Steel structure building state evaluation method and system based on multi-source environment sensing data

Abstract

The application relates to a steel structure building state evaluation method and system based on multi-source environment sensing data. The method first performs multiple differential evolution processes on M groups of historical multi-source environment sensing data of a steel structure building. Any differential evolution process includes the following steps: randomly selecting a set number of historical multi-source environment sensing data from the M groups of historical multi-source environment sensing data as an initial population, performing differential evolution, obtaining an offspring population, introducing a steel structure building state factor value to assist differential evolution, capturing the nonlinear correlation between multi-source environment factors, and selecting more representative historical multi-source environment sensing data as training data of a model. Then, clustering is performed according to the offspring population to obtain multiple clustering centers. The individuals of the clustering centers are extremely representative individuals in the data clusters and have great training value. By taking the multiple clustering centers as a training data set, the accuracy of model training can be improved.

Description

Technical Field

[0001] This application relates to the field of steel structure safety assessment technology, and in particular to a method and system for assessing the condition of steel structure buildings based on multi-source environmental sensing data.

[0002] Background Technology

[0003] Steel structure buildings have become the mainstream form of modern architecture due to their high strength and recyclability. However, steel structures are subject to the coupled effects of complex factors during long-term service. Traditional assessment methods mainly focus on the direct impact of structural damage on the building's condition (such as stress and load status), while neglecting the correlation mechanism between multi-source environmental sensor data and the building's condition. In actual engineering projects, environmental parameters such as wind speed, humidity, and air pressure can indirectly change the building's stress state by affecting structural vibration characteristics, and the impact of different environmental factors on the structure varies significantly. Summary of the Invention

[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0005] The main objective of this disclosure is to propose a method for assessing the condition of steel structure buildings based on multi-source environmental sensing data, the method comprising:

[0006] Acquire M sets of historical multi-source environmental sensor data for steel structure buildings;

[0007] Multiple differential evolution processes are performed on the M sets of historical multi-source environmental sensor data. Each differential evolution process includes: randomly selecting m sets of historical multi-source environmental sensor data from the M sets as an initial population, and performing differential evolution to obtain a descendant population; where each individual in the population represents a set of historical multi-source environmental sensor data; the fitness value of each individual in the differential evolution is determined based on the difference between a first value and a second value, where the second value is the individual's predicted value for the steel structure building's state factors, and the first value is the actual value of the steel structure building's state factors; m is less than M, and m is a positive integer greater than 1.

[0008] Cluster the offspring population obtained from each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1.

[0009] K cluster centers are used as the training dataset, and the steel structure building condition prediction model is trained based on the training dataset to obtain the trained steel structure building condition prediction model.

[0010] Based on the trained steel structure building state prediction model, the current steel structure building state is evaluated.

[0011] This disclosure provides a method for assessing the condition of steel structure buildings based on multi-source environmental sensor data, which has at least the following beneficial effects:

[0012] This method first acquires M sets of historical multi-source environmental sensor data for steel structure buildings. To capture the nonlinear correlations among multi-source environmental factors and select more representative training data, multiple differential evolution processes are performed on the M sets of historical multi-source environmental sensor data for steel structure buildings. Each differential evolution process includes randomly selecting a set number of historical multi-source environmental sensor data sets from the M sets as the initial population and performing differential evolution to obtain the offspring population. The fitness value of an individual is calculated based on the difference between the actual value of the steel structure building's state factors and the individual's predicted value of the steel structure building's state factors. Introducing the numerical value of the steel structure building's state factors assists in the selection of historical multi-source environmental sensor data through differential evolution, because the state factors of the steel structure building... State factors directly affect the state of steel structure buildings. Therefore, introducing this parameter to assist in screening allows for the selection of more representative historical multi-source environmental sensor data as training data for the model, thereby improving the accuracy of model training. Then, by clustering the offspring population obtained from each differential evolution process, multiple cluster centers are obtained. After clustering, multiple data clusters are obtained. The individuals serving as cluster centers are highly representative individuals within their respective data clusters and have significant training value. By using the core points from multiple data clusters as the training dataset, the accuracy of model training can be improved. Finally, based on the trained steel structure building state prediction model, the current state of the steel structure building is evaluated, resulting in a more accurate assessment.

