Method and device for predicting residual life of steel template

Abstract

The invention relates to the technical field of steel formwork detection, in particular to a method and device for predicting the remaining life of a steel formwork. The method comprises the following steps: acquiring image data of a steel template, dividing the image data of the steel template to obtain sub-image data of a plurality of steel templates, acquiring steel template mechanical data corresponding to the sub-image data of each steel template, performing feature extraction on the sub-image data of the plurality of steel templates to obtain a plurality of surface feature data, and calculating the surface feature data of the plurality of steel templates according to the surface feature data. Performing feature extraction on the mechanical data to obtain multiple pieces of mechanical feature data; carrying out feature fusion on each piece of surface feature data and the corresponding mechanical feature data to obtain a plurality of sub-fusion features, carrying out feature fusion on each sub-fusion feature according to an application influence factor to obtain a fusion feature matrix, and inputting the fusion feature matrix into a preset steel template residual life prediction model to obtain a prediction result of the residual life of the steel template. And obtaining the residual life of the steel template. By means of the configuration mode, the residual life of the steel formwork can be accurately predicted.

Description

Technical Field

[0001] The present invention relates to the technical field of steel formwork detection, and particularly to a method and device for predicting the remaining life of steel formwork. Background Art

[0002] Steel formwork is a steel formwork used for concrete pouring and molding, and is widely used in many engineering fields such as construction, bridges, and tunnels. Its quality and performance directly affect the appearance quality, dimensional accuracy, and durability of concrete structures. Since steel formwork is used in large quantities and has a high cost in engineering construction, and its damage or failure may lead to consequences such as engineering quality problems, project delays, and increased costs. Therefore, accurately predicting the remaining life of steel formwork is of great significance for reasonably arranging maintenance, timely replacing formwork, and ensuring project safety and benefits.

[0003] Based on this, the present invention proposes a method and device for predicting the remaining life of steel formwork to solve the above technical problems. Summary of the Invention

[0004] The present invention describes a method and device for predicting the remaining life of steel formwork, which can accurately predict the remaining life of steel formwork.

[0005] According to a first aspect, the present invention provides a method for predicting the remaining life of steel formwork, the method comprising:

[0006] Obtaining image data of the steel formwork;

[0007] Dividing the image data of the steel formwork to obtain multiple sub-image data of the steel formwork, and obtaining steel formwork mechanical data corresponding to each sub-image data of the steel formwork, wherein the mechanical data includes tensile strength and yield strength;

[0008] Performing feature extraction on multiple sub-image data of the steel formwork respectively to obtain multiple surface feature data, and performing feature extraction on the mechanical data to obtain multiple mechanical feature data;

[0009] Performing feature fusion on each surface feature data and the corresponding mechanical feature data to obtain multiple sub-fusion features;

[0010] Performing feature fusion on each sub-fusion feature according to an application influence factor to obtain a fusion feature matrix; wherein the application influence factor is determined according to the relative position of the sub-image data in the image data of the steel formwork;

[0011] Inputting the fusion feature matrix into a preset steel formwork remaining life prediction model to obtain the remaining life of the steel formwork.

[0012] According to a second aspect, the present invention provides a device for predicting the remaining life of a steel formwork, comprising:

[0013] An acquisition unit configured to acquire image data of the steel formwork;

[0014] A first data processing unit configured to divide the image data of the steel formwork to obtain sub-image data of a plurality of steel formworks, and acquire mechanical data of the steel formwork corresponding to each sub-image data of the steel formwork, wherein the mechanical data includes tensile strength and yield strength;

[0015] A second data processing unit configured to respectively perform feature extraction on the sub-image data of a plurality of steel formworks to obtain a plurality of surface feature data, and perform feature extraction on the mechanical data to obtain a plurality of mechanical feature data;

[0016] A third data processing unit configured to perform feature fusion on each of the surface feature data and the corresponding mechanical feature data to obtain a plurality of sub-fusion features;

[0017] A fourth data processing unit configured to perform feature fusion on each sub-fusion feature according to an application influence factor to obtain a fusion feature matrix; wherein the application influence factor is determined according to the relative position of the sub-image data in the image data of the steel formwork;

[0018] A fifth data processing unit configured to input the fusion feature matrix into a preset prediction model for the remaining life of the steel formwork to obtain the remaining life of the steel formwork.

