Disclosure of Invention
The application aims to solve the technical problems that: the application provides a detection method for the wind resistance of a metal roof, which aims to solve the technical problem that the wind resistance of the metal roof cannot be detected in practice by the detection method for the wind resistance of the metal roof in the prior art.
The technical scheme adopted for solving the technical problems is as follows: a detection method for the wind resistance of a metal roof comprises the following steps:
step S1: the method comprises the steps of obtaining the number of bolts when a plurality of metal panels in a metal roof system are connected through bolts, wherein the number of the bolts is X1, and the number of the screws when the metal roof system is connected with a wall through screws, and the number of the screws is X5;
the pretightening force of each bolt is X2;
step S2: obtaining a windage coefficient X3 of the metal roof system through a wind tunnel experiment;
step S3: measuring the vibration frequency of the metal roof system based on image processing, and acquiring a sound pressure level value X4 of the metal roof system according to the vibration frequency;
step S4: taking the number X1 of the bolts, the pretightening force X2 of each bolt, the number X5 of the screws, the wind resistance coefficient X3 and the sound pressure level value X4 as data sets, and dividing the data sets into training sets and test sets;
step S5: establishing an SVM algorithm model, converting the data set into an input vector identified by the SVM algorithm model, giving the input vector and a target value to the SVM algorithm model, and training the SVM algorithm model to realize classification application of the wind-break resistance of the metal roof;
step S6: and inputting the number of the bolts, the pretightening force of the bolts, the number of the screws, the wind resistance coefficient and the sound pressure level value into a trained SVM algorithm model as characteristic values to obtain whether the tested metal roof system can successfully resist wind-break capability.
Further, specifically, the step S3 specifically includes the following steps:
step S31: the method comprises the steps of obtaining the vibration frequency F of a metal roof system, wherein the vibration frequency F of the metal roof system comprises the vibration frequency F1 of the whole structure of the metal roof, the vibration frequency F2 of the joint of the metal roof and the vibration frequency F3 of the edge of the metal roof, and the vibration frequency F= (F1, F2 and F3) of the metal roof system;
step S32: polynomial expansion is carried out on the vibration frequency F= (F1, F2, F3) of the metal roof system, and the vibration characteristic Z after expansion is obtained i ;
Step S33: constructing a random forest model;
step S34: and inputting the vibration frequency F of the metal roof system to the random forest model, and fitting the sound pressure level value.
Further, specifically, the step S31 specifically includes the steps of:
step S311: acquiring video streams when all parts of the metal roof system vibrate through image acquisition equipment, and obtaining multi-frame continuous images according to frame drawing of the video streams;
step S312: according to the image, obtaining time domain signals of vibration states of the metal panel at all time points, and carrying out Fourier transform on the time domain signals to obtain frequency spectrum signals;
step S313: performing peak detection on the frequency spectrum signal to obtain a frequency peak;
step S314: acquiring sampling time, wherein the ratio of the frequency peak value to the sampling time is vibration frequency;
wherein, the image comprises: and (3) respectively calculating the vibration frequency f1 of the whole structure of the metal roof, the vibration frequency f2 of the connecting part of the metal roof and the vibration frequency f3 of the edge of the metal roof through the step S311-the step S314.
Further, specifically, the step S33 includes the steps of:
s331: inputting a characteristic value, and carrying out standardization processing on the characteristic value, wherein the characteristic value is the vibration frequency F= (F1, F2, F3) and the vibration characteristic Z of the metal roof system;
s332: randomly selecting a feature, randomly selecting from the normalized feature values, and selecting the best feature from the feature values for splitting of the node;
s333: constructing a decision tree, and training the decision tree according to the randomly selected characteristics and the characteristic values;
s334: integrating decision trees, combining a plurality of decision trees into the random forest model, and averaging the prediction results of all the decision trees by adopting an averaging method;
s335: model evaluation, which is to perform mean square error evaluation calculation on a random forest model based on the calculated average value, wherein the calculation formula is as follows:
;
where n represents the number of samples,represents the firstiSound pressure level true value of sample, +.>Represents the firstiSound pressure level prediction value of the sample.
Further, specifically, the step S5 includes the steps of:
s51: carrying out standardization processing on the training set and the testing set;
s52: inputting the data of the training set to the SVM algorithm model, and training the SVM algorithm model by combining the target value;
s53: inputting the data of the test set to the trained SVM algorithm model, and evaluating;
s54: and (3) optimizing and adjusting parameters of the SVM algorithm according to the result evaluated in the step S53.
Further, specifically, training the random forest model ends when the mse value is less than 0.05.
A computer device, comprising: a processor; a memory for storing executable instructions; the processor is used for reading the executable instructions from the memory and executing the executable instructions to realize the detection method of the wind resistance of the metal roof.
A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to implement a method of detecting wind resistance of a metal roofing as described above.
The method for detecting the wind resistance of the metal roof has the beneficial effects that the characteristics of important influence on a metal roof system are subjected to function mapping through the SVM algorithm model, so that the wind resistance of the metal roof is actually detected, the measuring precision is high, the safety of the whole building is improved, and the detecting cost is reduced.
Detailed Description
The application will now be described in further detail with reference to the accompanying drawings. The drawings are simplified schematic representations which merely illustrate the basic structure of the application and therefore show only the structures which are relevant to the application.
Example 1: as shown in fig. 1, the embodiment of the application provides a method for detecting the wind resistance of a metal roof, which comprises the following steps:
step S1: acquiring the number of bolts in the metal roof system when a plurality of metal panels are connected through bolts, wherein the number of the bolts is X1, and the number of the screws in the metal roof system and the wall are connected through screws, and the number of the screws is X5; wherein the pretightening force of each bolt is X2.
Because the structure body of the metal roofing system is large, the whole structure of the metal roofing system is difficult to process at one time, and in general, a plurality of metal panels are connected through bolts to form the metal roofing system, so that a plurality of bolts are needed to be connected to form the metal roofing system, the number of the bolts has a larger influence on the structural strength of the metal roofing, and then the wind-stopping capacity of the whole metal roofing system can be influenced. If the number of the bolts is small, the load borne by each bolt can be increased, and the probability that the bolts are pulled out when the metal roof system bears strong wind load is increased; if the number of the bolts is large, the elastic vibration space of the metal roof system is reduced, the overall bearing capacity is reduced, and the influence value of the pretightening force of each bolt on the final wind resistance is large. In addition, the metal roofing system and the wall body are generally connected by adopting screws, and the larger the number of the screws is according to the standard interval, the higher the connection strength between the metal roofing system and the wall body is, but the upper limit of the number of the screws is limited by a place. Therefore, the number of bolts and the pretightening force of the bolts and the number of screws are obtained and used as important characteristic values.
Step S2: and obtaining the wind resistance coefficient X3 of the metal roof system through a wind tunnel experiment.
The wind-stopping capacity of the metal roof structure is greatly partially related to the wind resistance coefficient of the metal roof structure, and the bearing condition of the whole structure can be greatly optimized under the strong wind load due to the lower wind resistance coefficient. And the large wind resistance can lead the metal roof to bear more load and have larger probability of being stopped by wind under the same wind power, and the wind resistance coefficient X3 of the metal roof system is obtained through a wind tunnel experiment and is taken as an important characteristic value.
It should be noted that, in this embodiment, the wind tunnel experiment is one of the common methods for obtaining the wind resistance coefficient of the metal roofing system, and in this embodiment, the wind resistance coefficient X3 of the metal roofing system is finally obtained through the steps of designing a wind tunnel experiment scheme, making a metal roofing structure sample, building a wind tunnel experiment facility, setting experiment parameters, wind tunnel experiment and the like, where the above steps are all in the prior art and are not described in detail herein.
Step S3: and measuring the vibration frequency of the metal roofing system based on image processing, and acquiring the sound pressure level value X4 of the metal roofing system according to the vibration frequency.
The sound pressure level value X4 of the metal roof system has a larger influence on the wind resistance of the whole metal roof system, but the direct measurement of the sound pressure level value of the metal roof overall structure, the sound pressure level value of the metal roof self-connection part and the sound pressure level value of the metal roof edge is extremely difficult, the measurement steps are complicated, and the subsequent rapid and economical detection of the wind resistance of the metal roof system is unfavorable. The method has the advantages that the sound pressure level value emitted when the metal roofing system vibrates is fitted based on the image processing measurement of the vibration frequency of the metal roofing system, the steps are simple, the follow-up rapid and economical detection of the wind-stop resistance of the metal roofing system is facilitated, the detection precision is further improved, and the detection efficiency can be improved.
In this embodiment, as shown in fig. 2, step S3 specifically includes the following steps:
step S31: the method comprises the steps of obtaining the vibration frequency F of a metal roof system, wherein the vibration frequency F of the metal roof system comprises the vibration frequency F1 of the whole structure of the metal roof, the vibration frequency F2 of the joint of the metal roof and the edge vibration frequency F3 of the metal roof, and the vibration frequency F= (F1, F2 and F3) of the metal roof system.
Further, the step S31 specifically includes the following steps:
step S311: the video stream when each part of the metal roof system vibrates is obtained through the image acquisition equipment, the video stream is imaged according to frames to obtain multi-frame continuous images, the image acquisition equipment is a high-speed camera, the acquired images are clear, the detection of the wind resistance of the metal roof is facilitated, and the measurement accuracy is improved.
Step S312: according to the image, obtaining time domain signals of vibration states of the metal panel at all time points, and carrying out Fourier transformation on the time domain signals to obtain frequency spectrum signals. Further, the fourier transform formula is:
wherein X (k) represents the amplitude of the spectral signal k,x(n) A vibration signal representing time n in the time domain,erepresents a natural constant of the natural product,jrepresenting imaginary units and N representing signal length.
Step S313: and carrying out peak detection on the frequency spectrum signal to obtain a frequency peak value.
Step S314: acquiring sampling time, wherein the ratio of a frequency peak value to the sampling time is the vibration frequency; the sampling time is the time interval of image acquisition.
Wherein, the image comprises: and (3) respectively calculating the vibration frequency f1 of the whole metal roof structure, the vibration frequency f2 of the joint of the metal roof and the edge vibration frequency f3 of the metal roof through steps S311-S314. The image acquisition device acquires the vibration image of each part under the condition of not contacting the metal roof system, so that the interference or influence caused by physical contact is avoided, meanwhile, the small change of the vibration of the metal panel can be captured, the image data with high time resolution is provided, the vibration mode and the frequency can be accurately analyzed through the steps S311-314, and the measurement precision of the detection method of the wind resistance of the metal roof is further improved.
Step S32: and (3) performing polynomial expansion on the vibration frequency F= (F1, F2, F3) of the metal roof system to obtain an expanded vibration characteristic Z.
Further, although the higher the vibration frequency of the metal roofing system is, the higher the pressure level of the generated noise is, but the vibration frequency and the pressure level of the noise are not in a linear relationship, in this embodiment, the vibration frequency F of the metal roofing system is expanded by adopting a nonlinear fitting expansion formula: z is Z i =f(fj),i=1, 2,3,4,5,6, j=1, 2,3, substituting the vibration frequency f= (F1, F2, F3) of the metal roofing system into the expansion formula to perform polynomial expansion, to obtain:
Z 1 =f1*f2
Z 2 =f1*f3
Z 3 =f2*f3;
Z 4 =f1 2
Z 5 =f2 2
Z 6 =f3 2
extended vibration signature z= (Z) 1 ,Z 2 ,Z 3 ,Z 4 ,Z 5 ,Z 6 )。
Step S33: vibration frequency f= (F1, F2, F3) and vibration characteristic Z based on metal roofing system i And constructing a random forest model, and obtaining the sound pressure extremum of the metal roof system.
Further, step S33 includes the steps of:
s331: inputting and normalizing characteristic values, wherein the characteristic values are the vibration frequency F= (F1, F2, F3) and the vibration characteristic Z of the metal roof system i ;
Feature value normalization refers to scaling the values of feature vectors to a specified range to facilitate model training and optimization. In this embodiment, the larger difference of the amplitudes of different vibration frequencies, that is, the scales of the eigenvalues, after the polynomial expansion, can affect the performance of the random forest model, the larger-scale features have larger influence on the model, and the other features have smaller influence on the model. Therefore, through eigenvalue standardization, the values of all eigenvectors can be mapped into the same range, and the difference between eigenvalues is eliminated, so that all the eigenvalues have equal contribution to the random forest model:
wherein m is a normalized characteristic value, and n is the vibration frequency F= (F1, F2, F3) and the vibration characteristic Z of the metal roof system i ,For mean value->Is the standard deviation.
S332: the features are randomly selected, and for each node of each decision tree, feature selection is required at the node, a part of features (such as a part of the total feature number) is randomly selected from the feature values of the normalization processing in step S321, and the best one is selected from the selected features for splitting of the node, so that the information entropy difference after splitting is maximized.
S333: and constructing a decision tree, and training the decision tree according to the randomly selected characteristics and the sample data. Specifically, a decision tree with depth is generated by recursive segmentation of the sample data. The steps are then repeated, randomly selecting a number of samples from the dataset (with the samples put back) for training each decision tree and training the decision tree using the randomly selected features and the sample data, in other words, by recursive segmentation of the sample data, a decision tree with depth is generated. The sample data are the vibration frequency f= (F1, F2, F3) and the vibration characteristic Z of the metal roofing system i 。
S334: integrating decision trees, combining a plurality of decision trees into a random forest model, and averaging the prediction results of all the decision trees by adopting an averaging method.
S335: model evaluation, which is to perform mean square error evaluation calculation on a random forest model based on the calculated average value, wherein the calculation formula is as follows:
where n represents the number of samples,represents the firstiSound pressure level true value of sample, +.>Represents the firstiSound pressure level prediction value of the sample. The sound pressure level real value is obtained by acquiring a metal roof system on site for training a random forest model, the sound pressure level predicted value is obtained by constructing the random forest model and predicting, whether the random forest model is continuously trained is determined by comparing the sound pressure level real value with the random forest model, so that the accuracy of the sound pressure level predicted value in the random forest model is improved, and the detection accuracy of the resistance of the metal roof system to wind is further improved.
In this embodiment, when the mse value (mean square error) is smaller than 0.05, the training is finished, the training result is good, and the detection accuracy of the wind-break resistance of the metal roofing system is high.
Step S34: and (3) inputting the vibration frequency of the metal roof system into a random forest model, fitting out a sound pressure level value, and when the sound pressure extremum is too large, the possibility that the metal roof system is damaged is also larger.
Step S4: taking the number X1 of bolts, the pretightening force X2 of each bolt, the number X5 of screws, the wind resistance coefficient X3 and the sound pressure level value X4 as data sets, and dividing the data sets into training sets and test sets; the training set is used to train the model and the test set is used to evaluate the performance of the model. In this embodiment, the data amount of the 50% data set is used as the training set, the data amount of the 50% data set is used as the test set, and the data amount of the test set is ensured by the data amount of the 50% data set, so that the accuracy of the test result is ensured.
Step S5: an SVM algorithm model is established, a data set is converted into an input vector recognized by the SVM algorithm model, the input vector and a target value are given to the SVM algorithm model, the SVM algorithm model is trained, and classification application of the wind-break resistance of the metal roof is realized;
further, the step S5 specifically includes the following steps:
s51: the data set is normalized. And (3) carrying out eigenvalue standardization on the data of the training set and the testing set in the step (S4) to ensure that the mean value is 0 and the variance is 1 so as to eliminate the influence of the dimension difference between the data of the training set and the testing set on the model and improve the measurement precision of the detection method. Step S51 is different from step S311 only in the processed data set, but the processing procedure of the step is the same, and will not be described here.
S52: and inputting the data of the training set into the SVM algorithm model, and training the SVM algorithm model by combining the target value.
S53: and inputting the data of the test set into the trained SVM algorithm model, and evaluating.
Specifically, a test set is used for evaluating a trained SVM algorithm model, wherein a metal roof is marked as 1 by wind rest, and the classification performance of the model is evaluated through a recall index re:
where TP is a true case and FN is a false negative case. The real example refers to the actual metal roofing system being left off by wind and predicted to be left off. A false negative example refers to a case where a sample belonging to a positive class is erroneously predicted as a negative class. re is the recall rate, and the situation that an actual metal roof system is stopped by wind and cannot be recalled is prevented.