[0013] In some embodiments, the fitness value is calculated using the following function:

[0014] ;

[0015] ;

[0016] in, For individuals fitness value, As weight, For individuals The Euclidean distance between the individual with the higher fitness value and the closest proximity. This represents the actual value of the state factor for steel structure buildings. For individual Predicted numerical values ​​for the state factors of steel structure buildings. It is a logarithmic function with base 10. for 2-norm.

[0017] In some embodiments, the process of obtaining predicted values ​​of steel structure building state factors based on the individual includes:

[0018] Based on a set of historical multi-source environmental sensor data corresponding to the individual, the historical environmental characteristic value of the individual is calculated;

[0019] Based on the regression model, the predicted values ​​of the steel structure building status factors corresponding to the historical environmental characteristic values ​​are calculated; wherein, the regression model has a mapping relationship between the historical environmental characteristic values ​​and the corresponding values ​​of the steel structure building status factors.

[0020] In some embodiments, a set of historical multi-source environmental sensor data includes: historical wind speed sensor data, historical humidity sensor data, and historical air pressure sensor data.

[0021] In some embodiments, the steel structure building state factor is a vibration factor.

[0022] In some embodiments, clustering the offspring population obtained from each differential evolution process includes:

[0023] K-means clustering is performed on the offspring population obtained from each differential evolution process.

[0024] In some embodiments, the steel structure building state prediction model is a gated recurrent neural network;

[0025] The step of evaluating the current steel structure building status based on the trained steel structure building status prediction model includes:

[0026] The current multi-source environmental sensing data of the steel structure building is input into the trained steel structure building state prediction model to obtain the current steel structure building state output by the trained steel structure building state prediction model.

[0027] A second aspect of this application proposes a steel structure building condition assessment system based on multi-source environmental sensing data, the system comprising:

[0028] The data acquisition module is used to acquire M sets of historical multi-source environmental sensor data for steel structure buildings;

[0029] The differential evolution module is used to perform multiple differential evolution processes on the M sets of historical multi-source environmental sensing data. Each differential evolution process includes: randomly selecting m sets of historical multi-source environmental sensing data from the M sets as an initial population, and performing differential evolution to obtain a descendant population; wherein each individual in the population represents a set of historical multi-source environmental sensing data; the fitness value of each individual in the differential evolution is determined based on the difference between a first value and a second value, where the second value is the individual's predicted value for the steel structure building state factor, and the first value is the actual value of the steel structure building state factor; m is less than M, and m is a positive integer greater than 1.

[0030] The population clustering module is used to cluster the offspring population obtained in each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1.

[0031] The model training module is used to use K cluster centers as training datasets and train the steel structure building state prediction model based on the training datasets to obtain the trained steel structure building state prediction model.

[0032] The state prediction module is used to evaluate the current state of the steel structure building based on the trained steel structure building state prediction model.

[0033] A third aspect of this application provides an electronic device, including at least one controller and a memory for communicatively connecting to the at least one controller; the memory stores instructions executable by the at least one controller, which, when executed by the controller, cause the controller to perform the steel structure building condition assessment method based on multi-source environmental sensing data as described in the first aspect.

[0034] A fourth aspect of this application provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the steel structure building condition assessment method based on multi-source environmental sensor data as described above.

[0035] It is understood that the beneficial effects of the second to fourth aspects compared with the related technologies are the same as the beneficial effects of the first aspect compared with the related technologies. Please refer to the relevant description in the first aspect above, which will not be repeated here. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating an embodiment of a steel structure building condition assessment method based on multi-source environmental sensing data provided in this application.

[0038] Figure 2 This is a structural schematic diagram of an embodiment of a steel structure building condition assessment system based on multi-source environmental sensing data provided in this application;

[0039] Figure 3 This is a schematic diagram of an embodiment of an electronic device provided in this application. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0041] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0043] like Figure 1 One embodiment of this application provides a method for assessing the condition of steel structure buildings based on multi-source environmental sensing data, the method comprising the following steps S110 to S150:

[0044] Step S110: Obtain M sets of historical multi-source environmental sensor data for the steel structure building.