[0019] In a third aspect, an embodiment of the present specification further provides an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the method described in any embodiment of the present specification is implemented.

[0020] In a fourth aspect, an embodiment of the present specification further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed on a computer, the computer is made to execute the method described in any embodiment of the present specification.

[0021] According to the prediction method and device for the remaining life of steel formwork provided by the present invention, first, image data is collected by using a camera device to obtain the image data of the steel formwork. The image segmentation technology is used to process this data and divide it into multiple sub-image data of the steel formwork. At the same time, for each sub-image data, the mechanical property data of the corresponding steel formwork is synchronously collected, including the tensile strength reflecting the ability of the material to resist tensile failure and the yield strength indicating the start of obvious plastic deformation of the material. Subsequently, feature extraction is performed on each sub-image data of the steel formwork. Multiple surface feature data are mined from the sub-images. These surface feature data can accurately quantify the corrosion condition, wear degree, and crack distribution characteristics on the surface of the steel formwork. As key visual feature indicators, they are directly related to the remaining life of the steel formwork. Feature extraction is performed on the mechanical data to obtain multiple mechanical feature data, which can reflect the internal mechanical response mechanism of the steel formwork under stress. To comprehensively consider the combined influence of surface features and mechanical features on the remaining life of the steel formwork, the present invention uses a feature fusion algorithm to fuse each surface feature data with the corresponding mechanical feature data to generate multiple sub-fusion feature vectors. Since in the actual engineering application of the steel formwork, the external load actions on different parts have significant spatial differences, the present invention introduces the concept of an application influence factor. This factor can be custom-set according to the relative position of the sub-image data in the overall image data of the steel formwork to reflect the influence weight of different positions on the remaining life of the steel formwork. Based on this, a weighted fusion strategy is used to perform secondary fusion on each sub-fusion feature vector according to the application influence factor, and finally a fusion feature matrix is constructed. Finally, the fusion feature matrix is input into a pre-trained and optimized prediction model for the remaining life of the steel formwork to obtain the remaining life of the steel formwork. Through the above configuration method, the present invention can accurately predict the remaining life of the steel formwork. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 The flowchart showing the prediction method for the remaining life of steel formwork according to one embodiment is shown;

[0024] Figure 2 The schematic block diagram showing the prediction device for the remaining life of steel formwork according to one embodiment is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] The solution provided by the present invention will be described below in conjunction with the accompanying drawings.

[0026] Figure 1 A schematic flowchart of a method for predicting the remaining life of a steel formwork according to an embodiment is shown. It can be understood that this method can be executed by any device, equipment, platform, or equipment cluster with computing and processing capabilities. As Figure 1 shown, the method includes:

[0027] Step 100: Obtain the image data of the steel formwork;

[0028] Step 102: Divide the image data of the steel formwork to obtain sub-image data of multiple steel formworks, and obtain the mechanical data of the steel formwork corresponding to each sub-image data of the steel formwork, where the mechanical data includes the tensile strength and the yield strength;

[0029] Step 104: Extract features from the sub-image data of multiple steel formworks respectively to obtain multiple surface feature data, and extract features from the mechanical data to obtain multiple mechanical feature data;

[0030] Step 106: Perform feature fusion on each surface feature data and the corresponding mechanical feature data to obtain multiple sub-fusion features;

[0031] Step 108: Perform feature fusion on each sub-fusion feature according to the application influence factor to obtain a fusion feature matrix; wherein, the application influence factor is determined according to the relative position of the sub-image data in the image data of the steel formwork;

[0032] Step 110: Input the fusion feature matrix into a preset steel formwork remaining life prediction model to obtain the remaining life of the steel formwork.

[0033] In this embodiment, first, an imaging device is used to collect image data and obtain the image data of the steel formwork. The data is processed using image segmentation technology and divided into multiple sub-image data of the steel formwork. At the same time, for each sub-image data, the corresponding mechanical property data of the steel formwork is collected synchronously, including the tensile strength reflecting the material's ability to resist tensile failure and the yield strength indicating the start of obvious plastic deformation of the material. Subsequently, feature extraction is performed on each sub-image data of the steel formwork. Multiple surface feature data are mined from the sub-images. These surface feature data can accurately quantify the corrosion condition, wear degree, and crack distribution characteristics on the surface of the steel formwork. As key visual feature indicators, they have a direct relationship with the remaining life of the steel formwork. Feature extraction is performed on the mechanical data to obtain multiple mechanical feature data, which can reflect the internal mechanical response mechanism of the steel formwork under stress. To comprehensively consider the combined influence of surface features and mechanical features on the remaining life of the steel formwork, the present invention uses a feature fusion algorithm to fuse each surface feature data with the corresponding mechanical feature data to generate multiple sub-fusion feature vectors. Since in the actual engineering application of the steel formwork, the external load acting on different parts has significant spatial differences, the present invention introduces the concept of an application influence factor. This factor can be custom-set according to the relative position of the sub-image data in the overall image data of the steel formwork to reflect the influence weight of different positions on the remaining life of the steel formwork. Based on this, a weighted fusion strategy is used to perform a secondary fusion on each sub-fusion feature vector according to the application influence factor, and finally a fusion feature matrix is constructed. Finally, the fusion feature matrix is input into a pre-trained and optimized prediction model for the remaining life of the steel formwork to obtain the remaining life of the steel formwork. Through the above configuration method, the present invention can accurately predict the remaining life of the steel formwork.

[0034] In an embodiment of the present invention, after inputting the fusion feature matrix into a preset prediction model for the remaining life of the steel formwork to obtain the remaining life of the steel formwork, it further includes:

[0035] When the delay condition for the remaining life of the steel formwork is not met, a correction factor for the remaining life is obtained; wherein, the delay constraint for the remaining life of the steel formwork is constructed based on the historical remaining life of the steel formwork and the remaining life of the steel formwork, and the correction factor for the remaining life is determined based on the actual usage environment data of the steel formwork;

[0036] Based on the correction factor for the remaining life and the remaining life of the steel formwork, the final remaining life of the steel formwork is determined.

[0037] In this embodiment, when the delay condition for the remaining life of the steel formwork is not met, it indicates that there is an error in the predicted remaining life of the steel formwork. To improve the accuracy of the prediction of the remaining life of the steel formwork, the prediction result needs to be corrected. Specifically, the predicted remaining life of the steel formwork is multiplied by the correction factor of the remaining life to determine the final remaining life of the steel formwork. The delay constraint condition for the remaining life of the steel formwork is constructed based on the historical remaining life of the steel formwork and the currently predicted remaining life of the steel formwork. By analyzing the relationship between the historical data and the current predicted value, a reasonable delay constraint is set to evaluate the reliability of the prediction result. If the delay condition is not met, it means that the prediction result may deviate from the actual situation. The correction factor of the remaining life is determined according to the actual usage environment data of the steel formwork.

[0038] In one embodiment of the present invention, the delay condition for the remaining life of the steel formwork is constructed by the following formula:

[0039]

[0040] In the formula, P RL is the remaining life of the steel formwork, C RL is the historical remaining life of the steel formwork, t 1 is the time point of the prediction of the remaining life of the steel formwork, t 2 is the time point of the prediction of the historical remaining life of the steel formwork, T is the time interval between two predictions, and K is an adjustment coefficient.

[0041] In this embodiment, the above formula can accurately reflect the relationship between the remaining life of the steel formwork and the historical remaining life of the steel formwork. K is an adjustment coefficient related to the usage environment and material factors of the steel formwork. Those skilled in the art can customize the adjustment coefficient according to the actual usage situation.

[0042] In one embodiment of the present invention, the actual usage environment data includes a temperature influence factor, a humidity influence factor, a chemical substance influence factor, a load influence factor, and a wear influence factor.

[0043] In one embodiment of the present invention, the correction factor of the remaining life is determined by the following formula:

[0044]

[0045] In the formula, Y S is the correction factor of the remaining life, S 0 is the initial structural strength of the steel formwork, Q is the temperature influence factor, H is the humidity influence factor, C is the chemical substance influence factor, F is the load influence factor, W is the wear factor, a 1 is the weight of the correction factor of the remaining life, a 2 is the weight coefficient of the humidity influence factor, a3 is the weight coefficient of the chemical substance influence factor, a 4 is the weight coefficient of the load influence factor, a 5 is the weight coefficient of the wear factor, λ is the dynamic adjustment parameter, I i is the secondary influence factor, n is the number of secondary influence factors.

[0046] In this embodiment, the secondary influencing factors may include ultraviolet radiation and microbial corrosion. The temperature influence factor is equal to the difference obtained by subtracting the reference temperature from the average temperature of the environment where the steel formwork is located, and then dividing this difference by the reference temperature. This temperature influence factor is used to measure the impact of the deviation of the environmental temperature from the reference temperature on the remaining life of the steel formwork. When the average temperature is higher than the reference temperature, the temperature influence factor is positive, indicating that high temperature accelerates the loss of the steel formwork and shortens the remaining life; if the average temperature is lower than the reference temperature, the temperature influence factor is negative, meaning that the low-temperature environment slows down the loss rate of the steel formwork, but also brings other potential problems affecting its life such as embrittlement of the steel. The load influence factor is obtained by dividing the actual load borne by the steel formwork by its design load. This factor is used to measure the degree of influence of the actual load borne by the steel formwork relative to the design load on its remaining life. If the load influence factor is greater than 1, it indicates that the actual load borne exceeds the design load, which will increase the risk of fatigue damage and deformation of the steel formwork, and thus significantly shorten its remaining life; if the load influence factor is less than 1, it means that the actual load borne is less than the design load, and the steel formwork is in a relatively safe working state, and its remaining life is relatively longer. The humidity influence factor is equal to the difference obtained by subtracting the reference relative humidity from the environmental relative humidity, and then dividing this difference by the reference relative humidity. This humidity influence factor is used to measure the impact of the deviation of the environmental relative humidity from the reference relative humidity on the remaining life of the steel formwork. If the environmental relative humidity is greater than the reference relative humidity, the humidity influence factor is positive, indicating that higher humidity will accelerate the corrosion rate of the steel formwork, thereby shortening its remaining life; if the environmental relative humidity is less than the reference relative humidity, the humidity influence factor is negative, meaning that lower humidity will slow down the corrosion rate of the steel formwork, which has a certain positive impact on its remaining life. The chemical substance influence factor is an index that measures the comprehensive influence degree of various chemical substances in the environment on the corrosion of the steel formwork. It is obtained by considering each chemical substance in the environment that has a corrosive effect on the steel formwork, multiplying the concentration of each chemical substance by the corresponding corrosion coefficient of the substance, and then adding up all these products. Among them, the corrosion coefficient reflects the influence size of the chemical substance with a unit concentration on the corrosion of the steel formwork, and can be determined through experiments. The larger the value of this factor, the more serious the corrosion influence of the chemical substance on the steel formwork, and the shorter the remaining life of the steel formwork. The wear influence factor is an index used to measure the degree of influence of the surface wear of the steel formwork on its remaining life. When only considering the wear amount, it is obtained by dividing the wear amount of the steel formwork by its initial thickness. The wear amount is the difference between the initial thickness and the current thickness of the steel formwork. The larger the value of this factor, the higher the wear degree of the steel formwork, and the lower its remaining life.

[0047] In an embodiment of the present invention, after obtaining the image data of the steel formwork, it further includes:

[0048] Crop the image data of the steel formwork to obtain the image data of the steel formwork with the background removed;

[0049] Perform gray normalization processing and image binarization processing on the image data of the steel formwork with the background removed to obtain preprocessed data;

[0050] Divide according to the preprocessed data to obtain sub-image data of multiple steel formworks.

[0051] In this embodiment, first, an image cropping algorithm is used to process the original steel formwork image data. With the help of object detection and positioning technology, the spatial position of the steel formwork in the image is accurately identified, and then the image is cropped to effectively remove the background information, thereby obtaining image data containing only the main body of the steel formwork. This operation can eliminate the interference of background noise on subsequent analysis and make the subsequent processing process focus on the key features of the steel formwork. Next, perform gray normalization on the image data of the steel formwork after removing the background. By statistically analyzing the gray distribution characteristics of the image and using linear transformation or non-linear transformation methods, the gray values of the image are mapped to a unified numerical interval, usually [0,1] or [0,255]. Gray normalization can effectively eliminate the gray differences in the image caused by factors such as lighting conditions and shooting equipment, ensure the comparability of gray levels between different images, and provide a stable data basis for subsequent feature extraction and analysis. Subsequently, perform binarization processing on the image after gray normalization. Based on the gray histogram of the image or an adaptive threshold algorithm, a suitable threshold is determined, and the pixel points in the image are divided into two categories according to the relationship between their gray values and the threshold, represented by 0 and 1 (or 0 and 255) respectively. Image binarization can highlight the key features of the steel formwork, such as surface cracks and corrosion areas, and convert the complex gray image into a simple binary image, which is convenient for subsequent feature extraction and analysis. Finally, perform image segmentation based on the preprocessed data to divide the steel formwork image into multiple sub-image data. An image segmentation algorithm based on region, edge or clustering is used to segment the image into multiple sub-regions with certain semantic information according to the structural characteristics, texture information or color distribution of the steel formwork. These sub-image data can more detailedly display the characteristics of different parts of the steel formwork, provide rich and accurate information for the subsequent input of the steel formwork remaining life prediction model, and thus effectively improve the detection accuracy and generalization ability of the model.

[0052] In an embodiment of the present invention, the preset steel formwork remaining life prediction model is a convolutional neural network model.

[0053] In this embodiment, in the task of predicting the remaining life of the steel formwork, it is preset to adopt a Convolutional Neural Network (CNN) model. The CNN model has powerful feature extraction and pattern recognition capabilities, especially suitable for processing image data, and can automatically learn deep and abstract features from the input images, thus providing strong support for accurately predicting the remaining life of the steel formwork.

[0054] The specific embodiments of the present invention have been described above. Other embodiments are within the scope of the appended 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 the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0055] According to an embodiment of another aspect, the present invention provides a prediction device for the remaining life of a steel formwork. Figure 2 A schematic block diagram showing a prediction device for the remaining life of a steel formwork according to an embodiment is shown. It can be understood that the device can be implemented by any device, equipment, platform, and cluster of devices with computing and processing capabilities. As Figure 2 shown, the device includes: an acquisition unit 200, a first data processing unit 202, a second data processing unit 204, a third data processing unit 206, a fourth data processing unit 208, and a fifth data processing unit 210. The main functions of each component unit are as follows:

[0056] The acquisition unit is configured to acquire image data of the steel formwork;

[0057] The first data processing unit is configured to divide the image data of the steel formwork to obtain sub-image data of multiple steel formworks, and acquire mechanical data of the steel formwork corresponding to each sub-image data of the steel formwork, where the mechanical data includes tensile strength and yield strength;

[0058] The second data processing unit is configured to respectively extract features from the sub-image data of multiple steel formworks to obtain multiple surface feature data, and extract features from the mechanical data to obtain multiple mechanical feature data;

[0059] The third data processing unit is configured to perform feature fusion on each surface feature data and the corresponding mechanical feature data to obtain multiple sub-fusion features;

[0060] A fourth data processing unit, configured to perform feature fusion on each sub-fusion feature according to an application influence factor to obtain a fusion feature matrix; wherein, the application influence factor is determined according to the relative position of the sub-image data in the image data of the steel formwork;

[0061] A fifth data processing unit, configured to input the fusion feature matrix into a preset steel formwork remaining life prediction model to obtain the remaining life of the steel formwork.

