Bridge anticorrosive coating performance detection method based on big data

Abstract

The invention relates to the technical field of bridge anti-corrosion coating performance detection, in particular to a bridge anti-corrosion coating performance detection method based on big data, which comprises the following steps: performing an accelerated aging test by using a bridge anti-corrosion coating sample, collecting state characteristic data of the bridge anti-corrosion coating sample, and generating a first state characteristic vector to divide a first time sequence; collecting state feature data of the anticorrosive coating of the target bridge area, and generating a second state feature vector to divide a second time sequence; based on the similarity between the first state feature vector and the second state feature vector, determining the corresponding relation between the first time sequence and the second time sequence, so as to calculate the aging acceleration rate of the bridge anticorrosive coating sample; and acquiring multi-dimensional environment monitoring data of the target bridge area to calculate an environment erosion index so as to determine whether the aging acceleration rate needs to be corrected or not, so that an aging acceleration curve is determined, and further, the actual endurance time of the anticorrosive coating of the target bridge area is determined. According to the invention, the precision of bridge anticorrosive coating performance detection is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge anticorrosive coating performance detection, and particularly relates to a bridge anticorrosive coating performance detection method based on big data. BACKGROUND

[0002] With the continuous extension of the service time of infrastructure, the performance detection and durability evaluation of bridge anticorrosive coating are increasingly important. As the first line of defense to protect the bridge structure from environmental erosion, the performance state of the coating is directly related to the safety and service life of the structure. It is of great significance to establish an accurate coating performance detection and life prediction method for the long-term safe operation of infrastructure.

[0003] However, the existing coating performance detection method has obvious deficiencies. The traditional detection method is difficult to identify the early hidden damage of the coating, and cannot establish an effective correlation between the laboratory accelerated aging data and the actual service behavior. Especially under complex environmental conditions, the existing method often cannot accurately quantify the dynamic influence of environmental factors on the aging process, resulting in a large gap between the coating durability prediction results and the actual service performance.

[0004] Chinese patent publication No. CN111879710A discloses a steel structure coating corrosion resistance evaluation method, system, server and storage medium. The present application provides a steel structure coating corrosion resistance evaluation method, comprising: acquiring the to-be-detected infrared spectrum of the to-be-detected steel structure coating; substituting the to-be-detected infrared spectrum into a preset intelligent identification model for calculation to generate coating performance data; and evaluating the coating performance data based on a preset grade evaluation standard to obtain the corrosion resistance evaluation result of the to-be-detected steel structure coating.

[0005] Therefore, the existing technology has the following problems:

[0006] The early warning of coating performance degradation is difficult due to the limitations of the detection method, and the laboratory data and field service life prediction deviation are large due to insufficient consideration of the influence of environmental history. SUMMARY

[0007] Therefore, the present application provides a bridge anticorrosive coating performance detection method based on big data to overcome the problems of early warning of coating performance degradation due to limitations of the detection method, and large deviation of laboratory data and field service life prediction due to insufficient consideration of the influence of environmental history in the prior art.

[0008] To achieve the above purpose, the present application provides a bridge anticorrosive coating performance detection method based on big data, comprising:

[0009] The bridge anticorrosion coating sample is subjected to an accelerated aging test under preset environmental load conditions, and state feature data of the bridge anticorrosion coating sample is collected by the intelligent sensor in a time sequence, wherein the state feature data includes acoustic emission signals, impedance spectrum data and appearance feature data;

[0010] A plurality of first state feature vectors are generated based on the state feature data to divide a first time sequence;

[0011] State feature data of the anticorrosion coating of the target bridge region in a historical period is collected by the intelligent sensor to generate a plurality of second state feature vectors, and a second time sequence is divided based on the corresponding relationship between the second state feature vectors and the collection time;

[0012] Based on the similarity of each of the first state feature vectors and each of the second state feature vectors, a plurality of aging feature corresponding points are determined to determine the corresponding relationship between the first time sequence and the second time sequence based on each of the aging feature corresponding points;

[0013] Based on the corresponding relationship, the aging acceleration rate of the bridge anticorrosion coating sample is calculated;

[0014] Multi-dimensional environmental monitoring data of the target bridge region in the historical period is obtained according to the second time sequence to calculate the environmental erosion index in each aging stage in the second time sequence, wherein the multi-dimensional environmental monitoring data includes daily average temperature, humidity and salt deposition rate;

[0015] Based on each of the environmental erosion indices, it is determined whether the corresponding aging acceleration rate needs to be corrected, and a corresponding correction coefficient is calculated;

[0016] The aging acceleration rate is corrected based on the correction coefficient to determine the aging acceleration curve;

[0017] The accelerated failure time of the bridge anticorrosion coating sample in the accelerated aging test is obtained to determine the durability time of the anticorrosion coating of the target bridge region based on the aging acceleration curve.