[0045] In this step, a set of historical multi-source environmental sensor data refers to multi-source environmental sensor data collected at a certain moment. M sets of historical multi-source environmental sensor data refer to multi-source environmental sensor data collected at M different moments. A set of multi-source environmental sensor data refers to environmental sensor data of multiple types, such as atmospheric pressure data collected by a barometric pressure sensor, humidity data collected by a humidity sensor, and wind speed data collected by a wind speed sensor.

[0046] In practical engineering, environmental parameters such as wind speed, humidity, and air pressure can indirectly change the state of steel structure buildings (such as stress and load state) by affecting structural vibration characteristics. Therefore, this implementation screens historical multi-source environmental sensing data to select representative historical multi-source environmental sensing data as training data to explore the relationship between multi-source environmental sensing data and the state of steel structure buildings.

[0047] Furthermore, the set of historical multi-source environmental sensor data corresponding to an individual includes: historical wind speed sensor data, historical humidity sensor data, and historical air pressure sensor data.

[0048] 1) Historical wind speed sensing data refers to the time-series measurement values ​​of the air flow speed in the building's environment, collected by wind speed sensors. Specifically, it can be achieved using an ultrasonic anemometer or a mechanical anemometer.

[0049] 2) Historical humidity sensing data refers to the time-series measurement values ​​of water vapor content in the ambient air of a building, collected by a humidity sensor. Specifically, it can be achieved using capacitive or resistive humidity sensors.

[0050] 3) Historical air pressure sensing data refers to the time-series measurement values ​​of the atmospheric pressure of the building's environment collected by air pressure sensors. Specifically, piezoelectric or piezoresistive sensors can be used.

[0051] Specifically, in constructing a condition assessment model for steel structure buildings, it is necessary to select core factors that significantly influence the condition of steel structure buildings from multi-dimensional environmental parameters. During the data acquisition phase, wind speed sensors can be deployed outside the building, humidity sensors can be installed at steel structure connections, and air pressure sensors can be deployed inside the building to form a multi-source monitoring network. The sensors continuously record environmental data at a fixed sampling frequency (e.g., once per second), and after data cleaning, a timestamped structured dataset is formed, which serves as the input for the subsequent differential evolution process.

[0052] Compared to existing technologies, this solution integrates three types of heterogeneous sensor data—wind speed, humidity, and air pressure—to capture the nonlinear correlations between environmental factors. For example, sudden changes in air pressure under high humidity conditions can exacerbate fatigue damage to steel components, and strong winds combined with humidity fluctuations can trigger resonance effects. Such complex effects cannot be effectively identified using a single data dimension. This application can establish a multidimensional correlation model between environmental parameters and the state of steel structures, solving the prediction bias problem caused by incomplete coverage of environmental factors in existing technologies. For instance, in typhoon-prone areas, considering the data combination of sudden wind speed changes and sudden increases in humidity can more accurately predict the risk of loosening at steel structure connection nodes. This multi-source data fusion mechanism enhances the environmental adaptability of the condition assessment model, giving the prediction results higher engineering reference value.

[0053] Step S120: Perform multiple differential evolution processes on M sets of historical multi-source environmental sensing data. Each differential evolution process includes: randomly selecting m sets of historical multi-source environmental sensing data from the M sets of historical multi-source environmental sensing data as the initial population, and performing differential evolution to obtain the offspring population; where each individual in the population is a set of historical multi-source environmental sensing data; the fitness value of each individual in the differential evolution is determined based on the difference between a first value and a second value, where the second value is the predicted value of the steel structure building state factor based on the individual, and the first value is the actual value of the steel structure building state factor; m is less than M, and m is a positive integer greater than 1.

[0054] In this step, to capture the nonlinear correlations between environmental factors and select more representative training data, a global optimization algorithm—differential evolution—is used to dynamically adjust the search direction and retain globally optimal information. Differential evolution is an optimization algorithm based on swarm intelligence, specifically using mutation, crossover, and selection operations to iteratively generate a high-quality population for selecting combinations of environmental data sensitive to building conditions. Fitness value calculation is a quantitative indicator that evaluates the predictive ability of individual data on building conditions.

