realized, or nondestructive detection can be carried out according to the vibration distribution. The method has the advantages of full field, non-contact, rapidity, strong anti-interference capability, stable structure and lower laser coherence requirement, and can be suitable for nondestructive testing of the glass curtain wall.
To solve this problem, the structure and operation of the system will be described with reference to fig. 3, which illustrates the use of an exemplary structure as shown in fig. 3 to measure the defects of the glass curtain wall of a building. In fig. 3, a detection device is shown in a dashed line, wherein 30 includes the camera 1, the piezoelectric ceramic 10, the first lens 11, the second lens 12, the beam splitter prism 13, the first mirror 14, the second mirror 15, and the third lens 16 shown in fig. 1 or fig. 2 as a detection end.
The device is composed of five parts including a detection end 30, a laser stroboscopic illumination box 2, a laser controller 3, an electronic control box 4 and an industrial personal computer 5 (the industrial personal computer 5 is provided with corresponding software modules). During measurement, the electronic control box outputs a sine signal modulation signal to generate ultrasonic waves to excite the wall body 9, so that the glass curtain wall 8 vibrates. Because the sound intensity changes in a sine wave manner, each point on the glass curtain wall also vibrates according to the sine law. If the surface condition of the glass curtain wall is uniform, the distribution of the vibration amplitude of the glass curtain wall is uniformly changed; if the glass curtain wall has the defects of cracking, breakage and the like, the vibration amplitude of the wall body corresponding to the defects is obviously inconsistent with the vibration amplitude of the periphery. Through the adjustment of a synchronous signal generator in the electronic control box, the laser stroboscopic illumination box generates stroboscopic light with the same frequency as the vibration to illuminate the wall, and then the detection end 30 records the obtained interference pattern in a computer (an industrial personal computer 5). By the stroboscopic illumination method, the detection end 30 can obtain the spatial gradient of the vibration amplitude distribution of the glass curtain wall, and the distribution of the vibration amplitude can be obtained after integration. The position and the size of the glass curtain wall defect can be obtained by observing and analyzing the speckle stripe shape related to the amplitude distribution.
The above-described time averaging method and flash illumination method are described below with reference to fig. 4.
The stroboscopic illumination method adopts laser stroboscopic illumination, and the frequency of the stroboscopic illumination is consistent with the vibration frequency, so that the illumination is locked on a certain phase of vibration. The stroboscopic illumination method obtains phase diagrams under two different states (for example, a state 1 that one glass curtain wall is intact, and a state 2 that the other glass curtain wall is broken or cracked, etc.) respectively, and then phase difference distribution corresponding to the displacement space gradient distribution of the measured object is obtained by subtracting. For example, when the excitation signal is respectively at a peak or a trough, the stroboscopic illumination method obtains respective corresponding phase diagrams, and the displacement spatial gradient distribution corresponding to the maximum vibration amplitude change can be obtained by subtracting the phase diagrams, so that the full-field vibration amplitude spatial gradient distribution can be quantitatively measured by the stroboscopic illumination method.
A schematic of the stroboscopic illumination is given by fig. 4. When the excitation vibration is simple harmonic vibration, the position of any point on the surface of the measured object is simple harmonic vibration, and the relation between the out-of-plane displacement of the measured object and the time can be described by a sine wave shown in the figure. Stroboscopic illumination occurs at a specific phase of vibration, such as the peak of the wave shown in the figureAssuming that its initial phase isα. If the pulse of strobe illumination is narrow, then the object of measurement for the detection end 30 is equivalent to a stationary target, and a phase shift technique can be used to obtain a phase map corresponding to the location of the vibration peak. The strobe illumination is then controlled at the next instant to move to another phase of oscillation, such as the phase shift shown in FIG. 4βAnd then to the trough position. A phase map corresponding to the position of the vibration trough can also be obtained. The key to stroboscopic illumination is that the strobe light is at the same frequency as the vibrations, so that the illumination can be locked to a specific phase of the vibrations. Theoretically, the pulse width of the strobe light should be as narrow as possible, and the variation of the oscillation phase should be as small as possible. If the pulse width ratio is wide, the resulting interferogram is actually the integral of the vibration over a short period of time. Because the variation in the oscillation is non-linear, excessive strobe pulse widths will affect the final phase map. Too narrow strobe illumination may result in insufficient laser illumination brightness, and therefore, it is necessary to select an appropriate strobe duty ratio according to actual conditions.
