Mass concrete crack assessment method and system for fan foundation

Abstract

The invention provides a mass concrete crack evaluation method and system for a fan foundation, and relates to the technical field of constructional engineering and structural monitoring, and the method comprises the steps: collecting the characteristic parameters of a crack in real time, calculating a crack hazard index, an influence index and an expansion index according to the parameters, and forming a characteristic index representing the crack condition; establishing a concrete crack risk prediction model based on a convolutional neural network, receiving the characteristic index through an input layer, outputting a risk grade index after hidden layer processing, considering construction design parameters to generate a crack risk correction factor, calculating a crack risk correction coefficient, and comparing the coefficient with a preset correction threshold value, and determining a final risk grade index of the concrete crack by using a correction lifting mechanism. By monitoring the characteristic parameters of the concrete crack in real time and combining the convolutional neural network model, accurate assessment of the concrete crack risk of the fan foundation is realized.

Description

Technical Field

[0001] This invention relates to the field of building engineering and structural monitoring technology, specifically to a method and system for assessing cracks in large-volume concrete for wind turbine foundations. Background Technology

[0002] Crack formation is a common and serious problem during the construction of large-volume concrete foundations for wind turbines, affecting the safety and durability of the structure. Traditional crack monitoring methods mainly rely on manual inspection and periodic assessment, making it difficult to achieve real-time monitoring and timely early warning. With the development of sensor technology and the advancement of data analysis methods, automated monitoring systems have been gradually introduced to improve the detection accuracy and response efficiency of concrete cracks.

[0003] In recent years, the application of artificial intelligence technologies based on machine learning and deep learning in the field of structural health monitoring has been increasing. These technologies can establish more accurate crack risk assessment models by analyzing complex crack characteristics and construction design parameters, thereby enabling effective prediction and management of concrete cracks. Simultaneously, combined with IoT technology, these systems can collect and transmit data in real time, providing engineers with more comprehensive decision support, thus promoting the development and optimization of wind turbine foundation concrete construction technology.

[0004] In existing technologies, traditional crack monitoring methods mainly rely on manual inspection and periodic assessment. This approach is not only labor-intensive, but the periodic inspections may cause crack occurrence and growth to be overlooked, thus delaying timely responses to potential risks. Furthermore, manual inspection is often affected by subjective factors, and different inspectors may have different assessment results for the same crack, leading to inconsistent and inaccurate crack condition judgments. This inconsistency may result in erroneous risk assessments, which in turn affect subsequent maintenance and reinforcement decisions. Existing technologies often lack comprehensive collection and analysis of crack characteristic parameters, resulting in inaccurate and incomplete assessments of concrete crack conditions.

[0005] Furthermore, existing crack monitoring methods cannot continuously monitor characteristic parameters such as crack width, depth, and propagation rate, leading to insufficient assessment accuracy. Traditional crack risk prediction models are often relatively simple, lacking the dynamic adaptability of deep learning and data-driven approaches. Moreover, traditional crack monitoring technologies often fail to consider environmental factors. Environmental factors such as temperature, humidity, and concrete curing conditions have a significant impact on the shrinkage and expansion of concrete, potentially leading to crack formation and development. Finally, many traditional methods rely on cumbersome data entry and manual processing, resulting in untimely data updates and delayed information feedback.

[0006] Therefore, it is necessary to provide a method and system for assessing cracks in large-volume concrete for wind turbine foundations to address the aforementioned problem.

[0007] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0008] The purpose of this invention is to provide a method and system for assessing cracks in large-volume concrete for wind turbine foundations, in order to solve the problems mentioned in the background art.

[0009] To achieve the above objectives, the present invention provides the following technical solution:

[0010] A method for assessing cracks in large-volume concrete for wind turbine foundations, comprising the following steps:

[0011] Step 1: During the current monitoring period, data is collected on the concrete foundation of the wind turbine to be evaluated and multiple control wind turbine foundations to obtain characteristic parameters for characterizing the surface cracks of each wind turbine foundation concrete. The characteristic parameters include crack width, crack length, crack depth, average spacing between cracks, crack propagation rate, and total number of cracks.

[0012] Step 2: Based on the characteristic parameters, obtain the characteristic indices used to characterize the surface crack condition of the corresponding wind turbine foundation concrete. The characteristic indices include the crack hazard index, crack influence index, and crack propagation index. The characteristic indices of the control wind turbine foundation concrete are evaluated based on the expert scoring method to determine its crack risk level index, which includes mild risk, moderate risk, and severe risk.

[0013] Step 3: Construct a concrete crack risk prediction model based on a deep learning network, with the input being the feature index and the output being the crack risk level index. Train the model based on the feature index and crack risk level index of the wind turbine foundation concrete. Input the feature index of the wind turbine foundation concrete to be evaluated into the model to obtain the corresponding crack risk level index.

[0014] Step 4: Obtain the influencing parameters of concrete cracks in the wind turbine foundation. The influencing parameters include wind turbine operating load, concrete strength, water-cement ratio and temperature difference. Generate a crack risk correction factor based on the obtained construction design parameters, and obtain the characteristic index of cracks on the concrete surface to be evaluated. Use the characteristic index of cracks in the concrete to be evaluated and the crack risk correction factor to calculate the crack risk correction coefficient.