[0055] In addition, this embodiment also introduces numerical-assisted differential evolution of steel structure building state factors (such as vibration factors) to screen historical multi-source environmental sensing data. Since steel structure building state factors can directly affect the state of steel structure buildings, the introduction of this parameter to assist in screening can select more representative historical multi-source environmental sensing data as training data for the model, thereby improving the accuracy of model training.

[0056] Step S130: Cluster the offspring population obtained from each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1.

[0057] In the steps, the offspring population obtained from each differential evolution process is clustered to obtain multiple cluster centers. After clustering, multiple data clusters are obtained. The individuals that serve as cluster centers are highly representative individuals in the corresponding data clusters and have significant training value. By using the core points in multiple data clusters as the training dataset, the accuracy of model training can be improved.

[0058] Step S140: Use K cluster centers as training datasets, and train the steel structure building condition prediction model based on the training datasets to obtain the trained steel structure building condition prediction model.

[0059] Step S150: Evaluate the current state of the steel structure building based on the trained steel structure building state prediction model.

[0060] The beneficial effects of the steel structure building condition assessment method based on multi-source environmental sensing data provided in this application include:

[0061] This method first acquires M sets of historical multi-source environmental sensor data for steel structure buildings. To capture the nonlinear correlations among multi-source environmental factors and select more representative training data, multiple differential evolution processes are performed on the M sets of historical multi-source environmental sensor data for steel structure buildings. Each differential evolution process includes randomly selecting a set number of historical multi-source environmental sensor data sets from the M sets as the initial population and performing differential evolution to obtain the offspring population. The fitness value of an individual is calculated based on the difference between the actual value of the steel structure building's state factors and the individual's predicted value of the steel structure building's state factors. Introducing the numerical value of the steel structure building's state factors assists in the selection of historical multi-source environmental sensor data through differential evolution, because the state factors of the steel structure building... State factors directly affect the state of steel structure buildings. Therefore, introducing this parameter to assist in screening allows for the selection of more representative historical multi-source environmental sensor data as training data for the model, thereby improving the accuracy of model training. Then, by clustering the offspring population obtained from each differential evolution process, multiple cluster centers are obtained. After clustering, multiple data clusters are obtained. The individuals serving as cluster centers are highly representative individuals within their respective data clusters and have significant training value. By using the core points from multiple data clusters as the training dataset, the accuracy of model training can be improved. Finally, based on the trained steel structure building state prediction model, the current state of the steel structure building is evaluated, resulting in a more accurate assessment.

[0062] Furthermore, the function for calculating the fitness value is:

[0063] ;

[0064] ;

[0065] in, For individuals fitness value As weight, For individuals The Euclidean distance between the individual with the higher fitness value and the closest proximity. This represents the actual value of the state factor for steel structure buildings. For individual Predicted numerical values ​​for the state factors of steel structure buildings. It is a logarithmic function with base 10. for 2-norm.

[0066] Among them, weight This refers to a coefficient used to adjust the proportion of the contribution of inter-individual distance and prediction error to the fitness value. Specifically, it can be implemented using a value in the range of 0.3 to 0.7. By adjusting the weights, the relationship between population diversity and model accuracy can be balanced. Distance metrics used to measure diversity information. Euclidean distance. refers to individuals The geometric distance between individuals with higher fitness in the data space can be calculated using the Euclidean norm between multidimensional sensor data vectors, to prevent the population from prematurely converging to a local optimum. This refers to the magnitude of the error vector between the true and predicted values. (Logarithmic function) This refers to a mathematical operation that performs nonlinear compression of the error magnitude to reduce the impact of abnormal errors on the fitness value.

[0067] Specifically, in the differential evolution process, each individual represents a set of historical environmental sensor data, which is mapped to predicted values ​​of steel structure state factors through a regression model. Actual value Compared with the predicted value The 2-norm error is formed after logarithmic transformation. The component reflects the prediction accuracy of this individual. Simultaneously, the minimum Euclidean distance between this individual and individuals with higher fitness in the population is calculated. The two components are used to maintain population diversity. The final fitness value is obtained by weighted fusion of these two components. It guides the population to evolve towards higher precision while avoiding the problem of insufficient search space coverage due to too many similar individuals.

[0068] Compared with existing technologies, this application can balance the dual requirements of accuracy optimization and data diversity maintenance during model training. It effectively selects high-quality samples with both prediction accuracy and data diversity during the training phase of the steel structure condition prediction model, thereby improving the reliability and generalization ability of the final steel structure building condition assessment results.

[0069] Furthermore, the predicted values ​​of the steel structure building state factors obtained in step S120 include the following steps S210 and S220:

[0070] Step S210: Calculate the historical environmental characteristic value of an individual based on a set of historical multi-source environmental sensor data corresponding to that individual.

[0071] Step S220: Based on the regression model, calculate the predicted values ​​of the steel structure building status factors corresponding to the historical environmental characteristic values; wherein, the regression model has a mapping relationship between the historical environmental characteristic values ​​and the corresponding values ​​of the steel structure building status factors.

[0072] Historical environmental characteristic values ​​refer to indicators reflecting the overall state of the environment extracted from multi-source environmental sensor data. Specifically, this can be achieved by weighting or extracting statistical measures from historical data such as wind speed, humidity, and air pressure, for example, calculating the average, variance, or peak value to characterize environmental fluctuations. Regression models are predictive tools used to establish mathematical relationships between environmental characteristics and state factors. Specifically, they can be implemented using linear regression, support vector regression, or neural network models, fitting a non-linear relationship between characteristic values ​​and actual influencing factors through training data.

[0073] Specifically, the process begins by extracting key features from a set of historical multi-source environmental sensor data corresponding to each individual building. For example, wind speed, humidity, and air pressure data at different time points are normalized and their statistical characteristics are calculated to form a multi-dimensional feature vector. This feature vector is then input into a pre-trained regression model, which outputs predicted values ​​based on the correspondence between feature values ​​in historical data and the actual influencing factors. For instance, if the condition factor for a steel structure building is a vibration factor, the regression model can predict the vibration intensity corresponding to the current environmental characteristics based on the correlation between historical environmental characteristics and vibration intensity. This process avoids noise interference problems caused by directly using raw sensor data by quantifying the complex relationship between environmental data and building condition.

[0074] This application can more accurately predict the numerical values ​​of the influence factors of environmental sensing data on the condition of steel structure buildings, providing reliable input for subsequent condition assessment. It solves the prediction bias problem caused by multi-source data redundancy and linear assumptions in the prior art, thereby improving the accuracy and reliability of building condition assessment.

[0075] Furthermore, clustering is performed based on the offspring populations obtained from each differential evolution process, including:

[0076] K-means clustering is performed on the offspring population obtained from each differential evolution process.

[0077] K-means clustering is an unsupervised machine learning method that divides data into K clusters. Specifically, it uses an iterative optimization approach to assign each data point to the nearest cluster center and update the cluster center positions. The final clustering result is determined by minimizing the within-cluster squared error. In this scheme, K-means clustering is used to group the offspring population generated by differential evolution. After generating a large number of offspring individuals through multiple differential evolutions, K-means clustering can effectively select representative data samples as the training set, reducing the impact of redundant data on model training.

[0078] After multiple differential evolution processes, the population data generated in each evolution are merged to form the overall dataset. When performing K-means clustering on this dataset, the target number of clusters needs to be set first. This number can be set according to the scale of historical data or the accuracy requirements of building condition assessment. Then, by randomly initializing cluster centroids, the Euclidean distance between each data point and each centroid is iteratively calculated. Data points are assigned to the nearest clusters, and the cluster center coordinates are recalculated until the cluster assignments no longer change or the maximum number of iterations is reached. The final set of cluster centroids can serve as the core samples of the training dataset. These samples retain the distribution characteristics of the original data while eliminating the interference of duplicate or similar data on model training.

