Concrete member detection system and method based on big data

Abstract

The invention relates to the technical field of concrete member detection, and discloses a concrete member detection system and method based on big data, and the system comprises a radar wave detection module which is used for transmitting a radar wave to a target concrete member, and receiving a reflection signal reflected when the radar wave encounters a medium interface in the target concrete member; an infrared imaging detection module; an environment monitoring module; the analysis processing module is used for receiving the reflection signal, the temperature distribution image and the environment data, obtaining the defect state of the target concrete member according to the reflection signal, and evaluating the defect state in combination with the temperature distribution image and the environment data; and the early warning module is used for sending out an early warning signal when the damaged target concrete member is detected according to the evaluation result. The damage of the concrete member is detected by combining a radar wave detection method and an infrared imaging detection method, so that the detection accuracy is improved while the member is not damaged.

Description

Technical Field

[0001] The present invention relates to the technical field of concrete component detection, and in particular to a concrete component detection system and method based on big data. Background Art

[0002] Concrete is one of the most important civil engineering materials in contemporary times. It is an artificial stone material made of cementitious materials, granular aggregates (also called aggregates), water, and admixtures and additives added when necessary in a certain proportion, mixed evenly, compacted, and cured and hardened. Concrete components refer to components such as beams, slabs, columns, and foundations made of concrete.

[0003] Due to the widespread use of reinforced concrete components in concrete structures, their construction quality fluctuates greatly, often leaving congenital defects in material properties, geometric dimensions, etc. These defects may include insufficient material strength, dimensional deviation, honeycomb surface, holes, cracks, insufficient thickness of protective layer, exposed steel bars, etc. In addition, due to the characteristics of the component material itself, reinforced concrete components may also suffer from cracks, concrete corrosion and freeze-thaw, steel bar corrosion, and other damage during use.

[0004] In order to ensure the safety and reliability of concrete components, they need to be regularly inspected and evaluated. However, traditional concrete component inspection methods may destroy the structure and cause damage to the components. Therefore, a concrete component inspection system and method based on big data is proposed to perform non-destructive inspection of concrete components. Summary of the invention

[0005] The purpose of the present invention is to provide a concrete component detection system and method based on big data to solve the problems mentioned in the background technology.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A concrete component detection system based on big data, comprising:

[0008] A radar wave detection module, used for transmitting radar waves to a target concrete component and receiving a reflection signal when the radar wave encounters a medium interface inside the target concrete component;

[0009] An infrared imaging detection module, used to heat the target concrete component and obtain a temperature distribution image of the surface of the target concrete component;

[0010] Environmental monitoring module, used to monitor environmental information in real time and obtain environmental data;

[0011] an analysis and processing module, configured to receive the reflection signal, the temperature distribution image and the environmental data, obtain the defect state of the target concrete component according to the reflection signal, and evaluate the defect state in combination with the temperature distribution image and the environmental data;

[0012] The early warning module sends out an early warning signal when a damaged target concrete component is detected according to the evaluation result.

[0013] Preferably, the process of obtaining the defect state of the target concrete component according to the reflection signal includes:

[0014] Analyzing the waveform, intensity and time of the reflected signal according to the reflected signal;

[0015] By formula:

[0016]

[0017] in,

[0018] Calculate the defect state coefficient D of the i-th region of the target concrete component i ;

[0019] Wherein, B0 is the reflection intensity of normal concrete around the target concrete component, B S is the reflection intensity of the reflection signal of the i-th area of ​​the target concrete component; L0 is the path length of the reflection signal actually measured, v0 is the propagation speed of the transmission signal, Δt is the propagation time of the transmission signal from transmission to reception, Δl is the preset path difference; t1~t2 is the corresponding time period of the transmission signal, Y i (t) is the waveform change curve of the reflection signal of the i-th area of ​​the target concrete component, Y i0 (t) a standard waveform change curve of the reflection signal of the i-th area of ​​the target concrete component, where ΔSY is a reference value of the waveform change of the corresponding area; N Yi is the total number of pixels of the waveform change curve, N i重合 is the number of pixel points where the waveform change curve overlaps with the standard waveform change curve; δ1, δ2, α1, α2 and α3 are preset weight coefficients.