Referring to fig. 1 or 2, when light reflected by an object to be measured passes through a detection end 30 (corresponding to the camera 1, the piezoelectric ceramic 10, the first lens 11, the second lens 12, the beam splitter prism 13, the first reflector 14, the second reflector 15, and the third lens 16 in fig. 1 or 2), the light is split into two beams according to a certain angle, so that each point on the object forms two images on an image plane; or each point on the image plane corresponds to two points on the object.
Laser emitted by the laser can irradiate the surface to be measured after passing through the beam expander or other beam expanding elements. The object light passes through the detection end 30 to form mutually interfered images, and then the images are imaged on the target surface of the digital camera. As shown in fig. 1-3, the first mirror 14 is at a small angle to the optical axis at the sensing end 30, which may be set empirically or determined experimentally. The second mirror 15 is perpendicular to the optical axis and is connected to the piezo ceramic for phase shifting.
The object light is split into two beams after passing through the beam splitting prism, and then reflected by the first reflecting mirror 14 and the second reflecting mirror 15, respectively. However, the light beam reflected by the first reflecting mirror 14 is deflected by a certain angle, the light beam reflected by the phase shift mirror is parallel to the optical axis, and finally the two reflected light beams are converged by the beam splitter prism again and form two mutually dislocated interference images on the target surface of the camera after passing through the imaging lens.
An example of a measurement performed using the above-described apparatus is described below with reference to fig. 5 to 7.
Fig. 5 shows the measured object, fig. 6 is an interference pattern obtained with the device, and fig. 7 is a real-time subtraction fringe pattern obtained based on fig. 6. The deformation of the object can be analyzed by resolving the fringes of fig. 7.
Referring to fig. 6, two images are shifted in the X direction, and S is the magnitude of the shift. Like this, through utilizing the utility model discloses above-mentioned device of embodiment carries out initiative safety inspection to building glass curtain wall state of service, can obtain the butterfly spot shown in figure 7, and the skilled person can confirm glass curtain wall's defect position and size according to this butterfly spot.
Further, in the preferred embodiment, the field of view of the system is expanded by using a 4f system, as shown in FIG. 8, where f is1And f2The focal lengths of lens L1 (i.e., the first lens described above) and lens L2 (i.e., the second lens described above), respectively, may be, for example, f1=f2. The utility model discloses in the initiative safety inspection system of glass curtain wall state of service, the image planes and the input plane coincidence of 4f system imaging lens, detection plane and the coincidence of camera target surface. Like this, make the utility model discloses glass curtain wall service's initiative safety inspection system can have great angle of vision, and figure 9 schematically shows the partly of the initiative safety inspection system of above-mentioned glass curtain wall service, and the angle of vision that can see out this system is great.
By adopting the active safety detection system for the service state of the glass curtain wall based on the stroboscopic illumination method, the area as large as possible can be measured in the detection of the service state of the glass curtain wall of the building, the large-area abnormal vibration distribution (usually corresponding to defects) can be found, the scanning speed is improved, the working efficiency is greatly improved, and the time required by the measurement is shorter compared with the traditional time averaging method.
The utility model discloses glass curtain wall state of service's initiative safety detection system, its integrated 4f system, simple structure, light path are stable, the angle of vision is big, can more be applicable to building glass curtain wall state of service initiative safety detection system.
And when the CCD camera obtains the image, storing the image into a computer, and then detecting and grading the quality defect of the building glass curtain wall by adopting a convolutional neural network on the image. The deep neural network carries out multilayer representation on the target by constructing a multilayer network so as to represent abstract semantic information of data by multilayer high-level features, and better feature robustness is obtained.