[0015] Step 5: Establish a correction adjustment mechanism, compare the crack risk correction coefficient of the concrete crack to be evaluated with the preset correction threshold range, and correct the crack risk level index according to the comparison results to determine the final risk level index of the concrete crack to be evaluated.

[0016] Furthermore, based on the characteristic parameters, characteristic indices are obtained to characterize the surface crack condition of the corresponding wind turbine foundation concrete. These indices include the crack hazard index, crack influence index, and crack propagation index, and the method used is as follows:

[0017] The crack hazard index is calculated based on the characteristic parameters of cracks on the concrete surface, namely crack width, crack length, and crack depth. The formula used is as follows:

[0018]

[0019] Where a, b, and c represent the crack width, crack length, and crack depth of the same wind turbine foundation concrete, respectively, and CHI represents the crack hazard index of the corresponding wind turbine foundation concrete.

[0020] The crack influence index is calculated by combining the crack width and crack depth, characteristic parameters of concrete surface cracks, with the average spacing between cracks and the total number of cracks. The formula used is as follows:

[0021]

[0022] Where N is the total number of cracks in the same wind turbine foundation concrete, S is the average spacing between cracks in the same wind turbine foundation concrete, and CII represents the crack influence index of the corresponding wind turbine foundation concrete.

[0023] The crack propagation index is calculated using the characteristic parameters of cracks on the concrete surface, namely crack propagation rate, crack width, and crack length. The formula used is as follows:

[0024]

[0025] Where v is the crack propagation rate of the same wind turbine foundation concrete, and CPII represents the crack propagation index of the corresponding wind turbine foundation concrete.

[0026] Furthermore, a concrete crack risk prediction model was established to predict crack risk level indicators. The method used was as follows:

[0027] The concrete crack risk prediction model adopts a neural network convolutional structure, including an input layer, a hidden layer, and an output layer. The input layer is responsible for receiving the extracted feature indices that characterize the crack condition. The hidden layer is used to process the extracted feature indices. By applying multiple convolutional kernels and using the ReLU activation function, a nonlinear relationship is introduced, enabling the model to fit complex feature relationships. The output layer contains an independent neuron that is responsible for converting the feature index representation extracted by the hidden layer into the final prediction result, i.e., the output crack risk level index.

[0028] Furthermore, the crack risk correction coefficient is calculated using the characteristic index of the concrete cracks to be evaluated and the crack risk correction factor. The method used is as follows:

[0029] Obtain the construction design parameters that affect the cracking of the concrete to be assessed, and generate a crack risk correction factor based on the obtained construction design parameters. The formula used is as follows:

[0030]

[0031] Where ε represents the crack risk correction factor, C strengh The concrete strength at the current moment. The water-cement ratio of concrete at the current moment, i.e., the mass ratio of water (W) to cement (J) in the concrete, T diff T represents the concrete temperature difference during the current monitoring period, i.e., the maximum temperature change that occurs in the concrete during construction. limit The critical temperature of the concrete used in construction is determined according to the design specifications.

[0032] The characteristic index of the concrete cracks to be evaluated is obtained. The crack risk correction factor is then combined with the characteristic index of the concrete cracks to be evaluated to generate a crack risk correction coefficient. The formula used is as follows:

[0033]

[0034] Where FX represents the crack risk correction factor.

[0035] Furthermore, the method used to determine the final risk level index of the concrete cracks to be assessed is as follows:

[0036] The concrete crack risk prediction model outputs crack risk level indicators including mild risk, moderate risk, and severe risk, and establishes a correction threshold range [Y] based on a correction adjustment mechanism. min ,Y max The generated crack risk correction coefficient FX is compared with the established correction threshold range, and combined with the output crack risk level index, when FX∈[Y] min ,Y max When FX > Y, the current risk index of the concrete cracks to be evaluated will be used as the final risk index; when FX > Y max The output of the current risk index for concrete cracks to be assessed is raised one level to become the final index; when FX <Y min The output risk index of the current concrete crack to be evaluated will be downgraded by one level as the final index; when the risk index of the current concrete crack to be evaluated output by the model is of severe risk, it is determined that no upgrade operation is required; when the risk index of the current concrete crack to be evaluated output by the model is of mild risk, it is determined that no downgrade operation is required.

[0037] The present invention also provides a system for assessing cracks in large-volume concrete for wind turbine foundations, the system being used to perform the above-described method for assessing cracks in large-volume concrete for wind turbine foundations, comprising:

[0038] The crack monitoring and acquisition module is used to collect data on the concrete foundation of the wind turbine to be evaluated and multiple control wind turbine foundations during the current monitoring period, so as to obtain characteristic parameters for characterizing the surface cracks of each wind turbine foundation concrete. The characteristic parameters include crack width, crack length, crack depth, average spacing between cracks, crack propagation rate and total number of cracks.

[0039] The crack characteristic index calculation module is used to obtain characteristic indices based on characteristic parameters to characterize the crack status of the concrete surface of the corresponding wind turbine foundation. The characteristic indices include crack hazard index, crack influence index and crack propagation index. The characteristic indices of the control wind turbine foundation concrete are evaluated based on expert scoring to determine its crack risk level index, which includes mild risk, moderate risk and severe risk.

[0040] The risk prediction model construction module is used to construct a concrete crack risk prediction model based on a deep learning network, with the input being a feature index and the output being a crack risk level index. The model is trained based on the feature index and crack risk level index of the wind turbine foundation concrete. The feature index of the wind turbine foundation concrete to be evaluated is input into the model to obtain the corresponding crack risk level index.