S54: and (3) according to the result evaluated in the step S53, optimizing and adjusting parameters of the SVM algorithm, such as weighting optimization, so as to improve the classification performance of the model. The classification result of the adjusted model comprises: completely anti-wind rest stable, anti-wind rest semi-stable and anti-wind rest unstable.
Step S6: and (3) inputting the number of bolts, the pretightening force of the bolts, the number of screws, the wind resistance coefficient and the sound pressure level value which are acquired in real time into a trained SVM algorithm model as characteristic values to obtain whether the tested metal roof system can successfully resist wind-break capability.
According to the detection method for the wind resistance of the metal roof, provided by the application, the characteristics of important influence on a metal roof system are subjected to function mapping through the SVM algorithm model, so that the wind resistance of the metal roof is actually detected, the measurement accuracy is high, the safety of the whole building is improved, and the detection cost is reduced.
Example 2: the embodiment of the application provides computer equipment, which comprises a processor and a memory, wherein at least one instruction or at least one section of program is stored in the memory, and the at least one instruction or the at least one section of program is loaded and executed by the processor so as to realize the method for detecting the wind resistance of the metal roof.
Fig. 3 shows a schematic hardware structure of a device for implementing the method for detecting wind resistance of a metal roof according to the embodiment of the present application, where the device may participate in forming or including an apparatus or a system according to the embodiment of the present application. As shown in fig. 3, the computer device 10 may include one or more processors 1002 (the processors may include, but are not limited to, processing means such as a microprocessor MCU or a programmable logic device FPGA), memory 1004 for storing data, and transmission means 1006 for communication functions. In addition, the method may further include: display devices, input/output interfaces (I/O interfaces), universal Serial Bus (USB) ports (which may be included as one of the ports of the I/O interfaces), network interfaces, power supplies, and/or cameras. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 3 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, computer device 10 may also include more or fewer components than shown in FIG. 3, or have a different configuration than shown in FIG. 3.
It should be noted that the one or more processors and/or other data processing circuits described above may be referred to herein generally as "data processing circuits. The data processing circuit may be embodied in whole or in part in software, hardware, firmware, or any other combination. Furthermore, the data processing circuitry may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the computer device 10 (or mobile device). As referred to in embodiments of the application, the data processing circuit acts as a processor control (e.g., selection of the path of the variable resistor termination connected to the interface).
The memory 1004 may be used to store software programs and modules of application software, such as a program instruction/data storage device corresponding to a method for detecting wind resistance of a metal roof in an embodiment of the present application, and the processor executes the software programs and modules stored in the memory 1004 to perform various functional applications and data processing, that is, implement a method as described above. Memory 1004 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 1004 may further include memory located remotely from the processor, which may be connected to computer device 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 1006 is for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communications provider of the computer device 10. In one example, the transmission means 1006 includes a network adapter (NetworkInterfaceController, NIC) that can be connected to other network devices via a base station to communicate with the internet. In one example, the transmission means 1006 may be a radio frequency (RadioFrequency, RF) module for communicating wirelessly with the internet.
The display device may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with a user interface of the computer device 10 (or mobile device).
Embodiment 3. The embodiment of the present application further provides a computer readable storage medium, where the computer readable storage medium may be configured in a server to store at least one instruction or at least one program related to a method for implementing a method for detecting wind resistance of a metal roof in a method embodiment, where the at least one instruction or the at least one program is loaded and executed by the processor to implement a method for detecting wind resistance of a metal roof provided in the foregoing method embodiment.
Alternatively, in this embodiment, the storage medium may be located in at least one network server among a plurality of network servers of the computer network. Alternatively, in the present embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Example 4: embodiments of the present application also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs a method for detecting the wind resistance of the metal roof provided in the above various alternative embodiments.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for apparatus, devices and storage medium embodiments, the description is relatively simple as it is substantially similar to method embodiments, with reference to the description of method embodiments in part.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
With the above-described preferred embodiments according to the present application as an illustration, the above-described descriptions can be used by persons skilled in the relevant art to make various changes and modifications without departing from the scope of the technical idea of the present application. The technical scope of the present application is not limited to the description, but must be determined according to the scope of claims.