[0020] Preferably, the process of heating the target concrete component and obtaining the temperature distribution image on the surface of the target concrete component includes:

[0021] After completing the radar wave detection, using an infrared thermal imager to perform infrared imaging detection on the target concrete component;

[0022] Acquire the temperature value of each area in the infrared image of the target concrete component, and use color coding to represent different temperature values;

[0023] The area with the color coding is plotted on a two-dimensional plane to form a temperature distribution image.

[0024] Preferably, the process of evaluating the defect state in combination with the temperature distribution image and the environmental data includes:

[0025] Adjusting the temperature distribution image according to the acquired environmental data;

[0026] Acquire the defect state corresponding interval of each area of ​​the target concrete component according to the adjusted temperature distribution image;

[0027] The defect state coefficients obtained in each region are matched with the corresponding defect state corresponding intervals respectively:

[0028] If the defect state coefficient is within the defect state corresponding interval, then the defect state is the defect state corresponding to the defect state corresponding interval;

[0029] Otherwise, the defect state is the defect state corresponding to the defect state coefficient.

[0030] Preferably, the process of adjusting the temperature distribution image according to the acquired environmental data includes:

[0031] By formula:

[0032]

[0033] Calculate the temperature correction value ΔT;

[0034] Calibrate the temperature value of each area in the infrared image of the target concrete component according to the temperature correction value ΔT, and adjust the temperature distribution image;

[0035] Where n is the number of environmental parameters of the environmental data, m∈[1,n], γ m is the weight coefficient of the mth environmental parameter, μ m is the application coefficient of the mth environmental parameter, and g is the ambient temperature influence function.

[0036] Preferably, the process of obtaining the defect state corresponding intervals of each area of ​​the target concrete component according to the adjusted temperature distribution image includes:

[0037] Inputting the temperature distribution image into a trained defect state recognition model to obtain a corresponding defect category;

[0038] Obtaining a corresponding defect state corresponding interval according to the defect category;

[0039] Wherein, the defect state recognition model is a trained machine learning model.

[0040] Preferably, the process of issuing a warning signal when detecting a damaged target concrete component according to the evaluation result includes:

[0041] By formula:

[0042]

[0043] Calculate the overall defect coefficient Z;

[0044] The overall defect coefficient Z is compared with the preset threshold Z0:

[0045] If Z ≥ Z0, a warning signal is issued;

[0046] Otherwise, no warning signal is issued;

[0047] Wherein, k is the number of regions where the target concrete component is divided, i∈[1, k], D0 is the preset standard state coefficient, τ i is the weight coefficient corresponding to the i-th region.

[0048] A concrete component detection method based on big data, comprising:

[0049] Transmitting radar waves to a target concrete component, and receiving a reflection signal when the radar wave encounters a medium interface inside the target concrete component;

[0050] After completing the radar wave detection, the target concrete component is heated, and a temperature distribution image of the surface of the target concrete component is obtained, and at the same time, environmental information is monitored in real time and environmental data is obtained;

[0051] receiving the reflection signal, the temperature distribution image and the environmental data, obtaining the defect state of the target concrete component according to the reflection signal, and evaluating the defect state in combination with the temperature distribution image and the environmental data;

[0052] According to the evaluation result, a warning signal is issued when a damaged target concrete component is detected.

[0053] Beneficial effects of the present invention:

[0054] The big data-based concrete component detection system and method detect the damage of concrete components by combining radar waves and infrared imaging detection methods. At the same time, the environmental information is monitored in real time and environmental data is obtained through the environmental monitoring module. The defect state of the target concrete component is obtained according to the reflection signal, and the defect state is evaluated in combination with the temperature distribution image and the environmental data. According to the evaluation result, an early warning signal is issued when a damaged target concrete component is detected, so as to accurately understand the damage condition of the target concrete component and improve the accuracy and efficiency of detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The present invention will be further described below in conjunction with the accompanying drawings.