[0041] The module for influencing parameters and risk correction is used to obtain the influencing parameters of concrete cracks in the wind turbine foundation. The influencing parameters include wind turbine operating load, concrete strength, water-cement ratio and temperature difference. Based on the obtained construction design parameters, a crack risk correction factor is generated, and the characteristic index of the cracks on the concrete surface to be evaluated is obtained. The crack risk correction coefficient is calculated using the characteristic index of the cracks on the concrete surface to be evaluated and the crack risk correction factor.

[0042] The risk level correction mechanism module is used to establish a correction adjustment mechanism, which compares the crack risk correction coefficient of the concrete crack to be evaluated with a preset correction threshold range, and corrects the crack risk level index according to the comparison result to determine the final risk level index of the concrete crack to be evaluated.

[0043] Compared with the prior art, the beneficial effects of the present invention are:

[0044] This invention employs meticulous data collection procedures, encompassing multi-dimensional characteristic parameters such as crack width, length, depth, spacing, propagation rate, and total number, ensuring a comprehensive understanding of the crack condition in wind turbine foundation concrete. Furthermore, by introducing crack hazard index, impact index, and propagation index, combined with expert scoring for risk level assessment, it overcomes the shortcomings of traditional methods that fail to adequately consider factors influencing cracks, thereby improving the scientific rigor and accuracy of risk assessment.

[0045] Secondly, this invention employs a neural network convolutional structure to construct a concrete crack risk prediction model, enabling it to effectively capture complex feature relationships and make dynamic adjustments. A crack risk correction coefficient FX is calculated by combining a crack risk correction factor and a feature index, further introducing a correction adjustment mechanism to make risk assessment more flexible and accurate. By establishing correction threshold ranges to optimize and adjust each risk level, the reliability and practicality of the assessment results are ensured, thereby effectively improving the safety and stability of wind turbine foundation concrete and addressing the shortcomings of existing technologies in risk management. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the overall method flow of the present invention.

[0047] Figure 2 This is a statistical chart of crack characteristic data for the control group of this invention.

[0048] Figure 3 This is a statistical chart showing the crack score and grade of the control group in this invention.

[0049] Figure 4 This is a diagram showing the crack correction factor analysis of the sample to be tested in this invention.

[0050] Figure 5 This is a calibration and correction analysis diagram for the crack risk level of this invention.

[0051] Figure 6 This is a schematic diagram of the system module flow of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0053] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0054] Example:

[0055] Please see Figure 1 —5. A method for assessing cracks in large-volume concrete for wind turbine foundations, comprising the following steps:

[0056] Step 1: During the current monitoring period, data is collected on the concrete foundation of the wind turbine to be evaluated and multiple control wind turbine foundations to obtain characteristic parameters for characterizing the surface cracks of each wind turbine foundation concrete. The characteristic parameters include crack width, crack length, crack depth, average spacing between cracks, crack propagation rate, and total number of cracks.

[0057] Step 2: Based on the characteristic parameters, obtain the characteristic indices used to characterize the surface crack condition of the corresponding wind turbine foundation concrete. The characteristic indices include the crack hazard index, crack influence index, and crack propagation index. The characteristic indices of the control wind turbine foundation concrete are evaluated based on the expert scoring method to determine its crack risk level index, which includes mild risk, moderate risk, and severe risk.

[0058] Step 3: Construct a concrete crack risk prediction model based on a deep learning network, with the input being the feature index and the output being the crack risk level index. Train the model based on the feature index and crack risk level index of the wind turbine foundation concrete. Input the feature index of the wind turbine foundation concrete to be evaluated into the model to obtain the corresponding crack risk level index.

[0059] Step 4: Obtain the influencing parameters of concrete cracks in the wind turbine foundation. The influencing parameters include wind turbine operating load, concrete strength, water-cement ratio and temperature difference. Generate a crack risk correction factor based on the obtained construction design parameters, and obtain the characteristic index of cracks on the concrete surface to be evaluated. Use the characteristic index of cracks in the concrete to be evaluated and the crack risk correction factor to calculate the crack risk correction coefficient.

[0060] Step 5: Establish a correction adjustment mechanism, compare the crack risk correction coefficient of the concrete crack to be evaluated with the preset correction threshold range, and correct the crack risk level index according to the comparison results to determine the final risk level index of the concrete crack to be evaluated.

[0061] It should be noted that, based on the total number of cracks in the concrete of the same wind turbine foundation recorded within the week preceding the current moment in the monitoring period, the average length, average width, average depth, average spacing between cracks, and average concrete propagation rate of the wind turbine foundation concrete are calculated using the following formula:

[0062]

[0063]

[0064]

[0065]

[0066]

[0067] Among them, a i ′、b i ′、c i ′ represents the length, width, and depth of the i-th crack in the concrete of the same wind turbine foundation at the current moment, N is the total number of cracks in the concrete of the same wind turbine foundation at the current moment, and S i ′-S i11 ′ represents the distance between the i-th crack and the (i+1)-th crack in the same wind turbine foundation concrete at the current moment; Δa, Δb, and Δc represent the changes in the length, width, and depth of the cracks in the wind turbine foundation concrete at the current moment and the previous week, respectively, and Δt represents the change over time; i is the crack index of the same wind turbine foundation concrete at the current moment, and i∈[1,N].

