阅读说明：本技术 一种套筒灌浆密实度智能检测方法 (Intelligent detection method for grouting compactness of sleeve ) 是由 卞德存 唐孟雄 孙晓立 周治国 杨军 邵继喜 赵亚宇 赵鸿彬 卓林波 于 2021-03-26 设计创作，主要内容包括：本发明公开了一种套筒灌浆密实度智能检测方法,通过小波分解钢筋套筒激振反馈波形,然后利用分形原理对分解后的波形进行盒维数分析,提取描述缺陷特征的分形特征向量F-B,最后将分形特征向量F-B作为BP神经网络的输入值,经BP神经网络智能分析判别后,输出钢筋套筒的灌浆缺陷类型及密度信息；通过这种智能识别方法对钢筋套筒灌浆密实度进行检测,可以大大的提高检测人员的检测效率、降低检测成本以及提高检测精度。(The invention discloses an intelligent detection method for sleeve grouting compactness, which decomposes an excitation feedback waveform of a steel bar sleeve by using wavelets, then performs box-dimension analysis on the decomposed waveform by using a fractal principle, and extracts a fractal feature vector F for describing defect features B Finally, fractal feature vector F B As an input value of the BP neural network, after intelligent analysis and judgment of the BP neural network, the grouting defect type and density information of the steel bar sleeve are output; the intelligent identification method is used for detecting the grouting compactness of the steel bar sleeve, so that the detection efficiency of detection personnel can be greatly improved, the detection cost is reduced, and the detection precision is improved.)

1. The intelligent detection method for the grouting compactness of the sleeve is characterized by comprising an intelligent detection tool for the grouting compactness of the sleeve, wherein the intelligent detection tool for the grouting compactness of the sleeve comprises a steel bar sleeve, steel bars are respectively embedded at two ends of the steel bar sleeve, and a grouting material for fixing the steel bars at the two ends of the steel bar sleeve is arranged in the steel bar sleeve; the reinforcing steel bar sleeve is provided with a grout outlet and a grout inlet;

the intelligent detection method for the grouting compactness of the sleeve comprises the following steps:

s1, preparing steel bar sleeves, wherein the number of the steel bar sleeves is set to be A, and the grouting defect types and the grouting defect densities of the steel bar sleeves are known;

s2, performing the following steps on the steel bar sleeve in the S1:

s21, arranging a vibration sensor at the grout inlet of the steel bar sleeve, wherein the vibration sensor is connected with data acquisition equipment, and the data acquisition equipment can receive signals of the vibration sensor and store the signals in real time;

s22, after the step s21 is completed, starting the data acquisition equipment, and enabling the slurry outlet of the steel bar sleeve to generate shock waves by using shock excitation equipment; acquiring a vibration response signal of the steel bar sleeve through a vibration sensor; the excitation equipment can control the excitation waves output each time to be consistent;

s23, loading the vibration response signal collected in the step s22 into a computer;

s24, selecting a Sym8 wavelet function according to the waveform of the vibration response signal of the step s23, wherein the value of the level of the wavelet decomposition of the Sym8 wavelet function is set as N;

then, for the vibration response signal of step s23, N-layer orthogonal wavelet decomposition is carried out by using the selected wavelet function to obtain the signal component { cA +1 wavelet decomposition in 1 st-N layer_N，cD_N，cD_N-1......cD₄，cD₃，cD₂，cD₁In which A_NBeing a low frequency component, cD_NIs a high frequency component;

s25, comparing A obtained in step s24 respectively_N，D_N，D_N-1......D₄，D₃，D₂，D₁Performing box dimension calculation to obtain box dimension F_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁；

s26, calculation step s 25F_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁Then calculating the average value by subtracting F from the average value_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁The resulting absolute value;

s27, the box-to-box dimension F from large to small according to the absolute value obtained in step s26_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁Rearranging to form fractal characteristic vector F_X＝{F₁，F₂，F₃，F₄......F_N-1、F_DN、F_AN}；

S3, obtaining a fractal feature vector F after the step S2 is finished_A、F_A-1、F_A-2......F₃、F₂、F₁(ii) a The obtained fractal feature vector F_A、F_A-1、F_A-2......F₃、F₂、F₁Guiding the grouting defect type and density of the steel bar sleeve corresponding to each fractal feature vector into a BP neural network in MATLAB software for training and learning, and storing;

s4, after the step S3 is completed, the steel bar sleeve to be detected is subjected to the operation of the step S2 to obtain a fractal feature vector F_B(ii) a Then fractal feature vector F_BAnd (4) outputting the grouting defect type and density of the steel bar sleeve after intelligent analysis and judgment of the BP neural network as the input value of the BP neural network trained in the step S3.