[0056] Figure 1 It is a schematic diagram of module connection of the concrete component detection system of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Concrete non-destructive testing technology refers to the technology of directly and quantitatively testing the concrete strength and defects of concrete structural components in situ without destroying the concrete structural components. This technology can accurately evaluate the performance and damage of concrete components without destroying the components, providing a reliable basis for the reinforcement and maintenance of engineering structures.

[0059] See also Figure 1 As shown, the present invention is a concrete component detection system based on big data, comprising:

[0060] A radar wave detection module is used to transmit radar waves to a target concrete component and receive a reflected signal when the radar wave encounters a medium interface inside the target concrete component;

[0061] An infrared imaging detection module is used to heat the target concrete component and obtain a temperature distribution image of the surface of the target concrete component;

[0062] Environmental monitoring module, used to monitor environmental information in real time and obtain environmental data;

[0063] An analysis and processing module is used to receive the reflection signal, the temperature distribution image and the environmental data, obtain the defect state of the target concrete component according to the reflection signal, and evaluate the defect state in combination with the temperature distribution image and the environmental data;

[0064] The early warning module sends out an early warning signal when detecting a damaged target concrete component based on the evaluation results.

[0065] Through the above technical scheme, radar wave and infrared imaging detection methods are combined to detect damage to concrete components. First, the target concrete components are cleaned and divided into areas as necessary to ensure that the surface is clean and flat for subsequent detection; at the same time, radar wave detection instruments and infrared thermal imagers are prepared, and necessary calibration and settings are performed; the radar wave transmitting antenna is placed on the surface of the component, and high-frequency electromagnetic waves are emitted into the concrete and the reflected signals are received to detect defects inside the concrete and information such as the position of steel bars; cracks, cavities and other defects inside the concrete can be inferred based on the characteristics of the received reflected signals; after completing the radar wave detection, the infrared thermal imager is used to perform infrared imaging detection on the target concrete component; the concrete component is heated, and the infrared thermal imager is used to capture the temperature distribution image on the surface of the component. By comparing the temperature difference between normal areas and abnormal areas, the internal defects and damage of concrete components can be further evaluated. At the same time, the environmental information is monitored in real time and environmental data is obtained through the environmental monitoring module. The defect status of the target concrete component is obtained according to the reflection signal, and the defect status is evaluated in combination with the temperature distribution image and environmental data. According to the evaluation results, an early warning signal is issued when a damaged target concrete component is detected, so as to accurately understand the damage status of the target concrete component and improve the accuracy of detection.

[0066] The process of obtaining the defect state of the target concrete component according to the reflection signal includes:

[0067] Analyze the waveform, intensity and time of the reflected signal according to the reflected signal;

[0068] By formula:

[0069]

[0070] in,

[0071] Calculate the defect state coefficient D of the i-th region of the target concrete component i ;

[0072] Among them, B0 is the reflection intensity of normal concrete around the target concrete component, B Sis the reflection intensity of the reflection signal of the i-th area of ​​the target concrete component; L0 is the path length of the reflection signal actually measured, v0 is the propagation speed of the transmitted signal, Δt is the propagation time of the transmitted signal from transmission to reception, Δl is the preset path difference; t1~t2 is the corresponding time period of the transmitted signal, Y i (t) is the waveform change curve of the reflection signal of the i-th area of ​​the target concrete component, Y i0 (t) the standard waveform change curve of the reflection signal of the i-th area of ​​the target concrete component, ΔSY is the reference value of the waveform change of the corresponding area; N Yi is the total number of pixels in the waveform change curve, N i重合 is the number of pixel points where the waveform change curve overlaps with the standard waveform change curve; δ1, δ2, α1, α2 and α3 are preset weight coefficients.

[0073] Through the above technical solution, this embodiment proposes a method for obtaining the defect state of the target concrete component according to the reflection signal. Specifically, through the formula Calculate the defect state coefficient D of the i-th region of the target concrete component i , thus analyzing the defect state of the target concrete component by analyzing the waveform, intensity and time characteristics of the reflected signal, where The waveform change curve of the reflected signal is compared with the standard waveform change curve, and the defect state is analyzed through the difference between the two, and then the defect state coefficient is obtained, thereby improving the accuracy of detection.