In addition, the system can adopt a Convolutional Neural Network (CNN) to realize the construction and detection of the model, and has excellent performance for large-scale image processing. It includes a convolutional layer and a pooling layer. For example, keras can be used as a high-level development API, known data can be converted into experimental results with minimal time delay, and the method can be implemented in an environment with a Tensorflow or caffe deep learning framework as a back end. Data process that the experiment adopted the utility model discloses the initiative safety inspection system collection of glass curtain wall state of active service makes into the data set. And reading the obtained picture, separating according to training, verifying and testing data, training the neural network, and optimizing a cost function by adopting methods such as a cross entropy function and the like to obtain a final active safety detection result of the service state of the glass curtain wall of the wall building.
In order to realize the active safety detection system for the service state of the glass curtain wall based on intelligent vision and big data, the wall examples of the glass curtain wall to be detected can be collected and then quantified in a preset mode. The method comprises the steps of obtaining wall body data by reading sample data of each city building, marking defects, uploading the wall body data to a cloud end data analysis center, analyzing and learning by using algorithms such as k-means and the like, and modeling and evaluating the sample data for multiple times to judge the defect condition of the current glass curtain wall body. For example, this process may be performed over weeks or months to collect glass curtain wall examples, different lighting conditions, different times of day, different temperatures, create a diverse database of images representing the wall, and after sufficient data has been obtained and analyzed, the system may perform a secondary modeling of the glass curtain wall conditions to inform the user that the glass curtain wall is flawless and flawed. Utilize the utility model discloses glass curtain wall service's initiative safety inspection system can collect the image of glass curtain wall body defect on the spot, speculates glass curtain wall body defect, and need not consume a large amount of manpowers, material resources cost and remove and collect wall body information, and this deployment degree of difficulty that has both reduced the project has also practiced thrift the fund consumption, has intelligent analysis and reminds the function, effectively detects glass curtain wall body defect.
In practical application, the wall defects of the glass curtain walls of all cities can be recorded into a cloud data analysis center, a database is established for each city, and passwords are set; and installing a wall diagnosis system interface, reading the wall defect data of the glass curtain wall according to a diagnosis system protocol, and uploading the data to a glass curtain wall defect database corresponding to each city in the cloud data analysis center.
Establishing a classification model for the glass curtain wall data obtained by the cloud data analysis center through deep learning algorithm analysis, processing the unbalanced data set, and balancing the data set by using undersampling; the phenomena of overlarge normal data proportion and undersize abnormal data proportion are avoided; establishing a classification model for the data set to assist in analyzing the defects of the glass curtain wall; attaching two labels of normal and abnormal data, and dividing the data into two parts according to the same proportion: de-tagging the data set and preserving the tagged data set; and performing clustering analysis on the unlabeled data set by adopting an anomaly detection mechanism based on k-means and other algorithms, performing the same clustering analysis on the labeled data set by adopting the anomaly detection mechanism based on the k-means algorithm, and comparing the distance variance from other data points to the cluster center to judge whether the point is in an abnormal state or a normal state. The label-free data set also needs to be added with various mixed models at the later stage to calculate the probability of the data being classified into different classes, so that the fine classification of the data points is realized, a more accurate result is obtained, and the generation of overfitting is avoided.
In addition, utilize the utility model discloses glass curtain wall body defect is detected to glass curtain wall service's initiative safety inspection system, collects its phase diagram, carries out operations such as filtering to the phase diagram. Establishing a prediction model for the real-time data set to provide technical support for early warning; the method comprises the steps of describing the state of wall defects by using abnormal data points appearing on a wall, detecting abnormal information by using a self-encoder, detecting and grading quality defects of the glass curtain wall by using a convolutional neural network, taking keras a high-level development API (application program interface), and taking a Tensorflow or caffe deep learning framework as a rear end; analyzing the data, and optimizing a cost function by adopting methods such as a cross entropy function and the like to obtain a wall defect model; the model in the self-encoder has the functions of compressing data and recovering the data, and the compression and the recovery mainly aim at the characteristic data in the hidden layer; the extracted characteristic data passes through a sigmoid function to realize discretization of the defect data of the glass curtain wall, so that the use condition of a K-means algorithm is met; each attribute weight is given through a neural network so as to overcome the defects of the equal weight of each attribute of the K-means algorithm; the self-encoder glass curtain wall defects can be modeled again, the defective glass curtain wall is pre-warned, and the glass curtain wall is repaired in a targeted manner in the later period, so that the level of personalized intelligent pre-warning is greatly improved.