2. The intelligent detection method for grouting compactness of sleeve according to claim 1, wherein the Sym8 wavelet function in step s24 can be Haar wavelet function, Daubechies wavelet function or Coiflet wavelet function.

3. The intelligent detection method for the grouting compactness of the sleeve according to claim 1, wherein after the step S4, a step S5 is provided: bisection of feature vector F by X-ray method_BAccurately judging the corresponding steel bar sleeve, and then carrying out fractal characteristic vector F_BAnd importing the defect type and the density information of the steel bar sleeve into a BP neural network in MATLAB software to continue training.

4. The intelligent detection method for grouting compactness of sleeve according to claim 1, wherein the vibration excitation device is a hand hammer.

5. The intelligent detection method for grouting compactness of sleeve according to claim 1, wherein in the step s21, a coupling agent is coated on a contact surface of the vibration sensor and a grout inlet of the steel bar sleeve.

6. The intelligent detection method for grouting compactness of sleeves according to claim 5, wherein the coupling agent is butter.

7. The intelligent detection method for grouting compactness of sleeve according to claim 1, wherein in the step S1, the value of a is greater than or equal to 100.

8. The intelligent detection method for grouting compactness of sleeve according to claim 1, wherein in the step s24, the value of N is less than or equal to 7.

Technical Field

The invention belongs to the field of fabricated buildings, and particularly relates to an intelligent detection method for grouting compactness of a sleeve.

Background

Along with the rapid development of economy and urbanization in China, the building industrialization process is accelerated, and the traditional cast-in-place building technology cannot meet the development requirements of the building industry due to unreasonable resource allocation, low construction mechanization degree and poor construction operation environment. The prefabricated building has the advantages of high industrialization degree, high construction efficiency, energy conservation, environmental protection and the like, and is rapidly popularized and used in China in recent years.

The important characteristic of the prefabricated building technology is that the whole or partial structure of the building is assembled by prefabricated parts on the construction site, and the effective connection of the nodes among all the assembling components is the key technology of the prefabricated concrete structure and the key of whether the prefabricated concrete structure can be popularized and applied. In order to improve the shock resistance and integrity of the fabricated building, it is necessary to ensure a reliable connection between the fabricated building elements. The common assembly type building connection mode is mainly realized by adopting a steel bar sleeve, and the connection mode effectively ensures the integrity of the assembly type building, so that the shock resistance of the assembly type building is correspondingly improved, and the assembly type building connection mode is widely applied to building structures such as a room construction assembly type shear wall, a bridge assembly type box girder, a bridge abutment and the like.

The steel bar sleeve is mainly composed of connecting steel bars and a sleeve. Currently, the conventional method for evaluating the connection strength of the steel bar sleeve is to adopt unidirectional tension, high-stress repeated tension-compression tests, large-deformation repeated tension-compression tests and the like on a steel bar sleeve joint test piece; in a nondestructive testing method, although the information of the grouting compactness of the steel bar sleeve can be obtained to a certain extent by an ultrasonic method and an impact echo method, the judgment of a testing result is greatly influenced by human factors; the detection of the pre-embedded steel wire drawing method and the pre-embedded sensor method is time-consuming and labor-consuming, and the general investigation of the grouting compactness of the steel bar sleeve cannot be realized; although the detection effect of the X-ray method is visual and easy to read, the detection equipment is expensive, the operation flow is complex, the parallel sleeves cannot be detected, the detection depth is limited, and ray radiation exists, so that the human body is easily damaged. Therefore, no intelligent method for detecting the grouting compactness of the steel bar sleeve with high efficiency, low cost exists at present.

Disclosure of Invention

In order to overcome the above disadvantages of the prior art, an object of the present invention is to provide an intelligent detection method for grouting compactness of a sleeve, which aims to improve the detection efficiency and the intelligent degree of grouting compactness of the sleeve.