[0068] a, b, c, S, and v are the average length, average width, average depth, average spacing between cracks, and average concrete propagation rate of the wind turbine foundation concrete, which are used as parameters in the calculation formula.

[0069] In the data table of the wind turbine foundation concrete samples, data were collected from 30 control wind turbine foundation concrete samples and processed using the above calculation formula to obtain the average length, average width, average depth, average spacing between cracks, and average concrete propagation rate of the wind turbine foundation concrete cracks. The processing of average values ​​eliminated the problem of data anomalies in individual control wind turbine foundation concrete samples. The calculated average length, width, depth, spacing, and propagation rate were then summarized to form a data report.

[0070]

[0071]

[0072] Table 1 - Comparison of Concrete Samples for Wind Turbine Foundations

[0073] It should be noted that the formulas for calculating crack characteristic indices are of great significance in the assessment of cracks in large-volume concrete of wind turbine foundations. These indices provide a systematic and quantitative way to evaluate the hazard, impact, and propagation trend of cracks. By comprehensively calculating the crack hazard index, crack impact index, and crack propagation index, the condition of the cracks and their potential threat to structural safety can be objectively reflected. This index-based assessment method, based on characteristic parameters, not only improves the scientific rigor and accuracy of crack monitoring but also provides engineers with clear decision-making support, enabling timely maintenance and reinforcement measures to effectively extend the service life of concrete structures and ensure the overall safety of wind turbine foundations.

[0074] Therefore, it is necessary to calculate and generate characteristic indices that characterize the crack condition, and the method used is as follows:

[0075] The crack hazard index is calculated based on the characteristic parameters of cracks on the concrete surface, namely crack width, crack length, and crack depth. The formula used is as follows:

[0076]

[0077] Where a, b, and c represent the crack width, crack length, and crack depth of the same wind turbine foundation concrete, respectively, and CHI represents the corresponding crack hazard index of the wind turbine foundation concrete. In the above formula, increasing the crack width a, crack length b, and crack depth c will all lead to an increase in the crack hazard index CHI. An increase in crack width usually indicates a deterioration in the stress condition of the concrete structure or material fatigue, which may lead to a decrease in the load-bearing capacity of the structure. Wider cracks may allow moisture and corrosive substances to seep in, further worsening the condition of the concrete and thus negatively impacting the safety of the overall structure. An increase in crack length usually means that the crack has spread more widely in the structure, which may indicate increased material fatigue or damage, leading to greater structural weaknesses. Concrete structures are more prone to failure under external loads, increasing the risk of damage. Increased crack depth often indicates that the crack has penetrated into the concrete, potentially leading to more severe structural damage. This further increases the risk of moisture and corrosive substances intruding, which in turn affects the reinforcing steel or other internal structures. Deeper cracks suggest that the concrete's load-bearing capacity may be significantly affected, indicating that the concrete material has been damaged or has lost its supporting capacity. Especially in cases of greater depth, cracks may trigger more severe structural failures. Therefore, an increased CHI indicates an increase in the potential risks and hazards of the concrete structure, implying higher maintenance and repair requirements. In other words, a lower CHI is better, indicating a better condition and higher safety for the concrete structure.

[0078] The crack influence index is calculated by combining the crack width and crack depth, characteristic parameters of concrete surface cracks, with the average spacing between cracks and the total number of cracks. The formula used is as follows:

[0079]

[0080] Where N represents the total number of cracks in the same wind turbine foundation concrete, S represents the average spacing between cracks in the same wind turbine foundation concrete, and CII represents the crack impact index of the corresponding wind turbine foundation concrete. In the above formula, an increase in the total number of cracks N will increase the CII, meaning that more cracks are observed in the concrete foundation, which usually leads to a deterioration in the overall health of the structure. Multiple cracks indicate potential design flaws, material fatigue, or external influences such as load changes and temperature variations. Increasing a and c will also increase the CII. When both the average width and average depth of the cracks increase, the increased width increases the cross-sectional area of ​​the cracks, potentially leading to a decrease in local bearing capacity at stress concentration points, while the increased depth means that these cracks may affect the bond strength between deeper layers of concrete and steel reinforcement, creating a double risk. An increase in S will decrease the CII, meaning that the average spacing between cracks increases. This usually indicates a sparser distribution of cracks, indicating fewer cracks observed over a relatively large area, thus reducing the impact of the cracks. This usually indicates a relatively good structural health; therefore, a smaller CII is better, indicating a better structural health and lower risk.

[0081] The crack propagation index is calculated using the characteristic parameters of cracks on the concrete surface, namely crack propagation rate, crack width, and crack length. The formula used is as follows:

[0082]

[0083] Where v is the crack propagation rate of the same wind turbine foundation concrete, and CPII represents the corresponding crack propagation index of the wind turbine foundation concrete; in the above formula, an increase in the crack propagation rate v leads to an increase in the crack propagation index CPII, meaning that the faster the crack propagates, the greater the potential risk to the structure. A high propagation rate usually indicates that the material or structure is experiencing more severe fatigue, stress, or external influences; in the calculation, due to the square of the crack width a 2 Magnification and increased width significantly increase the CPII value, indicating a more severe crack condition. Wide cracks can allow more moisture and contaminants to penetrate the concrete, accelerating structural degradation. Wide cracks generally signify higher risk, potentially leading to reduced concrete load-bearing capacity and increased susceptibility to environmental impacts; the square of the crack length (b) 2 Amplified, an increase in crack length will also lead to a significant increase in CPII, because a longer crack indicates a greater depth and extent of crack development, affecting more structural areas. Long cracks may make the structure more vulnerable and increase the risk of structural failure, especially when the crack connects to critical load-bearing parts. Therefore, the smaller the CPII, the better, indicating that the crack propagation of the concrete structure is less severe and the safety is higher.