In addition, the analyzed data can be stored in a database corresponding to the situation of the urban glass curtain wall through the cloud data analysis center, the analysis result is sent to the user mobile terminal, and the password set in the first step needs to be input during checking, so that the data security is ensured; the mobile terminal informs a user of the current glass curtain wall condition according to the data, so that a dangerous glass curtain wall body is prompted, and real-time detection is realized. Finally, establishing a measurement index; and quantifying the performance of the model, and checking the correctness, stability and dependence of the model so as to assist subsequent improvement.
In practical application, the utility model discloses an above-mentioned system can also acquire glass curtain wall state of service data comprehensively with multisensor information such as infrared heat sensing technique, collects and handles the screening in earlier stage to big data through techniques such as sensing net, thing networking, data preprocessing and big data management. The method is characterized in that complex interference conditions such as haze, variable illumination and shielding are analyzed, detection and risk assessment of the service state of the glass curtain wall are realized through a deep learning algorithm, all glass curtain walls of a building are regularly detected and subjected to data analysis, big data safety of all building curtain walls of a city is realized, and active safety detection and prediction of the service state of the building glass curtain walls are realized. The method and the technology for early warning and hidden danger mining of the service of the glass curtain wall based on the security domain and the intelligent model are provided by utilizing an automatic optimization algorithm, for example, a prototype can be developed according to the requirements of the first-pass standard specification and can be tested on site, and the real-time and predictive level of the online health diagnosis of the glass curtain wall of the urban building is improved.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of this description, will appreciate that other embodiments can be devised which do not depart from the scope of the invention as described herein. Moreover, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.
Claims (5)
1. The active safety detection system for the service state of the glass curtain wall is characterized by comprising a detection device, wherein the detection device comprises a camera (1), a laser stroboscopic illumination box (2), a laser controller (3), an electronic control box (4), an industrial personal computer (5), piezoelectric ceramics (10), a first lens (11), a second lens (12), a beam splitter prism (13), a first reflector (14), a second reflector (15) and a third lens (16);
the electronic control box (4) is used for outputting a sine signal modulation signal to generate an ultrasonic wave to excite a wall body (9), so that a glass curtain wall (8) to be tested installed on the wall body (9) vibrates;
the laser controller (3) is used for controlling the laser stroboscopic illumination box (2) to generate stroboscopic light with the same frequency as the vibration formed on the glass curtain wall (8) to be detected so as to illuminate the glass curtain wall (8) to be detected; the first lens (11) and the second lens (12) form a 4f system, so that light reflected by the glass curtain wall (8) to be detected passes through the 4f system and then is incident on the beam splitter prism (13) and then is divided into a first sub-beam and a second sub-beam;
the first sub-beam is reflected by a light splitting surface of the light splitting prism (13) and then enters the first reflecting mirror (14) along a direction forming a preset included angle with the normal direction of the mirror surface of the first reflecting mirror (14);
the second sub-beam is transmitted through the light splitting surface of the light splitting prism (13) and then enters the second reflecting mirror (15) along the normal direction of the mirror surface of the second reflecting mirror (15);
the piezoelectric ceramic (10) is used for connecting the second reflector (15) to control the second reflector (15) to generate a preset positive displacement or negative displacement along the direction of the optical axis;
the first sub-beam reflected from the first reflecting mirror (14) is transmitted by the beam splitting prism (13) and then is output to the camera (1) through the third lens (16);
and after the second sub-beam reflected back from the second reflecting mirror (15) is reflected by the light splitting prism (13), the second sub-beam is output to the camera (1) through the third lens (16), and is converged and interfered with the first sub-beam output to the camera (1), and the camera (1) receives a corresponding interference image so as to send the interference image to an industrial personal computer (5) through the camera (1).
2. The active safety detection system of a service state of a glass curtain wall as claimed in claim 1, wherein the preset included angle is an angle greater than 0 and less than 30 degrees; the preset included angle is 2 degrees, 5 degrees or 10 degrees.
3. Active safety inspection system of the service condition of glass curtain walls according to claim 1, characterized in that the inspection device further comprises a sound controller (6) and a transmitter (7); the electronic control box (4) is connected with the sound controller (6), and the electronic control box (4) controls the generated ultrasonic waves to excite the wall body (9) through the sound controller (6) and the transmitter (7).