In order to achieve the purpose, the technical scheme adopted by the invention is as follows:

the intelligent detection method for the grouting compactness of the sleeve comprises an intelligent detection tool for the grouting compactness of the sleeve, wherein the intelligent detection tool for the grouting compactness of the sleeve comprises a steel bar sleeve, steel bars are respectively embedded at two ends of the steel bar sleeve, and grouting materials for fixing the steel bars at the two ends of the steel bar sleeve are arranged in the steel bar sleeve; the reinforcing steel bar sleeve is provided with a grout outlet and a grout inlet;

the intelligent detection method for the grouting compactness of the sleeve comprises the following steps:

s1, preparing steel bar sleeves, wherein the number of the steel bar sleeves is set to be A, and the grouting defect types and the grouting defect densities of the steel bar sleeves are known;

s2, performing the following steps on the steel bar sleeve in the S1:

s21, arranging a vibration sensor at the grout inlet of the steel bar sleeve, wherein the vibration sensor is connected with data acquisition equipment, and the data acquisition equipment can receive signals of the vibration sensor and store the signals in real time;

s22, after the step s21 is completed, starting the data acquisition equipment, and enabling the slurry outlet of the steel bar sleeve to generate shock waves by using shock excitation equipment; acquiring a vibration response signal of the steel bar sleeve through a vibration sensor; the excitation equipment can control the excitation waves output each time to be consistent;

s23, loading the vibration response signal collected in the step s22 into a computer;

s24, selecting a Sym8 wavelet function according to the waveform of the vibration response signal of the step s23, wherein the value of the level of the wavelet decomposition of the Sym8 wavelet function is set as N;

then, for the vibration response signal of step s23, N-layer orthogonal wavelet decomposition is carried out by using the selected wavelet function to obtain the signal component { cA +1 wavelet decomposition in 1 st-N layer_N，cD_N，cD_N-1......cD₄，cD₃，cD₂，cD₁In which A_NBeing a low frequency component, cD_NIs a high frequency component;

s25, comparing A obtained in step s24 respectively_N，D_N，D_N-1......D₄，D₃，D₂，D₁Performing box dimension calculation to obtain box dimension F_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁；

s26, calculation step s 25F_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁Then calculating the average value by subtracting F from the average value_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁The resulting absolute value;

s27, the box-to-box dimension F from large to small according to the absolute value obtained in step s26_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁Rearranging to form fractal characteristic vector F_X＝{F₁，F₂，F₃，F₄......F_N-1、F_DN、F_AN}；

S3, obtaining a fractal feature vector F after the step S2 is finished_A、F_A-1、F_A-2......F₃、F₂、F₁(ii) a The obtained fractal feature vector F_A、F_A-1、F_A-2......F₃、F₂、F₁Guiding the grouting defect type and density of the steel bar sleeve corresponding to each fractal feature vector into a BP neural network in MATLAB software for training and learning, and storing;

s4, after the step S3 is completed, the steel bar sleeve to be detected is subjected to the operation of the step S2 to obtain a fractal feature vector F_B(ii) a Then fractal feature vector F_BAnd (4) outputting the grouting defect type and density of the steel bar sleeve after intelligent analysis and judgment of the BP neural network as the input value of the BP neural network trained in the step S3.

Preferably, the Sym8 wavelet function in step s24 may also be a Haar wavelet function, Daubechies wavelet function or Coiflet wavelet function.

Preferably, after step S4, step S5 is provided: bisection of feature vector F by X-ray method_BAccurately judging the corresponding steel bar sleeve, and then carrying out fractal characteristic vector F_BAnd importing the defect type and the density information of the steel bar sleeve into a BP neural network in MATLAB software to continue training.

Preferably, the excitation device is a hand hammer.

Preferably, in step s21, a coupling agent is applied to a contact surface of the vibration sensor and the grout inlet of the steel bar sleeve.

Preferably, the coupling agent is butter.

Preferably, in step S1, a value of a is equal to or greater than 100.

Preferably, in the step s24, the value of N is less than or equal to 7.