[0084] It should be noted that by employing a model with a neural network convolutional structure, crack feature indices can be effectively extracted and processed, thereby capturing complex nonlinear relationships and achieving more accurate crack risk level predictions. This method not only improves the ability to identify crack development trends but also helps to detect potential risks in advance, guiding maintenance and repair decisions, thus ensuring the safety and service life of structures and reducing economic losses and safety accidents.

[0085] Therefore, it is necessary to establish a concrete crack risk prediction model to predict the crack risk level index. The method used is as follows:

[0086] The concrete crack risk prediction model adopts a neural network convolutional structure, including an input layer, a hidden layer, and an output layer. The input layer is responsible for receiving the extracted feature indices that characterize the crack condition. The hidden layer is used to process the extracted feature indices. By applying multiple convolutional kernels and using the ReLU activation function, a nonlinear relationship is introduced, enabling the model to fit complex feature relationships. The output layer contains an independent neuron that is responsible for converting the feature index representation extracted by the hidden layer into the final prediction result, i.e., the output crack risk level index.

[0087] The model obtains characteristic indices representing crack conditions from historical data after survey and evaluation. Construction engineers assess the concrete crack conditions and classify them into mild, moderate, and severe risks. These characteristic indices are used as input to the model, while the crack risk level index is used as the model's output label. The concrete crack risk prediction model is then trained. During training, the mean squared error function is selected as the loss function. The loss function value is calculated based on the output results and the true labels. The gradient is calculated using the backpropagation algorithm, and the weights and biases of the neural network are updated. This process is repeated until the model reaches the predetermined number of training rounds.

[0088] The characteristic index calculation table for crack conditions on the concrete surface of wind turbine foundations calculates the crack hazard index, crack influence index, and crack propagation index. By employing a neural network convolutional structure to effectively extract and classify the characteristic indices of crack conditions, accurate prediction and assessment of concrete crack risk can be achieved. This helps engineers identify and respond to potential safety hazards in a timely manner, improving the safety and reliability of the structure. It is also clearly visible that a crack hazard index exceeding 30 is often accompanied by a severe risk indicator. The chart shows that the scoring range for mild risk is (0, 8], for severe risk is (8, 15], and for critical risk is (15, 18]. This classification helps engineers and managers more effectively identify and respond to concrete crack risks in practical operations. By calculating the specific values ​​of the characteristic indices and using a scoring mechanism, the specific condition of the cracks can be quickly determined.

[0089]

[0090]

[0091] Table 2 - Calculation of Characteristic Indices for Crack Conditions on Concrete Surface of Wind Turbine Foundations

[0092] It should be noted that by considering construction design parameters such as wind turbine operating load, concrete strength, water-cement ratio, and temperature variations, the potential risks of cracks can be assessed more comprehensively, thereby generating a more accurate risk correction coefficient. This coefficient not only integrates multiple influencing factors and reflects the performance of concrete under actual service conditions, but also provides a scientific basis for subsequent risk management and maintenance decisions. It helps to promptly detect and address crack problems, extend the service life of the structure, and ensure the safety of the project.

[0093] Therefore, it is necessary to use the characteristic index of the concrete cracks to be evaluated and the crack risk correction factor to calculate the crack risk correction coefficient. The method used is as follows:

[0094] Obtain the construction design parameters that affect the cracking of the concrete to be assessed, and generate a crack risk correction factor based on the obtained construction design parameters. The formula used is as follows:

[0095]

[0096] Where ε represents the crack risk correction factor, C strengh The concrete strength at the current moment. The water-cement ratio of concrete at the current moment, i.e., the mass ratio of water (W) to cement (J) in the concrete, T diff T represents the concrete temperature difference during the current monitoring period, i.e., the maximum temperature change that occurs in the concrete during construction. limitC is the critical temperature of the concrete used in construction, determined according to design specifications; in the above formula, C strengh and An increase in T and a decrease in ε indicate that the concrete material used for wind turbine foundations has good performance, strong shear and bending moment resistance, and is less prone to cracking; diff A smaller ε indicates a smaller temperature difference, meaning the concrete has a higher water solubility and can withstand the negative effects of extreme temperatures, meaning the concrete will not crack due to temperature changes. The smaller the crack risk correction factor ε, the higher the construction quality of the concrete used for wind turbine foundations, and the less likely it is to crack.

[0097] The characteristic index of the concrete cracks to be evaluated is obtained. The crack risk correction factor is then combined with the characteristic index of the concrete cracks to be evaluated to generate a crack risk correction coefficient. The formula used is as follows:

[0098]

[0099] Wherein, FX represents the crack risk correction coefficient. In the above formula, an increase in the three indices CHI, CII, and CPII will lead to an increase in FX, which means that the risk and potential hazards of the concrete structure are increased. Therefore, the crack risk correction coefficient should be as small as possible to indicate that the crack risk is low and the health of the concrete structure is good. In the above formula, CHI further affects FX through an exponential function. The exponential function increases with the increase of CHI and is suitable for describing the significant impact of crack width, depth, etc. on structural safety. The more severe the crack, the greater its contribution, thus significantly increasing FX. Using a logarithmic function for the crack impact index CII can effectively buffer its growth rate, preventing excessive weighting of FX when the crack's impact is small. The logarithmic function ln(1+CII) can indirectly reflect the crack's impact on the overall structural performance. In practical engineering, the crack impact index CII may be small in some cases. Directly linearly superimposing or amplifying it, such as using an exponential or square function, may lead to an overestimation of the impact of small cracks on FX, resulting in unreasonable risk assessment results. The crack propagation index CPII describes the crack propagation rate. The square function design emphasizes the weighting of the propagation rate on risk. The faster the crack propagation rate, the more significant the harm to the overall stability of the concrete, thus requiring a higher risk weight. Therefore, a smaller FX is better, meaning a lower risk of concrete crack formation, with crack width, depth, and propagation rate all within a small or controllable range. It also indirectly reflects the relatively small impact of external loads on the concrete structure and material properties during construction, such as concrete strength, water-cement ratio, and temperature changes, indicating good construction quality.

[0100] It should be noted that by comparing the crack risk correction coefficient with a set correction threshold range, the severity of the crack condition can be accurately assessed, ensuring that appropriate measures are taken at the appropriate risk level. This process, through a reasonable adjustment mechanism, ensures both flexibility and rigor in risk assessment, avoiding safety hazards caused by misjudgments of risk levels, thereby effectively extending the service life of concrete structures and protecting people's lives and property.

[0101] Therefore, it is necessary to determine the final risk level index of the concrete cracks to be assessed, and the method used is as follows:

[0102] The concrete crack risk prediction model outputs crack risk level indicators including mild risk, moderate risk, and severe risk, and establishes a correction threshold range [Y] based on a correction adjustment mechanism. min ,Y max The generated crack risk correction coefficient FX is compared with the established correction threshold range, and combined with the output crack risk level index, when FX∈[Y] min ,Y max When FX > Y, the current risk index of the concrete cracks to be evaluated will be used as the final risk index; when FX > Y max The output of the current risk index for concrete cracks to be assessed is raised one level to become the final index; when FX <Y min The output risk index of the current concrete crack to be evaluated will be downgraded by one level as the final index; when the risk index of the current concrete crack to be evaluated output by the model is of severe risk, it is determined that no upgrade operation is required; when the risk index of the current concrete crack to be evaluated output by the model is of mild risk, it is determined that no downgrade operation is required.

[0103] exist Figure 3 The statistical chart of crack characteristics in the control group shows that different samples exhibit fluctuations. The crack height, width, and depth data of different samples show significant fluctuations, indicating that the crack condition varies greatly among different samples. The purpose of selecting multiple control wind turbine foundation concrete samples is to compare the crack height, width, and depth of different samples. This allows for the analysis of the impact of environmental factors, construction technology, and material mix proportions on concrete crack characteristics, identification of potential risk factors, and analysis of crack indices of different samples. This helps to identify samples with higher risks and then take targeted maintenance and repair measures to extend the service life of concrete structures.

[0104] exist Figure 4The crack score and grade statistics chart for the control group shows the statistical results of expert scores and corresponding crack risk grade indicators for different samples. The chart reveals significant fluctuations between expert scores and crack risk grade indicators, reflecting substantial differences in crack conditions among different samples. The changes in expert scores correspond to fluctuations in crack risk grades, demonstrating the direct impact of crack severity on expert assessment results. Figure 3 Data shows that the expert score is positively correlated with the width, depth, propagation rate, length, number, and average spacing of concrete cracks. As the crack width, depth, propagation rate, length, and number increase, the expert score also rises accordingly, indicating that the potential risks and hazards of cracks to concrete structures are increasing. This positive correlation not only reflects the impact of crack development on concrete performance but also provides engineers with direct evidence in practical applications, helping to identify and address potential safety hazards in a timely manner. By comparing crack indices of different samples, engineers can effectively formulate maintenance and reinforcement measures, thereby extending the service life of concrete structures and ensuring the overall safety of wind turbine foundations.

[0105] exist Figure 5 The crack risk correction factor analysis chart for the samples under test shows the statistical situation of crack risk correction factors for different samples. According to the data in the chart, the crack risk correction factor values ​​fluctuate between 0.70 and 0.86, reflecting the differences in crack risk assessment among different samples. When the crack risk correction factor value is high, close to 0.86, it indicates that the concrete construction quality is good, the material properties are strong, and the crack resistance is good, meaning that under the corresponding construction design parameters, the concrete is not prone to cracking. When the value is low, close to 0.70, it indicates that the concrete has deficiencies in strength, water-cement ratio, temperature difference, etc., and there is a risk of cracking. These fluctuating data not only reflect the differences in the actual performance of concrete in different samples, but also have a direct relationship with the characteristic index of cracks in the concrete under assessment. By combining this information, engineers can gain a more comprehensive understanding of the concrete condition and formulate corresponding maintenance and reinforcement measures to ensure the safety and durability of the wind turbine foundation.