4. The active safety inspection system for the service condition of glass curtain walls as claimed in claim 1, wherein the inspection device further comprises an infrared heat sensing device for sensing the glass curtain wall to be inspected to obtain heat sensing data.
5. Active safety inspection system according to any one of claims 1 to 4, characterized in that it comprises a plurality of inspection devices for being arranged at a plurality of inspection points to obtain inspection data of the glass curtain wall corresponding to the inspection points, said inspection data comprising at least a corresponding interference image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202022972553.7U CN213843125U (en) | 2020-12-13 | 2020-12-13 | Active safety detection system for service state of glass curtain wall based on intelligent vision and big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202022972553.7U CN213843125U (en) | 2020-12-13 | 2020-12-13 | Active safety detection system for service state of glass curtain wall based on intelligent vision and big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN213843125U true CN213843125U (en) | 2021-07-30 |
Family
ID=76998410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202022972553.7U Active CN213843125U (en) | 2020-12-13 | 2020-12-13 | Active safety detection system for service state of glass curtain wall based on intelligent vision and big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN213843125U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112505148A (en) * | 2020-12-13 | 2021-03-16 | 河南省科学院应用物理研究所有限公司 | Active safety detection system for service state of glass curtain wall based on intelligent vision and big data |
-
2020
- 2020-12-13 CN CN202022972553.7U patent/CN213843125U/en active Active
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112505148A (en) * | 2020-12-13 | 2021-03-16 | 河南省科学院应用物理研究所有限公司 | Active safety detection system for service state of glass curtain wall based on intelligent vision and big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112666254B (en) | Active safety detection method for service state of glass curtain wall based on intelligent vision and big data | |
| CN107462581A (en) | Defect inspection method and defect detecting device | |
| US11073501B2 (en) | System and method for inspecting parts using dynamic response function | |
| Park et al. | Vision‐based natural frequency identification using laser speckle imaging and parallel computing | |
| CN102033081A (en) | Infrared lock-in thermal wave non-destructive detection method based on image sequence processing | |
| JP2008064755A (en) | Method for distinguishing damage of component, and component-inspection system | |
| Sánchez‐Rodríguez et al. | Detection of structural faults in piers of masonry arch bridges through automated processing of laser scanning data | |
| KR102621156B1 (en) | Welding area inspection system and method thereof for assessing the risk based on artificial intelligence | |
| CN213843125U (en) | Active safety detection system for service state of glass curtain wall based on intelligent vision and big data | |
| CN102081045B (en) | Structural damage identification method based on laser television holographic technique | |
| Wu et al. | Non-contact measurement method of beam vibration with laser stripe tracking based on tilt photography | |
| Aoyama et al. | Vision-based modal analysis using multiple vibration distribution synthesis to inspect large-scale structures | |
| CN112505148A (en) | Active safety detection system for service state of glass curtain wall based on intelligent vision and big data | |
| West et al. | Applying concepts of complexity to structural health monitoring | |
| Ghafoor et al. | Non-contact detection of railhead defects and their classification by using convolutional neural network | |
| Chen et al. | Shape characterization and depth recognition of metal cracks based on laser infrared thermography and machine learning | |
| Sabato et al. | Advancements in structural health monitoring using combined computer-vision and unmanned aerial vehicles approaches | |
| Zhou et al. | Defect detection of carbon fiber deflectors based on laser infrared thermography and experimental modal analysis | |
| Sutcliffe et al. | Automatic defect recognition of single-v welds using full matrix capture data, computer vision and multi-layer perceptron artificial neural networks | |
| Liu et al. | Practical ultrasonic damage monitoring on pipelines using component analysis methods | |
| Nyongesa et al. | Neural fuzzy analysis of delaminated composites from shearography imaging | |
| Staub Felipe et al. | Procedure for detecting the shape and size of defects on metallic substrates under composite repairs using shearography | |
| CN112213396A (en) | Nondestructive testing method for ballastless track plate of track traffic | |
| Spagnolo et al. | Local Correlation Degree of Laser Speckle for Vibration Analysis | |
| Fahad et al. | Pavement Crack Monitoring: Literature Review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |