Building structure detection method based on WiFi
By setting up WiFi signal base stations in the building and combining machine learning algorithms, the existing building structure health detection methods are solved, and efficient, low-cost and generally feasible structural health detection is achieved. .
Patent Information
- Application Number
- CN202411581336.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-07
- Publication Date
- 2025-02-14
AI Technical Summary
The existing building structure health testing methods have problems such as high equipment costs, expensive inspection costs, low efficiency and accuracy due to manual operation, poor universality, and complex instrument installation and layout.
Using WiFi-based building structure detection method, by setting up WiFi signal base stations inside the building, collecting information such as WiFi signal strength, wavelength, frequency, etc., and combining machine learning algorithms, a model of the internal structure of the building structure is constructed to realize non-destructive detection.
It reduces the cost of testing equipment, improves the detection efficiency and accuracy, enhances the universality and feasibility of testing, and realizes efficient, low-cost and long-term health monitoring of building structures.
Smart Images
Figure CN119438248A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of building detection, and in particular relates to a building structure detection method based on WiFi. Background Art
[0002] Structural health monitoring of buildings and structures refers to the continuous or regular monitoring and evaluation of buildings or engineering structures to obtain information on their performance, status and safety during service, so as to timely discover and warn of potential structural problems. It is of great significance to ensure the safety and reliability of various buildings and structures during their life cycle and to ensure the normal operation of social infrastructure.
[0003] At present, there are many methods for structural health testing of buildings and structures, which are mainly divided into destructive testing and non-destructive testing. Among them, non-destructive testing will not cause permanent damage or changes to the structure being tested during the testing process, which means that the structure can still continue to be used after the test. Non-destructive testing is applicable to various in-service structures, such as bridges and high-rise buildings. It is environmentally friendly and has a wide range of applications. It is currently the main means of structural health testing of buildings and structures. There are many non-destructive testing methods, such as ultrasonic testing, radar testing, electrochemical testing, and infrared testing. Although non-destructive testing methods are very useful in the current health testing of building structures, each method has its limitations and defects. Summarizing the common problems of these detection methods, it can be found that they generally have the following shortcomings:
[0004] (1) High equipment costs and expensive testing fees. The purchase and maintenance costs of ultrasonic and radar equipment are usually high, and the cost of a single test may range from several thousand yuan to tens of thousands of yuan. Especially when high-precision testing or covering a large area of structure is required, the demand for equipment testing is more significant.
[0005] (2) Reliance on manual operation, with low efficiency and accuracy. Since manual operation and the interpretation of test results are highly dependent on the operator's experience and judgment, this human factor can easily introduce subjective errors, which may lead to deviations in the determination of the actual strength of the structure. This deviation may not only affect the accuracy of the test results, but may also have an adverse impact on the safety assessment of the structure and increase potential risks.
[0006] (3) Poor universality. Single nondestructive testing methods perform well under specific conditions, but due to the limitations of technical characteristics and operational requirements, these methods are often difficult to be widely used in different types of projects. This limitation makes it difficult for these testing methods to be universally used in different engineering projects, limiting their practical application scope.
[0007] (4) The installation and layout of the instruments are complex. In particular, some detection instruments need to be laid out in advance, and the requirements are extremely high. During the layout process, the installation position, angle and environmental adaptability need to be accurately designed to ensure the accuracy and reliability of the monitoring data. Due to the complexity of the requirements, the layout work needs to be carried out by personnel with rich professional knowledge, which is not conducive to the promotion and application of the monitoring method.
[0008] As a type of electromagnetic wave, WiFi has the characteristics of strong penetration, wide coverage, and sensitive signal reflection. When WiFi signals penetrate structures such as tunnels, houses, bridges, etc., they will experience signal attenuation and multipath effects. By combining machine learning algorithms, these attenuation, penetration, and reflection characteristics can be used to build an internal model of the building structure, thereby achieving non-destructive testing of the internal structure.
[0009] Based on the above shortcomings and characteristics, in the field of non-destructive testing of buildings and structures, there is a need for a method that can solve the shortcomings of the current traditional reinforced concrete non-destructive testing methods such as low detection efficiency, high detection cost, and lack of detection universality, and to achieve an efficient, low-cost and universally feasible rapid structural health detection method for building structures. Summary of the invention
[0010] The object of the present invention is to provide a WiFi-based building structure detection method, which is characterized by comprising the following steps:
[0011] Step 1: Database collection phase: Conduct 1-1 data collection work on all types of buildings and structures that are in normal operation and maintenance and buildings and structures with structural damage.
[0012] WiFi signal base stations are set up inside the building space, which should meet the following requirements: 1. The WiFi signal can cover the entire building; 2. The WiFi signal should use a suitable frequency so that it can penetrate most of the internal structure of the building; 3. If it does not meet the requirements, multiple WiFi base stations of the same model should be deployed to meet the above requirements. Use mobile data collection equipment to collect information such as WiFi signal strength, wavelength, frequency, etc. at various locations inside the building, and collect and organize them into a database.
[0013] Step 2: Database training: Extract the WiFi signal features collected in step 1, perform comparative fusion learning on the data in the learning database, extract the WiFi strength features of various types of buildings under different working conditions, and form an integrated database. For the extracted data, use WiFi strength, building type, and health status as features to perform database training and form a model for health status evaluation and damage identification of different buildings.
[0014] Step 3: Structural data collection phase: For the structures to be tested, data collection in the form of S1 is carried out, and the required data information is collected inside the completed structures to be tested, including structure data and WiFi data. The structure data is the design drawing of the structure, including the material and spatial distribution information data of each wall, plate, column, beam and other structure. The collection of WiFi data is based on meeting the three requirements of 1, 2, and 3. WiFi signal base stations are deployed when the structures are completed or in the operation and maintenance stage, and various WiFi data including the strength, wavelength, frequency and other information of WiFi at various spatial locations in the structures are collected.
[0015] Step 4: Structural data analysis phase: Call the trained building health status evaluation and damage identification model obtained in step 2, and perform machine learning training with the building data to be tested and the WiFi data collected in step 3 to obtain a structural health status evaluation model for the structure under different health conditions.
[0016] Step 5: Structural health monitoring and evaluation phase: Carry out long-term structural health status monitoring. The WiFi base stations deployed in step 3 will work continuously for a long time. When personnel move in the buildings to be tested, their mobile devices will automatically collect WiFi data and continuously transmit the newly collected data to the health status evaluation model. The model compares and integrates machine learning to analyze the health status and damage status of the buildings to be tested, and gives a structural health evaluation. If it is healthy, it will continue to operate. If it is damaged, the damage type, degree of damage, and scope of damage will be indicated to provide data support for the operation and maintenance of buildings.
[0017] Compared with the prior art, the beneficial effects of the present invention are mainly reflected in:
[0018] 1. The method of the present invention is based on WiFi base station detection, the equipment layout is simpler, the detection equipment cost is lower, the efficiency is higher, and it can realize intelligent detection of reinforced concrete throughout the life cycle of unit building structures.
[0019] 2. The method of the present invention can deploy base stations according to different building architectures, and has stronger universality.
[0020] 3. The method of the present invention can realize long-term strength detection for the same building structure, has strong pertinence, and relatively improves detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 The present invention is a flowchart of a WiFi-based building structure detection method.
[0022] Figure 2 The schematic diagram of a WiFi-based building structure detection method of the present invention.
[0023] Among them, 1. WiFi base station; 2. Mobile data receiving equipment; 3. Reinforced concrete; 4. Steel bars; 5. Cavity; 6. Moving route of detection equipment; 7. WiFi electromagnetic wave signal. DETAILED DESCRIPTION
[0024] The following will be described in more detail with reference to a schematic diagram of a WiFi-based building structure detection method of the present invention, in which a preferred embodiment of the present invention is shown. It should be understood that those skilled in the art can modify the present invention described herein while still achieving the beneficial effects of the present invention. Therefore, the following description should be understood as being widely known to those skilled in the art and not as a limitation to the present invention.
[0025] Example 1
[0026] like Figure 1 As shown, the principle of the WiFi-based building structure detection method of the present invention is: based on the electromagnetic wave propagation characteristics including signal attenuation, signal reflection and refraction and multipath effect of WiFi signals.
[0027] The above-mentioned WiFi signal attenuation refers to the fact that the strength of the WiFi signal will be significantly reduced when it passes through building materials, especially when it encounters dense and conductive materials such as steel bars, which will cause the signal to be severely attenuated during penetration and reduce the signal strength.
[0028] Signal attenuation can be analyzed by testing the WiFi signal strength and analyzing the thickness and density of building materials. For buildings, the following loss formula is used for calculation:
[0029]
[0030] Among them, PL0 refers to the signal strength of the WiFi signal when it propagates in free space, PL is the received signal strength, d is the distance the signal propagates, f is the frequency of the signal, c is the speed of light, and W i is the additional loss of signal strength caused by buildings, n is the path loss exponent, and N is the number of obstacles.
[0031] The reflection of the above-mentioned WiFi signal includes specular reflection and diffuse reflection, which means that when the WiFi signal touches the boundary of different media, part of the energy will be reflected back to the original medium. Specular reflection is more likely to occur at a smooth interface with high dielectric constant and conductivity, while diffuse reflection is more likely to occur otherwise.
[0032] The principle of electromagnetic wave signal reflection is that when WiFi signals encounter heterogeneous materials such as internal structures or cavities, they will be reflected. The reflected signal will return to the signal source and form an echo. By measuring the echo, we can analyze and obtain information about the internal materials of the building, and realize the mapping of the internal structure of the building.
[0033] The refraction of WiFi signals refers to the change in the propagation direction of electromagnetic waves from one medium into another due to the change in propagation speed, resulting in refraction.
[0034] The refraction angle of WiFi signals is based on Snell's law:
[0035]
[0036] Among them, θ2 is the refraction angle, θ1 is the incident angle, n is the refractive index, ε r is the relative dielectric constant, μ r is the relative magnetic permeability.
[0037] The multipath propagation of the above-mentioned WiFi signal refers to the phenomenon that when the WiFi signal encounters multiple contact surfaces such as structural changes and holes during propagation, multiple reflections and refractions will occur, resulting in the signal reaching the signal receiving point through multiple paths, affecting the phase and intensity changes of the signal.
[0038] The above-mentioned propagation characteristics of electromagnetic waves are based on the principle that WiFi signals will encounter steel bars, gaps and other materials in reinforced concrete during propagation. The dielectric constants and conductivity of these different materials will affect the propagation of WiFi signals, resulting in signal attenuation and reflection.
[0039] The principle of the above-mentioned attenuation of electromagnetic wave signals is that when WiFi signals pass through building structures, the signal strength will be weakened due to the absorption and scattering of the materials. In particular, steel structures, due to their conductivity, will significantly absorb and reflect WiFi signals. By measuring the degree of signal attenuation, non-destructive testing of building structures can be achieved.
[0040] The above-mentioned non-destructive testing method is a method used to evaluate the structural performance and strength performance of buildings and structures. It will not cause destruction or permanent damage to the object being tested during the testing process.
[0041] Example 2
[0042] like Figure 2 As shown, a WiFi-based building structure detection method includes the following steps:
[0043] Step 1
[0044] Database collection stage: S1 data collection work is carried out in all kinds of buildings and structures that are in normal operation and maintenance and buildings and structures with structural damage. A WiFi signal base station 1 is set up inside the building space, which should meet the following requirements: ① The WiFi signal can cover the entire interior of the building; ② The WiFi signal should use a suitable frequency so that it can penetrate most of the internal structures of the building; ③ If it does not meet the requirements, multiple WiFi base stations of the same model should be arranged to meet the above requirements. Use mobile collection equipment 2 to collect information such as WiFi signal strength, wavelength, frequency, etc. at various locations inside the building, and collect and organize them into a database.
[0045] Step 2
[0046] Database training stage: As in S2.1, extract the WiFi signal features collected in step 1, conduct comparative fusion learning on the data in the learning database, extract the WiFi strength features of various types of buildings under different working conditions, and form an integrated database. For the extracted data, use WiFi strength, building type, and health status as features to conduct S2.2 training to form a model for health status evaluation and damage identification of different buildings.
[0047] Step 3
[0048] Structural data collection stage: For the structures to be tested, carry out S3.1 as S1.2 data collection, and collect the required data information inside the completed structures to be tested, including structure data and WiFi data. The structure data is the design drawing of the structure, including the material and spatial distribution information data of each wall, plate, column, beam and other structure. Carry out 3.2, as in step 1, ①②③ requirements, deploy WiFi signal base stations when the structure is completed or in the operation and maintenance stage, and collect various WiFi data including the strength, wavelength, frequency and other information of WiFi at various spatial locations in the structure.
[0049] Step 4
[0050] Structural data analysis phase: Carry out S4 health status assessment model training, call the trained building health status assessment and damage identification model obtained in S2.2, and conduct machine learning training with the building data to be tested collected by S3.1 and the WiFi data collected by S3.2 to obtain the structural health status assessment model under different health conditions for the structure.
[0051] Step 5
[0052] Structural health monitoring and evaluation stage: Carry out S5 long-term structural health status monitoring. The WiFi base stations deployed in step 3 will work continuously for a long time. When personnel move in the buildings to be tested, their mobile devices will automatically collect WiFi data in S3.2 and continuously transmit the newly collected data to the health status evaluation model obtained in step 4. The model compares and integrates machine learning to analyze the health status and damage status of the buildings to be tested, and gives a structural health evaluation. If it is healthy, the health monitoring system will continue to operate normally. If it is damaged, the damage type, degree and scope will be indicated to provide data support for the operation and maintenance of buildings.
[0053] Structural health information of buildings is provided in a hierarchical system, specifically, healthy, slightly damaged, moderately damaged, and severely damaged.
[0054] Based on Examples 1 and 2, the principle of the detection method of the present invention is as follows:
[0055] The WiFi base station 1 arranged in the building will continuously emit WiFi electromagnetic wave signals 7. When it touches the structure to be tested (taking the reinforced concrete 3 structure as an example), the signal will be reflected, refracted and multipathed. When the signal touches the surface of reinforced concrete, partial reflection and partial refraction will occur. When the refracted signal touches the steel bar 4, total reflection such as the signal on the left will occur, and the signal will be reflected out of the structure; when the refracted signal touches the cavity 5, further reflection and refraction such as the WiFi signal on the right will occur. Due to the different internal structures of the building to be tested, the reflected / emitted signals will converge, and different signal strengths, wavelengths and frequencies will be generated at different locations in the building space. When the mobile monitoring device 2 moves along the monitoring device moving route 6, it will collect the above-mentioned different WiFi signal strengths, frequencies, wavelengths and other information. This information is the WiFi data information collected in S2.1 and S3.2. Using this information, the health status of the docking structure can be analyzed and evaluated, and the non-destructive monitoring of the building to be tested can be achieved.
[0056] The above is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any technician in the relevant technical field, without departing from the scope of the technical solution of the present invention, makes any form of equivalent replacement or modification to the technical solution and technical content disclosed in the present invention, which does not depart from the content of the technical solution of the present invention and still falls within the protection scope of the present invention.
Claims
1. A WiFi-based building structure detection method, characterized in that: The steps include: S1: Collect data on various types of buildings and structures in normal operation and maintenance as well as buildings and structures with structural damage to complete the database; S2: Train the collected database to obtain health status evaluation and damage identification models for different buildings and structures; S3: Collect data on the buildings to be tested; S4: using the database obtained in S3, perform machine learning training on the health status evaluation and damage identification model obtained in S2 to obtain a structural health status evaluation model under different health conditions for the building to be tested; S5: Continue S3 and input the latest collected data into the trained structural health status assessment model to obtain the structural health information at that moment and realize the structural detection of the building.
2. The WiFi-based building structure detection method according to claim 1, characterized in that: The S1 specifically includes: setting up a WiFi signal base station inside the building space, and using a mobile collection device to collect WiFi data from various locations inside the building, and collecting and collating the data into a database; Among them, the WiFi signal base station simultaneously meets the following requirements: the WiFi signal covers the entire interior of the building, and the WiFi signal has the characteristic of penetrating the internal structure of the building; when a single WiFi signal base station cannot meet the requirements, multiple WiFi signal base stations are set up.
3. The WiFi-based building structure detection method according to claim 2, characterized in that: The S2 specifically includes the following steps: S21: extract the collected WiFi signal features, perform comparative fusion learning on the data in the database, extract the WiFi strength features of various types of buildings under different working conditions, and form an integrated database; S22: Based on the extracted data, WiFi strength, building type and health status are used as features for training to form a health status evaluation and damage identification model for different buildings.
4. The WiFi-based building structure detection method according to claim 1, characterized in that: In S3, the collected data include the building data and WiFi data of the building to be tested, wherein the building data is the design drawing of the building, including building materials and spatial distribution information data, and the WiFi data is the WiFi signal data of each spatial position.
5. The WiFi-based building structure detection method according to claim 1, characterized in that: In S4, the trained building health status evaluation and damage identification model obtained in S3 is called, and the structural health status evaluation model under different health conditions of the building to be tested is obtained by performing machine learning training on the building data to be tested and the WiFi data with the model.
6. The WiFi-based building structure detection method according to claim 1, characterized in that: In S5, when the structural health information is damage, the damage type, damage degree and damage range are obtained.