[0018] Further, each of the first state feature vectors obtained at the first collection frequency is compared with a preset reference vector to divide a plurality of first aging stages and determine the first time sequence.

[0019] Further, each of the second state feature vectors obtained at the second collection frequency is compared with a preset reference vector to divide a plurality of second aging stages and determine the second time sequence.

[0020] Further, the first state feature vector at the end of each first aging stage is extracted as a corresponding first state feature representation vector;

[0021] The second state feature vector at the end of each second aging stage is extracted as a corresponding second state feature representation vector.

[0022] Further, based on the maximum value of the similarity between each second state feature representation vector and all first state feature representation vectors, a corresponding aging feature corresponding point is determined.

[0023] Further, based on the one-to-one correspondence relationship between the plurality of aging feature corresponding points and the plurality of first aging stages and the plurality of second aging stages, a corresponding relationship between the first time sequence and the second time sequence is determined.

[0024] Further, based on the corresponding relationship between the first time sequence and the second time sequence, each first aging stage and the corresponding second aging stage are extracted.

[0025] The ratio of the duration of each first aging stage to the duration of the corresponding second aging stage is calculated to determine the corresponding aging acceleration rate.

[0026] Further, based on the sum of the ratio of the multi-dimensional environmental monitoring data to the corresponding threshold value, an environmental erosion index of each second aging stage is determined.

[0027] Based on the environmental erosion index being greater than a preset environmental erosion index threshold value, it is determined that the corresponding aging acceleration rate needs to be corrected.

[0028] Further, based on the ratio of the environmental erosion index to the preset environmental erosion index threshold value and the amplification effect coefficient of the corresponding second aging stage, a corresponding correction coefficient is determined.

[0029] Further, it also includes determining the performance state of the target bridge area anticorrosive coating at a specified time point based on the aging acceleration curve.

[0030] Compared with the prior art, the beneficial effects of the present application are that by constructing a complete technical system from laboratory accelerated aging test to field performance detection, a systematic bridge anticorrosive coating performance evaluation and prediction method is established. The system can realize early insight into the degradation trend of coating performance through dynamic tracking and mapping of laboratory and field state characteristics, and solve the problem of lagging early warning of traditional methods. The present application realizes the effective correlation of laboratory data and field service behavior through the organic combination of time sequence division, feature correspondence, acceleration rate calculation and environmental correction and other links. This multi-linkage collaborative working mechanism makes the coating durability prediction no longer based on static deduction in ideal environment, but can dynamically respond to actual environmental fluctuations, significantly improving the accuracy and reliability of life prediction in real complex environment.

[0031] Further, the application realizes the standardization of the laboratory aging process by adopting a stage division method based on a difference threshold. This quantitative division eliminates the subjectivity of human judgment and ensures the consistency and repeatability of the aging stage identification. By dividing the continuous aging process into discrete development stages, a clear time framework is provided for in-depth analysis of the performance evolution of the coating, making laboratory research better reveal the stage characteristics of coating aging and creating favorable conditions for subsequent time sequence correspondence.

[0032] Further, the application ensures the uniformity of data processing in two different scenarios by applying the laboratory stage division method to field data. This unified data processing method enables laboratory research results to be directly applied to field evaluation, establishing an effective link between theoretical research and engineering practice. By maintaining the consistency of the stage division standard, systematic errors caused by different data processing methods are eliminated, providing a necessary prerequisite for accurate comparison of laboratory data and field data and enhancing the internal coordination of the entire evaluation system.

[0033] Further, the application realizes efficient condensation of stage feature information by extracting feature vectors at the end of each aging stage as a representation. This method not only retains the most representative state information of each aging stage, but also effectively reduces the complexity of data processing. By highlighting the state characteristics of the stage transition nodes, the identification ability of the key nodes in the aging process is enhanced, providing a high-quality data foundation for accurately establishing the correspondence between laboratory and field aging stages and improving the accuracy and efficiency of time sequence mapping.

[0034] Further, the application realizes accurate correspondence between laboratory and field aging stages through a matching strategy based on maximum similarity. This method can effectively overcome state evaluation deviations caused by environmental differences, material batches, and other factors, ensuring the scientific nature of the correspondence. By finding the most similar state feature points, a reliable connection between the two time sequence systems is established, providing an accurate correspondence benchmark for subsequent acceleration rate calculation and significantly improving the logical rigor and result reliability of the entire evaluation system.

[0035] Further, the application establishes a systematic time sequence mapping framework by establishing a one-to-one correspondence between stages. This global correspondence goes beyond the limitations of single-point correspondence and can more comprehensively reflect the overall laws of the aging process. By establishing a complete stage correspondence chain, a continuous mapping path from the laboratory to the field is formed, making it possible to infer long-term service behavior based on limited experimental data and greatly expanding the engineering application value of the technical solution.

[0036] Further, the present application realizes the fine description of the coating aging speed by calculating the aging acceleration rate in stages. This not only reveals the dynamic law of the aging rate changing with time, but more importantly, by capturing the trend of the acceleration rate, it provides a key basis for judging whether the coating has entered the accelerated degradation channel and thus issuing an early warning. By obtaining the quantitative acceleration index of each stage, a direct correlation between the aging process and time is established, providing key parameter support for accurately predicting the remaining life of the coating and enhancing the practicality of the life prediction model.

[0037] Further, the present application realizes the intelligent identification of environmental impact by establishing a threshold judgment mechanism for the environmental erosion index. This method can automatically detect the interference of abnormal environmental conditions on the aging process, ensuring the adaptive ability of the evaluation. This mechanism directly addresses the problem that the historical impact of the environment has not been quantified. By identifying and marking the data segment disturbed by environmental fluctuations, it locks the target for subsequent precise correction, reducing the prediction deviation caused by environmental factors from the source.

[0038] Further, the present application realizes the fine processing of environmental impact by introducing a correction calculation method of amplification effect coefficient. This method not only considers the immediate impact of environmental factors, but also takes into account the sensitivity change characteristics in the material aging process. By dynamically adjusting the correction strength, the environmental correction is more in line with the physical nature of material aging, significantly improving the accuracy of aging prediction under complex environmental conditions and enhancing the engineering applicability of the method.

[0039] Further, the present application greatly enhances the practical value of the technology by extending the aging acceleration curve into a performance state query tool. This method enables users not only to obtain macro life prediction, but also to understand the detailed performance state at a specific time point. By establishing a direct correspondence between time points and performance states, it provides more abundant reference information for maintenance decision-making, making the development of preventive maintenance plans more targeted and operable.

[0040] Further, the present application realizes the automatic collection of multi-source heterogeneous data through intelligent sensors. This intelligent data collection method not only greatly reduces manual intervention, but more importantly, ensures the consistency of laboratory and field data in format, quality, and time synchronization, laying a solid foundation for building a reliable time series feature database. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 Flowchart of the bridge anti-corrosion coating performance detection method based on big data of the present application embodiment;

[0042] Figure 2 Flowchart of determining the correspondence between the first time series and the second time series of the present application embodiment;

[0043] Figure 3 A flow chart for calculating the aging acceleration rate of a bridge anticorrosion coating sample for an embodiment of the present application;

[0044] Figure 4 A logic decision diagram for determining whether correction of the aging acceleration rate is needed for an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the objects and advantages of the present application clearer, the present application will be further described in conjunction with embodiments. It should be understood that the specific embodiments described herein merely serve the purpose of explaining the present application and are not intended to limit the present application.

[0046] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. It should be understood by those skilled in the art that the embodiments are merely used to explain the technical principles of the present application and are not intended to limit the protection scope of the present application.

[0047] It should be noted that, in the description of the present application, the terms "upper", "lower", "left", "right", "inner", "outer" and the like indicating the direction or positional relationship are based on the direction or positional relationship shown in the drawings, which is merely for the convenience of description and does not indicate or imply that the device or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0048] In addition, it should also be noted that, in the description of the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connection" should be understood in a broad sense, for example, can be fixed connection, can also be detachable connection, or integrally connected; can be mechanical connection, can also be electrical connection; can be directly connected, can also be indirectly connected through an intermediate medium, can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0049] Please refer to Figure 1 Fig. 1 is a flow chart of a bridge anticorrosion coating performance detection method based on big data according to an embodiment of the present application, and the bridge anticorrosion coating performance detection method based on big data according to an embodiment of the present application comprises the following steps:

[0050] In step S1, an accelerated aging test is performed on a bridge anticorrosion coating sample under a preset environmental load condition, and state characteristic data of the bridge anticorrosion coating sample is collected by an intelligent sensor in a time sequence, wherein the state characteristic data comprises acoustic emission signals, impedance spectrum data and appearance characteristic data;

[0051] In step S2, a plurality of first state characteristic vectors are generated based on the state characteristic data, so as to divide a first time sequence.

[0052] In step S3, the state feature data of the anticorrosive coating of the target bridge region in the historical period is collected by the intelligent sensor to generate a plurality of second state feature vectors, and the second time sequence is divided based on the corresponding relationship between the second state feature vectors and the collection time.

[0053] In step S4, a plurality of aging feature corresponding points are determined based on the similarity between each of the first state feature vectors and each of the second state feature vectors, and the corresponding relationship between the first time sequence and the second time sequence is determined based on each of the aging feature corresponding points.

[0054] In step S5, the aging acceleration rate of the bridge anticorrosive coating sample is calculated based on the corresponding relationship.

[0055] In step S6, the multi-dimensional environmental monitoring data of the target bridge region in the historical period is obtained according to the second time sequence to calculate the environmental erosion index in each aging stage in the second time sequence, wherein the multi-dimensional environmental monitoring data includes daily average temperature, humidity and salt deposition rate.

[0056] In step S7, it is determined whether the corresponding aging acceleration rate needs to be corrected based on the environmental erosion index, and the corresponding correction coefficient is calculated.

[0057] In step S8, the aging acceleration rate is corrected based on the correction coefficient to determine the aging acceleration curve.

[0058] In step S9, the accelerated failure time of the bridge anticorrosive coating sample in the accelerated aging test is obtained to determine the durability time of the anticorrosive coating of the target bridge region based on the aging acceleration curve.

[0059] In the embodiment, first, an accelerated aging test of a bridge anticorrosive coating sample is carried out under a preset environmental load condition in the laboratory, and state characteristic data of the sample is collected in time sequence, including acoustic emission signals, impedance spectrum data and appearance characteristic data. The preset environmental load condition is a salt spray-humid heat-ultraviolet coupling cycle environmental load condition, which can be specifically set as: salt spray spraying for 4 hours, temperature 35°C; then converted to a humid heat environment for 4 hours, temperature 45°C, relative humidity 95%; and then ultraviolet irradiation for 8 hours, irradiance 0.68 W / m2@340 nm. It can be understood that the salt spray-humid heat-ultraviolet coupling cycle environmental load condition is set in this way to accurately simulate and accelerate the most severe and typical corrosion environment faced by the bridge coating in the real world, especially in coastal or industrial areas. The acoustic emission signals include ring count, signal energy and amplitude parameters; the impedance spectrum data include impedance modulus value at the maximum phase angle frequency and coating resistance value; and the appearance characteristic data include color difference ΔE value and 60° gloss retention rate. It can be understood that the three groups of data respectively depict the health state of the coating from three dimensions of “dynamic damage event”, “electrochemical protection performance” and “apparent physical state”. The acoustic emission signals are used to represent the initiation and expansion of micro-damage inside the coating; the impedance spectrum data are used to represent the barrier protection performance and corrosion resistance of the coating; and the appearance characteristic data are used to represent the aging degree and surface physical state of the coating.

[0060] Subsequently, state characteristic data of the anticorrosive coating in the historical period in the target bridge area is collected. A plurality of first state characteristic vectors are generated based on the state characteristic data to divide a first time sequence, and a plurality of second state characteristic vectors are generated to divide a second time sequence. Then, a plurality of aging feature corresponding points are determined based on the similarity of the first state characteristic vectors and the second state characteristic vectors, and a corresponding relationship between the first time sequence and the second time sequence is established. After calculating the aging acceleration rate based on the corresponding relationship, the multi-dimensional environmental monitoring data of the target bridge area in the historical period is obtained according to the second time sequence, including daily average temperature, humidity and salt spray deposition rate, and the environmental erosion index in each aging stage is calculated. It is determined whether the corresponding aging acceleration rate needs to be corrected based on the environmental erosion index, the aging acceleration rate is corrected after calculating the correction coefficient, and the aging acceleration curve is determined. Finally, the accelerated failure time of the bridge anticorrosive coating sample is obtained, and the actual durability time of the anticorrosive coating of the target bridge area is determined based on the aging acceleration curve.

[0061] In the embodiment, the state characteristic data of the anticorrosion coating are collected by intelligent sensors, wherein the intelligent sensors include: a high-resolution acoustic emission sensor for automatically capturing acoustic emission signals released when microcracks of the coating are generated; a local electrochemical impedance spectroscopy probe for automatically collecting impedance spectroscopy data of a specified measurement point; and a multispectral imager for automatically collecting appearance characteristic data of the coating surface. In the field monitoring, the multiple intelligent sensors are deployed at distributed monitoring nodes at key positions of the bridge and communicate with a central data platform through an Internet of Things protocol. The intelligent sensors automatically work according to a preset collection frequency and transmit the collected state characteristic data to a big data analysis platform in real time through the network. This intelligent data collection method not only greatly reduces manual intervention, but more importantly, ensures the consistency of the laboratory and field data in terms of format, quality and time synchronization, thereby laying a solid foundation for subsequent construction of a reliable time sequence feature database.

[0062] Specifically, in step S2, the first state characteristic vectors obtained at the first collection frequency are compared with a preset reference vector, and a plurality of first aging stages are divided to determine a first time sequence.

[0063] In the embodiment, in the laboratory accelerated aging test, the vector generated by the state characteristic data at the starting time point is used as the initial reference vector, and the first state characteristic vectors at subsequent time points are compared with the reference vector at a first collection frequency of 24 hours per day. When the difference between the first state characteristic vector and the reference vector exceeds a preset difference threshold, it is determined that the coating state has changed significantly, i.e., the time point is determined as the dividing point of the first aging stage. Subsequently, the first state characteristic vector at the dividing point is used as a new reference vector, and the above process is repeated, so as to divide the continuous laboratory aging data into a plurality of discrete first aging stages with clear physical meaning. That is, all the dividing points are arranged in chronological order, which divides the entire continuous aging process into a plurality of first aging stages, and the plurality of first aging stages form a first time sequence in chronological order. It can be understood that the first time sequence refers to a time sequence of a series of key states capable of representing the aging process of the coating arranged in chronological order in the laboratory accelerated aging test, i.e., the plurality of first aging stages are organized in chronological order to form a time sequence with clear physical meaning. Before calculating the difference, the state characteristic vectors need to be normalized to scale all the characteristic components to the interval [0, 1]. It can be understood that any method in the prior art can be used to normalize the state characteristic vectors. After normalization, the Euclidean distance between the two characteristic vectors is calculated as the difference. The preset difference threshold is preferably set to 0.15.

[0064] Specifically, in step S3, the second state feature vectors obtained at the second acquisition frequency are compared with the preset reference vector, and several second aging stages are divided to determine the second time sequence.

[0065] In the embodiment, in the field data collection of the target bridge area, the vector generated by the state feature data of the initial time point is taken as the initial reference vector, and the second state feature vectors of the subsequent time points are compared with the reference vector in turn according to the second acquisition frequency of every month, i.e. 30 days. The same difference threshold as that of the laboratory division is adopted, and when the difference between the second state feature vector and the reference vector exceeds the threshold, the time point is determined as the demarcation point of the second aging stage. Subsequently, the first state feature vector of the demarcation point is taken as the new reference vector, and the above process is repeated, so as to divide the continuous field monitoring data into several discrete second aging stages. That is, all the demarcation points are arranged in time sequence, which divides the entire continuous field service process into several second aging stages, and the several second aging stages constitute the second time sequence in time sequence. It can be understood that the second time sequence refers to a time sequence sequence of a series of key states capable of representing the coating aging process arranged in time sequence during the field service process of the target bridge, that is, the demarcation points of the several second aging stages are organized in time sequence to constitute a time sequence sequence comparable with the first time sequence. This implementation ensures the consistency of the field data and the laboratory data in the stage division standard.

[0066] Please refer to Figure 2 Fig. 2 is a flow chart of determining the corresponding relationship between the first time sequence and the second time sequence according to the embodiment of the present application.

[0067] Specifically, in step S4, it includes: step S41, extracting the first state feature vector at the end of each first aging stage as the corresponding first state feature representation vector;

[0068] Step S42, extracting the second state feature vector at the end of each second aging stage as the corresponding second state feature representation vector.

[0069] In the embodiment, after the several first aging stages and the several second aging stages are divided, the first state feature vector corresponding to the end time point of each first aging stage is extracted as the first state feature representation vector of the stage. At the same time, the second state feature vector corresponding to the end time point of each second aging stage is extracted as the second state feature representation vector of the stage. These representation vectors serve as the representative state data of each aging stage to provide input for subsequent aging feature corresponding point determination.

[0070] Specifically, step S4 comprises: step S43, determining the corresponding aging feature corresponding point based on the maximum value of the similarity between each second state feature characterization vector and all first state feature characterization vectors.

[0071] In the embodiment, for each obtained second state feature characterization vector, the cosine similarity with all first state feature characterization vectors is calculated. Through traversal comparison, the first state feature characterization vector and the second state feature characterization vector corresponding to the maximum value of the similarity are selected, and the two are determined as the corresponding aging feature corresponding point. This step finds the most matched laboratory aging stage for each field aging stage by maximizing the similarity.

[0072] It can be understood that, in addition to the first pair of aging feature corresponding points, other second state feature characterization vectors do not consider the first state feature characterization vectors matched as aging feature corresponding points and before them when calculating the cosine similarity with the first state feature characterization vectors.

[0073] Specifically, step S4 comprises: step S44, determining the corresponding relationship between the first time sequence and the second time sequence based on the one-to-one corresponding relationship between the plurality of first aging stages and the plurality of second aging stages determined by the plurality of aging feature corresponding points.

[0074] In the embodiment, after a series of discrete aging feature corresponding points are determined, a one-to-one corresponding relationship between the plurality of first aging stages in the first time sequence and the plurality of second aging stages in the second time sequence is established based on the corresponding points. This corresponding relationship associates the laboratory aging process and the field service process at the stage level, forms a systematic mapping framework of the first time sequence and the second time sequence, and lays a foundation for subsequent aging acceleration rate calculation.

[0075] Please refer to Figure 3 Fig. 1 is a flowchart of the method for calculating the aging acceleration rate of the bridge anticorrosive coating sample according to the embodiment of the present application.

[0076] Specifically, step S5 comprises: step S51, extracting each first aging stage and the corresponding second aging stage based on the corresponding relationship between the first time sequence and the second time sequence.

[0077] Step S52, calculating the ratio of the time length of each first aging stage to the time length of the corresponding second aging stage to determine the corresponding aging acceleration rate.

[0078] In the embodiment, based on the determined correspondence between the first time sequence and the second time sequence, each corresponding first aging stage and second aging stage are extracted. For each pair of corresponding aging stages, the ratio of the first aging stage duration and the second aging stage duration is calculated, and the ratio is determined as the corresponding aging acceleration rate. By calculating the acceleration rates of multiple consecutive stages, the trend of the coating aging speed changing with time can be obtained, which provides data support for understanding the aging law.

[0079] Referring to Figure 4 Fig. 4 shows a logical decision diagram for determining whether the aging acceleration rate needs to be corrected according to an embodiment of the present application.

[0080] Specifically, in step S6, the environment erosion index of each second aging stage is determined based on the sum of the ratio of the multi-dimensional environment monitoring data and the corresponding threshold value.

[0081] Specifically, in step S7, it is determined that the corresponding aging acceleration rate needs to be corrected based on the environment erosion index being greater than a preset environment erosion index threshold value.

[0082] In the embodiment, first, based on the multi-dimensional environment monitoring data in each aging stage in the second time sequence, including daily average temperature, humidity, and salt spray deposition rate, the environment erosion index of each stage is calculated by weighted fusion. The threshold value corresponding to the multi-dimensional environment monitoring data is preferably set as the average of the simulated environment in the laboratory accelerated aging test, the weight of the salt spray deposition rate is set as the highest 0.5, the weight of the humidity is set as the second highest 0.3, and the weight of the temperature is set as the lowest 0.2. The environment erosion index determined by weighted summation directly reflects the severity of the field environment relative to the laboratory simulated environment. Subsequently, the environment erosion index is compared with a preset environment erosion index threshold value, and preferably, the environment erosion index threshold value can be set as 1.1. When the environment erosion index is greater than the threshold value, it is determined that the aging acceleration rate of the stage is deviated due to environmental fluctuations, i.e., it is determined that the corresponding aging acceleration rate needs to be corrected. This mechanism ensures that the influence of environmental abnormal fluctuations on the aging process can be handled in a timely manner.

[0083] Specifically, in step S7, the corresponding correction coefficient is determined based on the ratio of the environment erosion index and the preset environment erosion index threshold value and the amplification effect coefficient of the corresponding second aging stage.

[0084] In the embodiment, for the aging acceleration rate that needs to be corrected, a correction coefficient is calculated based on the ratio of the corresponding environmental erosion index to the preset environmental erosion index threshold, combined with the amplification effect coefficient corresponding to the aging stage. The calculation formula of the correction coefficient is "1+(environmental erosion index / environmental erosion index threshold-1)*amplification effect coefficient", and the amplification effect coefficient is equal to the ratio of the serial number of the current second aging stage to the total number of the second aging stages. Among them, the amplification effect coefficient increases with the advancement of the aging stage, so as to reflect the improvement of the material sensitivity to the environment in the later aging stage. Through this calculation, dynamic environmental correction of the aging acceleration rate is realized.

[0085] Specifically, in step S8, the aging acceleration rate is corrected based on the correction coefficient to determine the aging acceleration curve.

[0086] In the embodiment, the aging acceleration rate calculated in each stage is multiplied by the corresponding correction coefficient to obtain the corrected aging acceleration rate. Based on the corrected acceleration rate in each stage, a continuous aging acceleration curve is constructed by interpolation method. The curve is a nonlinear curve describing the relationship between field service time and equivalent laboratory aging time, and the slope of the curve, i.e. the aging rate, gradually increases with the extension of service time, reflecting the acceleration phenomenon of the coating aging process. The abscissa of the curve is the field service time, and the ordinate is the equivalent laboratory aging time.

[0087] Specifically, in step S9, the accelerated failure time of the bridge anti-corrosion coating sample in the accelerated aging test is obtained to determine the durability time of the target bridge area anti-corrosion coating based on the aging acceleration curve.

[0088] In the embodiment, first, the accelerated failure time of the coating is determined through the laboratory accelerated aging test, such as the time when the impedance modulus value drops to 50% of the initial value. Subsequently, on the corrected aging acceleration curve, find the point whose ordinate is equal to the accelerated failure time, and the abscissa of this point is the predicted actual durability time of the target bridge area anti-corrosion coating. Through this process, scientific prediction from laboratory accelerated aging data to field actual service life is realized.

[0089] It can be understood that the aging acceleration curve is composed of a historical section and a prediction section, wherein the historical section is constructed by interpolation based on the second aging stages corresponding to the completed time sequence and the corrected aging acceleration rates thereof; the prediction section refers to the curve section extending from the end of the last second aging stage to the predicted actual durability time, and the slope of the curve section is determined by trend extrapolation: the moving average of the corrected acceleration rates of the last three aging stages in the historical section is taken as the reference aging acceleration rate of the prediction section; at the same time, considering the acceleration characteristics of the material aging process, the average growth rate of the aging acceleration rate of the next stage relative to the previous stage in the historical section is calculated, and a growth rate increasing with time is given to the reference acceleration rate, so that the slope of the prediction section curve shows an increasing trend, that is, the aging rate constantly accelerates with time. The curve slope, that is, the aging acceleration rate at any time in the prediction section = reference aging acceleration rate * (1 + average growth rate) ^ (the field time point in the prediction section - the field time at the end of the last second aging stage).

[0090] Specifically, in step S9, the performance state of the target bridge area anticorrosive coating at a specified time point is determined based on the aging acceleration curve.

[0091] In the embodiment, after the corrected aging acceleration curve is established, the performance state of the target bridge area anticorrosive coating at a specified time point can be determined based on the curve. By mapping the specified time point to the aging acceleration curve, the corresponding equivalent laboratory aging time is obtained, and then the detailed performance state data at the time point is obtained by querying the laboratory characteristic database. This function expands the application range of the method and realizes real-time state evaluation of the coating performance.

[0092] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will all fall within the protection scope of the present application.

Claims

1. A method for testing the performance of bridge anti-corrosion coatings based on big data, characterized in that, include: Accelerated aging tests were conducted on bridge anti-corrosion coating samples under preset environmental load conditions. The state characteristic data of the bridge anti-corrosion coating samples were collected by intelligent sensors according to the time sequence. The state characteristic data included acoustic emission signals, impedance spectrum data and appearance characteristic data. Several first state feature vectors are generated based on the state feature data to divide the first time series; The system collects state characteristic data of the anti-corrosion coating of the target bridge area within a historical period using intelligent sensors, generates several second state feature vectors, and divides the second time series based on the correspondence between the second state feature vectors and the collection time. Based on the similarity between each of the first state feature vectors and each of the second state feature vectors, several aging feature corresponding points are determined, so as to determine the correspondence between the first time series and the second time series based on each aging feature corresponding point. The aging acceleration rate of bridge anti-corrosion coating samples was calculated based on the aforementioned correspondence. According to the second time series, multidimensional environmental monitoring data of the target bridge area within the historical period are obtained to calculate the environmental erosion index in each aging stage in the second time series. The multidimensional environmental monitoring data includes daily average temperature, humidity and salt spray deposition rate. Based on each environmental erosion index, determine whether the corresponding aging acceleration rate needs to be corrected, and calculate the corresponding correction coefficient; The aging acceleration rate is corrected based on the correction coefficient to determine the aging acceleration curve; The accelerated failure time of bridge anti-corrosion coating samples in accelerated aging tests is obtained, and the durability time of the anti-corrosion coating in the target bridge area is determined based on the aging acceleration curve.

2. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 1, characterized in that, Based on the comparison between the first state feature vectors obtained at the first acquisition frequency and the preset benchmark vector, several first aging stages are divided and determined as the first time sequence.

3. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 2, characterized in that, Based on the comparison between the second state feature vectors obtained at the second acquisition frequency and the preset benchmark vector, several second aging stages are divided and determined as the second time series.

4. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 3, characterized in that, Extract the first state feature vector at the end of each first aging stage as the corresponding first state feature representation vector; Extract the second-state feature vector at the end of each second aging stage as the corresponding second-state feature representation vector.

5. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 4, characterized in that, The corresponding aging feature point is determined based on the maximum similarity between each second-state feature representation vector and all first-state feature representation vectors.

6. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 5, characterized in that, Based on the one-to-one correspondence between several first aging stages and several second aging stages determined by several aging characteristic corresponding points, the correspondence between the first time series and the second time series is determined.

7. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 6, characterized in that, Based on the correspondence between the first time series and the second time series, each first aging stage and its corresponding second aging stage are extracted; The ratio of the duration of each first aging stage to the duration of the corresponding second aging stage is calculated and determined as the corresponding aging acceleration rate.

8. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 7, characterized in that, The sum of the ratios of the multidimensional environmental monitoring data to the corresponding thresholds is used to determine the environmental erosion index for each second aging stage. Based on the fact that the environmental erosion index is greater than the preset environmental erosion index threshold, it is determined that the corresponding aging acceleration rate needs to be corrected.

9. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 8, characterized in that, Based on the ratio of the environmental erosion index to the preset environmental erosion index threshold and the amplification effect coefficient of the corresponding second aging stage, the corresponding correction coefficient is determined.

10. The method for testing the performance of bridge anti-corrosion coatings based on big data according to claim 1, characterized in that, It also includes determining the performance status of the anti-corrosion coating in the target bridge area at a specified time point based on the aging acceleration curve.

Images