Compared with the prior art, the scheme of the invention has the following specific beneficial effects:

decomposing the excitation feedback waveform of the steel bar sleeve by using wavelet, then carrying out box-dimension analysis on the decomposed waveform by using a fractal principle, and extracting a fractal feature vector F for describing defect features_BFinally, fractal feature vector F_BAs an input value of the BP neural network, after intelligent analysis and judgment of the BP neural network, the grouting defect type and density information of the steel bar sleeve are output; the intelligent identification method is used for detecting the grouting compactness of the steel bar sleeve, so that the detection efficiency of detection personnel can be greatly improved, the detection cost is reduced, and the detection precision is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a structural diagram of an intelligent detection tool for grouting compactness of a sleeve according to an embodiment of the invention;

FIG. 2 is a flow chart of an embodiment of the present invention;

description of reference numerals:

the device comprises a steel bar sleeve 1, a steel bar 2, a vibration sensor 3, a data acquisition device 4, a computer 5, a vibration excitation device 6, a grout outlet 11 and a grout inlet 12.

Detailed Description

So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments thereof which are illustrated in the appended drawings. It should be noted that the embodiments of the present invention and features of the embodiments may be combined with each other without conflict. In the following description, numerous specific details are set forth to provide a thorough understanding of the present invention, and the described embodiments are merely a subset of the embodiments of the present invention, rather than a complete embodiment. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

Referring to fig. 1 to 2, the invention discloses a sleeve grouting compactness intelligent detection method, which comprises a sleeve grouting compactness intelligent detection tool, wherein the sleeve grouting compactness intelligent detection tool comprises a steel bar sleeve 1, steel bars 2 are respectively embedded at two ends of the steel bar sleeve 1, and grouting materials for fixing the steel bars at the two ends of the steel bar sleeve are arranged in the steel bar sleeve; the reinforcing steel bar sleeve is provided with a grout outlet 11 and a grout inlet 12;

the intelligent detection method for the grouting compactness of the sleeve comprises the following steps:

s1, preparing steel bar sleeves, wherein the number of the steel bar sleeves is set to be A, and the grouting defect types and the grouting defect densities of the steel bar sleeves are known;

s2, performing the following steps on the steel bar sleeve in the S1:

s21, arranging a vibration sensor 3 at the grout inlet of the steel bar sleeve, wherein the vibration sensor is connected with a data acquisition device 4, and the data acquisition device can receive and store signals of the vibration sensor in real time;

s22, after the step s21 is completed, starting the data acquisition equipment, and enabling the slurry outlet of the steel bar sleeve to generate shock waves by using the shock excitation equipment 6; acquiring a vibration response signal of the steel bar sleeve through a vibration sensor; the excitation equipment can control the excitation waves output each time to be consistent;

s23, loading the vibration response signal collected in the step s22 into the computer 5;

s24, selecting a Sym8 wavelet function according to the waveform of the vibration response signal of the step s23, wherein the value of the level of the wavelet decomposition of the Sym8 wavelet function is set as N;

then, for the vibration response signal of step s23, N-layer orthogonal wavelet decomposition is carried out by using the selected wavelet function to obtain the signal component { cA +1 wavelet decomposition in 1 st-N layer_N，cD_N，cD_N-1......cD₄，cD₃，cD₂，cD₁In which A_NBeing a low frequency component, cD_NIs a high frequency component;

s25, comparing A obtained in step s24 respectively_N，D_N，D_N-1......D₄，D₃，D₂，D₁Performing box dimension calculation to obtain box dimension F_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁；

s26, calculation step s 25F_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁Then calculating the average value by subtracting F from the average value_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁The resulting absolute value;

s27, the box-to-box dimension F from large to small according to the absolute value obtained in step s26_AN、F_DN、F_N-1......F₄、F₃、F₂、F₁Rearranging to form fractal characteristic vector F_X＝{F₁，F₂，F₃，F₄......F_N-1、F_DN、F_AN}；

S3, obtaining a fractal feature vector F after the step S2 is finished_A、F_A-1、F_A-2......F₃、F₂、F₁(ii) a The obtained fractal feature vector F_A、F_A-1、F_A-2......F₃、F₂、F₁Guiding the grouting defect type and density of the steel bar sleeve corresponding to each fractal feature vector into a BP neural network in MATLAB software for training and learning, and storing;

s4, after the step S3 is completed, the steel bar sleeve to be detected is sleevedPerforming the operation of step S2 to obtain a fractal feature vector F_B(ii) a Then fractal feature vector F_BAnd (4) outputting the grouting defect type and density of the steel bar sleeve after intelligent analysis and judgment of the BP neural network as the input value of the BP neural network trained in the step S3.