[0074] It should be noted that the preset path difference Δl, the standard waveform change curve Y of the reflection signal of the i-th area of ​​the target concrete component i0 (t), the waveform change reference value ΔSY of the corresponding area, and the preset weight coefficients δ1, δ2, α1, α2 and α3 are all selectively formulated through experimental data and will not be described in detail here.

[0075] The process of heating the target concrete component and obtaining the temperature distribution image on the surface of the target concrete component includes:

[0076] After completing the radar wave detection, use an infrared thermal imager to perform infrared imaging detection on the target concrete component;

[0077] Obtain the temperature value of each area in the infrared image of the target concrete component, and use color coding to represent different temperature values;

[0078] Plot color-coded areas on a 2D plane to create a temperature distribution image.

[0079] Through the above technical solution, this embodiment proposes a method for obtaining a temperature distribution image on the surface of a target concrete component. Specifically, after completing the radar wave detection, an infrared thermal imager is used to perform infrared imaging detection on the target concrete component; the temperature value of each area in the infrared image of the target concrete component is obtained, and color coding is used to represent different temperature values, for example, warmer colors represent higher temperatures, and colder colors represent lower temperatures, and the colors are set to gradient colors, and the gradient speed is related to a preset scale unit value; the area with color coding is drawn on a two-dimensional plane to form a temperature distribution image, which is conducive to the recognition of the defect state recognition model.

[0080] The process of adjusting the temperature distribution image according to the acquired environmental data includes:

[0081] By formula:

[0082]

[0083] Calculate the temperature correction value ΔT;

[0084] Calibrate the temperature value of each area in the infrared image of the target concrete component according to the temperature correction value ΔT, and adjust the temperature distribution image;

[0085] Where n is the number of environmental parameters of the environmental data, m∈[1,n], γ m is the weight coefficient of the mth environmental parameter, μ m is the application coefficient of the mth environmental parameter, and g is the ambient temperature influence function.

[0086] Through the above technical solution, this embodiment proposes a method for adjusting the temperature distribution image according to the acquired environmental data. Specifically, through the formula Calculate the temperature correction value ΔT; calibrate the temperature value of each area in the infrared image of the target concrete component according to the temperature correction value ΔT, and adjust the temperature distribution image, thereby eliminating the interference of environmental factors on the temperature distribution image and improving the accuracy of detection.

[0087] It should be noted that the weight coefficient γ of the mth environmental parameter is m 、Application coefficient μ of the mth environmental parameter m The environmental temperature influence function g is obtained after fitting the experimental data. The environmental parameters include but are not limited to temperature, humidity, wind speed, solar radiation, etc.

[0088] The process of obtaining the corresponding intervals of the defect states of each area of ​​the target concrete component according to the adjusted temperature distribution image includes:

[0089] Input the temperature distribution image into the trained defect state recognition model to obtain the corresponding defect category;

[0090] Obtain the corresponding interval of the defect status according to the defect category;

[0091] Among them, the defect state recognition model is a trained machine learning model.

[0092] Through the above technical scheme, this embodiment proposes a method for obtaining the corresponding intervals of the defect states of each area of ​​the target concrete component according to the adjusted temperature distribution image. Specifically, the temperature distribution image is input into a trained defect state recognition model to obtain the corresponding defect category; the corresponding intervals of the defect state are obtained according to the defect category; these intervals are determined according to the classification results of the model, and each interval represents a specific defect state or category, such as "normal", "defect 1", "defect 2", etc., and each category corresponds to a specific defect interval.

[0093] Among them, the defect state recognition model is a trained machine learning model, and the machine learning algorithm used is based on convolutional neural network (CNN). Convolutional neural network (CNN) is a type of feedforward neural network (Feedforward Neural Networks) that includes convolution calculation and has a deep structure, and is often used to analyze visual images. In the above technical solution, the convolutional neural network model building and the generation and processing of training samples are implemented through conventional machine learning algorithms in the prior art, which will not be described in detail here.

[0094] The process of evaluating defect status by combining temperature distribution images and environmental data includes:

[0095] Adjust the temperature distribution image according to the acquired environmental data;

[0096] Obtaining the corresponding interval of the defect state of each area of ​​the target concrete component according to the adjusted temperature distribution image;

[0097] Match the defect state coefficients obtained in each area with the corresponding defect state corresponding intervals:

[0098] If the defect state coefficient is within the defect state corresponding interval, the defect state is the defect state corresponding to the defect state corresponding interval;

[0099] Otherwise, the defect state is the defect state corresponding to the defect state coefficient.

[0100] Through the above technical solution, this embodiment adjusts the temperature distribution image by acquiring environmental data, thereby improving the accuracy of infrared imaging detection, and then obtains the defect state corresponding interval of each area of ​​the target concrete component according to the adjusted temperature distribution image; the defect state coefficient obtained in each area is matched with the corresponding defect state corresponding interval respectively. If the defect state coefficient is within the defect state corresponding interval, it means that the damage state of the target concrete component detected by the radar wave and infrared imaging detection methods is the same, otherwise, the defect state is the defect state corresponding to the defect state coefficient. Because radar technology has a longer sensing distance and higher sensitivity, it can achieve all-round sensing, while infrared technology has a relatively short sensing distance, a small angle, and is greatly affected by the environment. Radar wave detection is further verified by infrared imaging detection, which improves the accuracy of detection. At the same time, when the detections of the two are inconsistent, re-detection can be performed to further improve the accuracy of detection.

[0101] The process of issuing a warning signal when detecting a damaged target concrete component based on the evaluation results includes:

[0102] By formula:

[0103]

[0104] Calculate the overall defect coefficient Z;

[0105] Compare the overall defect coefficient Z with the preset threshold Z0:

[0106] If Z ≥ Z0, a warning signal is issued;

[0107] Otherwise, no warning signal is issued;

[0108] Where k is the number of regions where the target concrete component is divided, i∈[1, k], D0 is the preset standard state coefficient, τ i is the weight coefficient corresponding to the i-th region.

[0109] Through the above technical solution, this embodiment proposes a method for issuing a warning signal when detecting a damaged target concrete component according to the evaluation result. Specifically, through the formula Calculate the overall defect coefficient Z; compare the overall defect coefficient Z with the preset threshold Z0. Obviously, if Z≥Z0, there is damage and an early warning signal is issued; otherwise, no early warning signal is issued.

[0110] It should be noted that the preset standard state coefficient D0 and the weight coefficient τ corresponding to the i-th region i It is obtained by fitting the experimental data and will not be described in detail here.

[0111] A concrete component detection method based on big data, comprising:

[0112] Transmitting radar waves to the target concrete component and receiving reflected signals when the radar waves encounter the medium interface inside the target concrete component;

[0113] After completing the radar wave detection, the target concrete component is heated and the temperature distribution image of the surface of the target concrete component is obtained. At the same time, the environmental information is monitored in real time and the environmental data is obtained;

[0114] Receiving reflected signals, temperature distribution images and environmental data, obtaining defect status of the target concrete component according to the reflected signals, and evaluating the defect status in combination with the temperature distribution images and environmental data;

[0115] Based on the evaluation results, an early warning signal is issued when a damaged target concrete component is detected.

[0116] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A concrete component detection system based on big data, characterized in that: include: A radar wave detection module, used for transmitting radar waves to a target concrete component and receiving a reflection signal when the radar wave encounters a medium interface inside the target concrete component; An infrared imaging detection module, used to heat the target concrete component and obtain a temperature distribution image of the surface of the target concrete component; Environmental monitoring module, used to monitor environmental information in real time and obtain environmental data; an analysis and processing module, configured to receive the reflection signal, the temperature distribution image and the environmental data, obtain the defect state of the target concrete component according to the reflection signal, and evaluate the defect state in combination with the temperature distribution image and the environmental data; The early warning module sends out an early warning signal when detecting a damaged target concrete component according to the evaluation result.