[0106] exist Figure 6The crack risk level calibration and correction analysis chart shows the comparison between the initial and final risk levels of different samples. The comparison reveals that, based on the upgrade and downgrade mechanism, some samples exhibit changes between their initial and final risk levels. This reflects the assessment decisions made by comparing the crack risk correction coefficient with a set correction threshold range. For most samples, the final risk level remains consistent with the initial risk level; however, in some samples, the final level is adjusted upwards or downwards, demonstrating the flexibility and rigor of the assessment mechanism. This process ensures that appropriate measures are taken at the appropriate risk level, contributing to the effective extension of the service life of concrete structures.

[0107] Please see Figure 6 The present invention also provides a system for assessing cracks in large-volume concrete for wind turbine foundations. This system is used to perform the aforementioned method for assessing cracks in large-volume concrete for wind turbine foundations, comprising:

[0108] A crack monitoring and acquisition module is used to collect characteristic parameters of concrete surface cracks during the use of multiple wind turbine foundation concrete. The characteristic parameters of concrete surface cracks include crack width, crack length, crack depth, average spacing between cracks, crack propagation rate, and total number of cracks.

[0109] The crack characteristic index calculation module is used to calculate and generate characteristic indices that characterize the crack condition based on the obtained characteristic parameters of cracks on the concrete surface. The characteristic indices that characterize the crack condition include crack hazard index, crack influence index and crack propagation index.

[0110] The risk prediction model construction module is used to establish a concrete crack risk prediction model. It evaluates each set of feature indices based on expert scoring and generates corresponding crack risk level indicators as labels. The model adopts a convolutional neural network model structure and trains the model based on the feature indices of historical concrete surface cracks. The generated feature indices are input into the trained concrete crack risk prediction model to determine the indicators of the concrete to be evaluated. The crack risk level indicators include mild risk, moderate risk, and severe risk.

[0111] The construction parameters and risk correction module is used to obtain the construction design parameters that affect the cracks in the concrete to be evaluated. The construction design parameters include the wind turbine operating load, concrete strength, water-cement ratio and temperature difference. Based on the obtained construction design parameters, a crack risk correction factor is generated, and the characteristic index of the cracks in the concrete to be evaluated is obtained. The crack risk correction coefficient is calculated using the characteristic index of the cracks in the concrete to be evaluated and the crack risk correction factor.

[0112] The risk level correction mechanism module is used to establish a correction adjustment mechanism, which compares the crack risk correction coefficient of the concrete crack to be evaluated with a preset correction threshold range, and corrects the crack risk level index according to the comparison result to determine the final risk level index of the concrete crack to be evaluated.

[0113] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0114] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0116] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for assessing cracks in large-volume concrete for wind turbine foundations, characterized in that, The specific steps include: Step 1: During the current monitoring period, data is collected on the concrete foundation of the wind turbine to be evaluated and multiple control wind turbine foundations to obtain characteristic parameters for characterizing the surface cracks of each wind turbine foundation concrete. The characteristic parameters include crack width, crack length, crack depth, average spacing between cracks, crack propagation rate, and total number of cracks. Step 2: Based on the characteristic parameters, obtain the characteristic indices used to characterize the surface crack condition of the corresponding wind turbine foundation concrete. The characteristic indices include the crack hazard index, crack influence index, and crack propagation index. The characteristic indices of the control wind turbine foundation concrete are evaluated based on the expert scoring method to determine its crack risk level index, which includes mild risk, moderate risk, and severe risk. Step 3: Construct a concrete crack risk prediction model based on a deep learning network, with the input being the feature index and the output being the crack risk level index. Train the model based on the feature index and crack risk level index of the wind turbine foundation concrete. Input the feature index of the wind turbine foundation concrete to be evaluated into the model to obtain the corresponding crack risk level index. Step 4: Obtain the influencing parameters of concrete cracks in the wind turbine foundation. The influencing parameters include wind turbine operating load, concrete strength, water-cement ratio and temperature difference. Generate a crack risk correction factor based on the obtained construction design parameters, and obtain the characteristic index of cracks on the concrete surface to be evaluated. Use the characteristic index of cracks in the concrete to be evaluated and the crack risk correction factor to calculate the crack risk correction coefficient. Step 5: Establish a correction adjustment mechanism, compare the crack risk correction coefficient of the concrete crack to be evaluated with the preset correction threshold range, and correct the crack risk level index according to the comparison results to determine the final risk level index of the concrete crack to be evaluated.

2. The method for assessing cracks in large-volume concrete for wind turbine foundations according to claim 1, characterized in that, Based on the characteristic parameters, characteristic indices are obtained to characterize the surface crack condition of the corresponding wind turbine foundation concrete. These indices include a crack hazard index, a crack influence index, and a crack propagation index. The method used is as follows: The crack hazard index is calculated using the characteristic parameters of cracks on the concrete surface, namely crack width, crack length, and crack depth, based on the following formula: Where a, b, and c represent the crack width, crack length, and crack depth of the same wind turbine foundation concrete, respectively, and CHI represents the crack hazard index of the corresponding wind turbine foundation concrete. The crack influence index is calculated using the characteristic parameters of concrete surface cracks, including crack width and crack depth, combined with the average spacing between cracks and the total number of cracks. The formula used is as follows: Where N is the total number of cracks in the same wind turbine foundation concrete, S is the average spacing between cracks in the same wind turbine foundation concrete, and CII represents the crack influence index of the corresponding wind turbine foundation concrete. The crack propagation index is calculated using the characteristic parameters of cracks on the concrete surface, namely crack propagation rate, crack width, and crack length, based on the following formula: Where v is the crack propagation rate of the same wind turbine foundation concrete, and CPII represents the crack propagation index of the corresponding wind turbine foundation concrete.