[0062] In an embodiment of the present invention, after inputting the fusion feature matrix into a preset steel formwork remaining life prediction model to obtain the remaining life of the steel formwork, it further includes:

[0063] When the delay condition of the remaining life of the steel formwork is not satisfied, obtain a correction factor for the remaining life; wherein, the delay constraint of the remaining life of the steel formwork is constructed by the historical remaining life of the steel formwork and the remaining life of the steel formwork, and the correction factor for the remaining life is determined by the actual use environment data of the steel formwork;

[0064] Determine the final remaining life of the steel formwork according to the correction factor for the remaining life and the remaining life of the steel formwork.

[0065] In an embodiment of the present invention, the delay condition of the remaining life of the steel formwork is constructed by the following formula:

[0066]

[0067] In the formula, P RL is the remaining life of the steel formwork, C RL is the historical remaining life of the steel formwork, t 1 is the time point for predicting the remaining life of the steel formwork, t 2 is the time point for predicting the historical remaining life of the steel formwork, T is the time interval between two predictions, and K is an adjustment coefficient.

[0068] In an embodiment of the present invention, the actual use environment data includes a temperature influence factor, a humidity influence factor, a chemical substance influence factor, a load influence factor, and a wear influence factor.

[0069] In an embodiment of the present invention, the correction factor for the remaining life is determined by the following formula:

[0070]

[0071] In the formula, Y S is the correction factor for the remaining life, S 0is the initial structural strength of the steel formwork, Q is the temperature influence factor, H is the humidity influence factor, C is the chemical substance influence factor, F is the load influence factor, W is the wear influence factor, a 1 is the weight of the correction factor for the remaining life, a 2 is the weight coefficient of the humidity influence factor, a 3 is the weight coefficient of the chemical substance influence factor, a 4 is the weight coefficient of the load influence factor, a 5 is the weight coefficient of the wear influence factor, λ is the dynamic adjustment parameter, I i is the secondary influence factor, and n is the number of secondary influence factors.

[0072] In an embodiment of the present invention, after obtaining the image data of the steel formwork, it further includes:

[0073] Cropping the image data of the steel formwork to obtain the image data of the steel formwork with the background removed;

[0074] Performing gray normalization processing and image binarization processing on the image data of the steel formwork with the background removed to obtain preprocessing data;

[0075] Dividing according to the preprocessing data to obtain the sub-image data of multiple steel formworks.

[0076] In an embodiment of the present invention, the preset prediction model for the remaining life of the steel formwork is a convolutional neural network model.

[0077] According to an embodiment of another aspect, there is also provided a computer-readable storage medium, on which a computer program is stored. When the computer program is executed in a computer, the computer is made to execute the combination Figure 1 The described method.

[0078] According to an embodiment of still another aspect, there is also provided an electronic device, including a memory and a processor. An executable code is stored in the memory. When the processor executes the executable code, the combination Figure 1 The described method is implemented.

[0079] Each embodiment in the present invention is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment.

[0080] Those skilled in the art should be able to realize that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0081] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting the remaining life of a steel formwork, characterized in that: The method comprises: Acquire image data of steel formwork; Dividing the image data of the steel template to obtain a plurality of sub-image data of the steel template, and obtaining mechanical data of the steel template corresponding to each sub-image data of the steel template; wherein the mechanical data includes tensile strength and yield strength; Extracting features from the sub-image data of the plurality of steel templates respectively to obtain a plurality of surface feature data, and extracting features from the mechanical data to obtain a plurality of mechanical feature data; Performing feature fusion on each of the surface feature data and the corresponding mechanical feature data to obtain a plurality of sub-fusion features; Each sub-fusion feature is subjected to feature fusion according to an application influencing factor to obtain a fusion feature matrix; wherein the application influencing factor is determined according to the relative position of the sub-image data to the image data of the steel template; The fused feature matrix is ​​input into a preset steel formwork remaining life prediction model to obtain the steel formwork remaining life.

2. The method according to claim 1, characterized in that After inputting the fused feature matrix into a preset steel template remaining life prediction model to obtain the steel template remaining life, the method further includes: When the delay condition of the remaining life of the steel template is not met, a correction factor of the remaining life is obtained; wherein the delay constraint of the remaining life of the steel template is constructed by the remaining life of the historical steel template and the remaining life of the steel template, and the correction factor of the remaining life is determined by the actual use environment data of the steel template; The final remaining life of the steel formwork is determined based on the correction factor of the remaining life and the remaining life of the steel formwork.

3. The method according to claim 2, characterized in that The time-delay condition of the remaining life of the steel formwork is constructed by the following formula: Where P RL is the remaining life of the steel formwork, C RL is the historical remaining life of the steel formwork, t1 is the time point for the prediction of the remaining life of the steel formwork, t2 is the time point for the prediction of the remaining life of the historical steel formwork, T is the time interval between two predictions, and K is the adjustment coefficient.

4. The method according to claim 3, characterized in that The actual use environment data includes temperature influence factor, humidity influence factor, chemical substance influence factor, load influence factor, and wear influence factor.

5. The method according to claim 4, characterized in that The correction factor for the remaining life is determined by the following formula: Where Y S is the correction factor of the remaining life, S0 is the initial structural strength of the steel formwork, Q is the temperature influence factor, H is the humidity influence factor, C is the chemical influence factor, F is the load influence factor, W is the wear influence factor, a1 is the weight of the correction factor of the remaining life, a2 is the weight coefficient of the humidity influence factor, a3 is the weight coefficient of the chemical influence factor, a4 is the weight coefficient of the load influence factor, a5 is the weight coefficient of the wear influence factor, λ is the dynamic adjustment parameter, I i is the secondary influencing factor, and n is the number of secondary influencing factors.

6. The method according to claim 5, characterized in that After acquiring the image data of the steel formwork, it also includes: The image data of the steel template is cropped to obtain image data of the steel template with the background removed; The image data of the steel template with the background removed is subjected to grayscale normalization processing and image binarization processing to obtain preprocessed data; The sub-image data of multiple steel templates are obtained by dividing the pre-processed data.

7. The method according to claim 6, characterized in that The preset steel formwork remaining life prediction model is a convolutional neural network model.

8. A device for predicting the remaining life of a steel formwork, characterized in that: include: An acquisition unit configured to acquire image data of the steel template; A first data processing unit is configured to divide the image data of the steel template to obtain sub-image data of a plurality of steel templates, and obtain mechanical data of the steel template corresponding to each sub-image data of the steel template, wherein the mechanical data includes tensile strength and yield strength; The second data processing unit is configured to perform feature extraction on the sub-image data of the plurality of steel templates respectively to obtain a plurality of surface feature data, and perform feature extraction on the mechanical data to obtain a plurality of mechanical feature data; A third data processing unit is configured to perform feature fusion on each of the surface feature data and the corresponding mechanical feature data to obtain a plurality of sub-fusion features; The fourth data processing unit is configured to perform feature fusion on each sub-fusion feature according to an application influencing factor to obtain a fusion feature matrix; wherein the application influencing factor is determined according to a relative position of the sub-image data to the image data of the steel template; The fifth data processing unit is configured to input the fused feature matrix into a preset steel formwork remaining life prediction model to obtain the steel formwork remaining life.

9. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images