2. The big data-based concrete component detection system according to claim 1 is characterized in that: The process of obtaining the defect state of the target concrete component according to the reflection signal includes: Analyzing the waveform, intensity and time of the reflected signal according to the reflected signal; By formula: in, Calculate the defect state coefficient D of the i-th region of the target concrete component i ; Wherein, B0 is the reflection intensity of normal concrete around the target concrete component, B S is the reflection intensity of the reflection signal of the i-th area of ​​the target concrete component; L0 is the path length of the reflection signal actually measured, v0 is the propagation speed of the transmission signal, Δt is the propagation time of the transmission signal from transmission to reception, Δl is the preset path difference; t1~t2 is the corresponding time period of the transmission signal, Y i (t) is the waveform change curve of the reflection signal of the i-th area of ​​the target concrete component, Y i0 (t) a standard waveform change curve of the reflection signal of the i-th area of ​​the target concrete component, ΔSY is a waveform change reference value of the corresponding area; NY i is the total number of pixels of the waveform change curve, N i重合 is the number of pixel points where the waveform change curve overlaps with the standard waveform change curve; δ1, δ2, α1, α2 and α3 are preset weight coefficients.

3. The big data-based concrete component detection system according to claim 1, characterized in that: The process of heating the target concrete component and obtaining a temperature distribution image on the surface of the target concrete component includes: After completing the radar wave detection, using an infrared thermal imager to perform infrared imaging detection on the target concrete component; Acquire the temperature value of each area in the infrared image of the target concrete component, and use color coding to represent different temperature values; The area with the color coding is plotted on a two-dimensional plane to form a temperature distribution image.

4. The big data-based concrete component detection system according to claim 2, characterized in that: The process of evaluating the defect state by combining the temperature distribution image and the environmental data includes: Adjusting the temperature distribution image according to the acquired environmental data; Acquire the defect state corresponding interval of each area of ​​the target concrete component according to the adjusted temperature distribution image; The defect state coefficients obtained in each region are matched with the corresponding defect state corresponding intervals respectively: If the defect state coefficient is within the defect state corresponding interval, then the defect state is the defect state corresponding to the defect state corresponding interval; Otherwise, the defect state is the defect state corresponding to the defect state coefficient.

5. The big data-based concrete component detection system according to claim 1, characterized in that: The process of adjusting the temperature distribution image according to the acquired environmental data includes: By formula: Calculate the temperature correction value ΔT; Calibrate the temperature value of each area in the infrared image of the target concrete component according to the temperature correction value ΔT, and adjust the temperature distribution image; Where n is the number of environmental parameters of the environmental data, m∈[1,n], γ m is the weight coefficient of the mth environmental parameter, μ m is the application coefficient of the mth environmental parameter, and g is the ambient temperature influence function.

6. The big data-based concrete component detection system according to claim 1, characterized in that: The process of obtaining the defect state corresponding intervals of each area of ​​the target concrete component according to the adjusted temperature distribution image includes: Inputting the temperature distribution image into a trained defect state recognition model to obtain a corresponding defect category; Obtaining a corresponding defect state corresponding interval according to the defect category; Wherein, the defect state recognition model is a trained machine learning model.

7. The big data-based concrete component detection system according to claim 1, characterized in that: The process of issuing a warning signal when detecting a damaged target concrete component according to the evaluation result includes: By formula: Calculate the overall defect coefficient Z; The overall defect coefficient Z is compared with the preset threshold Z0: If Z ≥ Z0, a warning signal is issued; Otherwise, no warning signal is issued; Wherein, k is the number of regions where the target concrete component is divided, i∈[1, k], D0 is the preset standard state coefficient, τ i is the weight coefficient corresponding to the i-th region.

8. A concrete component detection method based on big data, characterized in that: include: Transmitting radar waves to a target concrete component, and receiving a reflection signal when the radar wave encounters a medium interface inside the target concrete component; After completing the radar wave detection, the target concrete component is heated, and a temperature distribution image of the surface of the target concrete component is obtained, and at the same time, environmental information is monitored in real time and environmental data is obtained; receiving the reflection signal, the temperature distribution image and the environmental data, obtaining the defect state of the target concrete component according to the reflection signal, and evaluating the defect state in combination with the temperature distribution image and the environmental data; According to the evaluation result, a warning signal is issued when a damaged target concrete component is detected.

Images