First, the term explanation is made:

wavelet analysis: the method is a time-frequency analysis method of signals and has the characteristic of multi-resolution analysis. The method uses an oscillation waveform called mother wavelet with finite length or rapid attenuation to represent a signal, obtains the frequency characteristic of the signal by scaling the width of the mother wavelet, and obtains the time information of the signal by translating the mother wavelet, thereby having the capability of representing the local characteristic of the signal in both time and frequency domains. For transient shock vibration response type non-stationary random signals with a wide frequency band, the wavelet analysis technology can perform multi-resolution and saliency analysis on local non-stationary random signals, and can quickly and accurately detect defect abnormal signals contained in structural vibration response.

BP neural network: a multi-layer feedforward network trained according to an error inverse propagation algorithm is one of the most widely applied neural network models at present. It is possible to learn and store a large number of input-output pattern mappings without prior disclosure of mathematical equations describing such mappings.

Box dimension: the vibration wave signal s generated by the stimulated vibration of the steel bar sleeve belongs to F, wherein F is n-dimensional Euclidean space RⁿThe above closed set. R is to beⁿDivided into square squares of width delta as small as possible, if N_δThe number of grids covering the F set least in discrete space with grid width δ, and we define the box dimension of the vibration wave s as:

when the construction defects of the steel bar sleeve are detected, the influence of different grouting construction defects on vibration signals caused by the same excitation in the steel bar sleeve is different, the box dimension in a fractal theory is used as a dimensionless index for measuring the structural vibration characteristics, and the box dimension is widely applied to defect identification and anchor rod anchoring quality diagnosis of entities such as mechanical structures, pile foundations, beams, columns and the like. For the steel bar sleeve of the assembly type building, as the steel bar sleeve in the prefabricated part has the characteristics of consistent structure size, the same grouting material, the consistent steel bar model and approximate embedding mode, under the condition of good construction quality, the box dimension of each steel bar sleeve has small difference, and if the steel bar sleeve with grouting construction defects exists, the steel bar sleeve can be rapidly judged through the box dimension.

Considering that the construction defect of the steel bar sleeve and the box dimension of the vibration response curve of the steel bar sleeve are not in simple linear corresponding relation, the invention introduces a BP neural network algorithm to establish the nonlinear mapping relation between the construction defect of the sleeve and the box dimension. The neural network has the advantages of simple network structure, strong approaching and fault-tolerant capabilities and is the most applied neural network at present. The learning mode of the BP neural network is that a teacher learns, and a large number of reinforcing steel bar sleeve structures exist in the assembly type building engineering, so that massive training samples can be provided for learning of the BP neural network, and the defect recognition capability of the neural network is improved.

The invention decomposes the excitation feedback waveform of the steel bar sleeve by wavelet, then carries out box dimension analysis on the decomposed waveform by utilizing the fractal principle, extracts the fractal characteristic vector F for describing the defect characteristics_BFinally, fractal feature vector F_BAs an input value of the BP neural network, after intelligent analysis and judgment of the BP neural network, the grouting defect type and density information of the steel bar sleeve are output; the intelligent identification method is used for detecting the grouting compactness of the steel bar sleeve, so that the detection efficiency of detection personnel can be greatly improved, the detection cost is reduced, and the detection precision is improved.

Preferably, the Sym8 wavelet function in step s24 may be a Haar wavelet function, Daubechies wavelet function or Coiflet wavelet function, according to practical situations, considering that different wavelet functions may have certain influence on the waveform decomposition.

Preferably, after step S4, step S5 is provided: bisection of feature vector F by X-ray method_BAccurately judging the corresponding steel bar sleeve, and then carrying out fractal characteristic vector F_BAnd importing the defect type and the density information of the steel bar sleeve into a BP neural network in MATLAB software to continue training.

Preferably, to simplify the apparatus, the excitation apparatus is a hand hammer.

Preferably, in order to enable the vibration sensor to transmit the feedback excitation wave in the steel bar sleeve more accurately, in step s21, a coupling agent is coated on the contact surface of the vibration sensor and the grout inlet of the steel bar sleeve.

Preferably, in order to reduce the detection cost, the coupling agent is butter.

Preferably, in step S1, a value of a is equal to or greater than 100.

Preferably, in the step s24, the value of N is less than or equal to 7.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, so that any modification, equivalent change and modification made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.