3. The method for assessing cracks in large-volume concrete for wind turbine foundations according to claim 1, characterized in that, A concrete crack risk prediction model is constructed based on a deep learning network, taking feature indices as input and outputting crack risk level indicators. The method used to predict crack risk level indicators is as follows: The concrete crack risk prediction model adopts a neural network convolutional structure, including an input layer, a hidden layer, and an output layer. The input layer is responsible for receiving the extracted feature indices that characterize the crack condition. The hidden layer is used to process the extracted feature indices. By applying multiple convolutional kernels and using the ReLU activation function, a nonlinear relationship is introduced, enabling the model to fit complex feature relationships. The output layer contains an independent neuron that is responsible for converting the feature index representation extracted by the hidden layer into the final prediction result, i.e., the output crack risk level index.

4. The method for assessing cracks in large-volume concrete for wind turbine foundations according to claim 2, characterized in that, The crack risk correction coefficient is calculated using the characteristic index of the concrete cracks to be evaluated and the crack risk correction factor. The method used is as follows: Obtain the construction design parameters that affect the cracking of the concrete to be assessed, and generate a crack risk correction factor based on the obtained construction design parameters. The formula used is as follows: Where ε represents the crack risk correction factor, C strengh The concrete strength at the current moment. The water-cement ratio of concrete at the current moment, i.e., the mass ratio of water (W) to cement (J) in the concrete, T diff T represents the concrete temperature difference during the current monitoring period, i.e., the maximum temperature change that occurs in the concrete during construction. limit The critical temperature of the concrete used in construction is determined according to the design specifications. The characteristic index of the concrete cracks to be evaluated is obtained. The crack risk correction factor is then combined with the characteristic index of the concrete cracks to be evaluated to generate a crack risk correction coefficient. The formula used is as follows: Where FX represents the crack risk correction factor.

5. The method for assessing cracks in large-volume concrete for wind turbine foundations according to claim 1, characterized in that, The method used to determine the final risk level index of the concrete cracks to be assessed is as follows: The concrete crack risk prediction model outputs crack risk level indicators including mild risk, moderate risk, and severe risk, and establishes a correction threshold range [Y] based on a correction adjustment mechanism. min ,Y max The generated crack risk correction coefficient FX is compared with the established correction threshold range, and combined with the output crack risk level index, when FX∈[Y] min ,Y max If the output of the current risk index of the concrete crack to be evaluated is used as the final risk index, then the risk index of the current concrete crack to be evaluated will be used as the final risk index. When FX>Y max The output of the current risk index for concrete cracks to be assessed is raised one level to become the final index; when FX <Y min The output risk index of the current concrete crack to be evaluated will be downgraded by one level as the final index; when the risk index of the current concrete crack to be evaluated output by the model is of severe risk, it is determined that no upgrade operation is required; when the risk index of the current concrete crack to be evaluated output by the model is of mild risk, it is determined that no downgrade operation is required.

6. A system for assessing cracks in large-volume concrete for wind turbine foundations, characterized in that, The evaluation system is used to perform the method for evaluating cracks in large-volume concrete for wind turbine foundations as described in any one of claims 1-5, including: The crack monitoring and acquisition module is used to collect data on the concrete foundation of the wind turbine to be evaluated and multiple control wind turbine foundations during the current monitoring period, so as to obtain characteristic parameters for characterizing the surface cracks of each wind turbine foundation concrete. The characteristic parameters include crack width, crack length, crack depth, average spacing between cracks, crack propagation rate and total number of cracks. The crack characteristic index calculation module is used to obtain characteristic indices based on characteristic parameters to characterize the crack status of the concrete surface of the corresponding wind turbine foundation. The characteristic indices include crack hazard index, crack influence index and crack propagation index. The characteristic indices of the control wind turbine foundation concrete are evaluated based on expert scoring to determine its crack risk level index, which includes mild risk, moderate risk and severe risk. The risk prediction model construction module is used to construct a concrete crack risk prediction model based on a deep learning network, with the input being a feature index and the output being a crack risk level index. The model is trained based on the feature index and crack risk level index of the wind turbine foundation concrete. The feature index of the wind turbine foundation concrete to be evaluated is input into the model to obtain the corresponding crack risk level index. The module for influencing parameters and risk correction is used to obtain the influencing parameters of concrete cracks in the wind turbine foundation. The influencing parameters include wind turbine operating load, concrete strength, water-cement ratio and temperature difference. Based on the obtained construction design parameters, a crack risk correction factor is generated, and the characteristic index of the cracks on the concrete surface to be evaluated is obtained. The crack risk correction coefficient is calculated using the characteristic index of the cracks on the concrete surface to be evaluated and the crack risk correction factor. The risk level correction mechanism module is used to establish a correction adjustment mechanism, which compares the crack risk correction coefficient of the concrete crack to be evaluated with a preset correction threshold range, and corrects the crack risk level index according to the comparison result to determine the final risk level index of the concrete crack to be evaluated.

Images