[0079] Compared with existing technologies, this method improves model training efficiency by reducing data redundancy, while ensuring the uniform distribution of training samples in the feature space. This results in the final trained steel structure building condition prediction model having higher generalization ability and evaluation accuracy, thereby achieving accurate prediction of key indicators such as building vibration status.

[0080] Furthermore, the state prediction model for steel structure buildings is a gated recurrent neural network;

[0081] The current state of the steel structure building is assessed based on the trained steel structure building state prediction model, including:

[0082] The current multi-source environmental sensor data of the steel structure building is input into the trained steel structure building state prediction model to obtain the current steel structure building state output by the trained steel structure building state prediction model.

[0083] Among them, gated recurrent neural networks refer to recurrent neural networks with update gates and reset gates. They control the transmission and forgetting of temporal information through a gating mechanism. Specifically, they can be implemented using a bidirectional network structure with a hidden layer dimension of 64. This structure can effectively capture the temporal dependencies of multi-source environmental sensing data.

[0084] The trained steel structure building condition prediction model extracts temporal features from the input multi-source environmental sensor data using a gated recurrent neural network. The update gate calculates the information retention ratio between the current input and the previous hidden state, while the reset gate determines the degree of historical information forgetting. The model recursively processes the sensor data sequence layer by layer along the time dimension, ultimately outputting the predicted value of the steel structure vibration factor through a fully connected layer. This predicted value is mapped to the safety level assessment result of the steel structure building. For example, when the vibration factor exceeds a set threshold, the model can output a structural stability warning signal.

[0085] Compared with existing technologies, this method achieves high-precision temporal modeling of the state of steel structure buildings. The unique gating structure of the gated recurrent neural network effectively suppresses the gradient vanishing problem during long-term sequence training, enabling the model to accurately identify the impact of abrupt environmental parameter events on the building's safety status. Simultaneously, this method avoids error accumulation caused by manual feature engineering through an end-to-end prediction mechanism, significantly improving the real-time performance and reliability of steel structure health status assessment.

[0086] like Figure 2 As shown in one embodiment of this application, a steel structure building condition assessment system based on multi-source environmental sensing data is provided. The system includes:

[0087] The data acquisition module 1100 is used to acquire M sets of historical multi-source environmental sensor data of steel structure buildings.

[0088] The differential evolution module 1200 is used to perform multiple differential evolution processes on M sets of historical multi-source environmental sensing data. Each differential evolution process includes: randomly selecting m sets of historical multi-source environmental sensing data from the M sets of historical multi-source environmental sensing data as the initial population, and performing differential evolution to obtain the offspring population; where each individual in the population is a set of historical multi-source environmental sensing data; the fitness value of each individual in the differential evolution is determined based on the difference between a first value and a second value, where the second value is the predicted value of the steel structure building state factor based on the individual, and the first value is the actual value of the steel structure building state factor; m is less than M, and m is a positive integer greater than 1.

[0089] The population clustering module 1300 is used to cluster the offspring population obtained from each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1.

[0090] The model training module 1400 is used to take K cluster centers as training datasets and train the steel structure building state prediction model based on the training datasets to obtain the trained steel structure building state prediction model.

[0091] The state prediction module 1500 is used to evaluate the current state of the steel structure building based on the trained steel structure building state prediction model.

[0092] It should be noted that since the steel structure building condition assessment system based on multi-source environmental sensor data in this embodiment is based on the same inventive concept as the steel structure building condition assessment method based on multi-source environmental sensor data described above, the corresponding content in the embodiment of the steel structure building condition assessment method based on multi-source environmental sensor data is also applicable to the embodiment of the steel structure building condition assessment system based on multi-source environmental sensor data, and will not be described in detail here.

[0093] like Figure 3 As shown in the illustration, this application also provides an electronic device, which includes:

[0094] At least one memory;

[0095] At least one processor;

[0096] At least one program;

[0097] The program is stored in memory, and the processor executes at least one program to implement the above-described method for assessing the condition of steel structures based on multi-source environmental sensing data.

[0098] This electronic device can be any smart terminal, including mobile phones, tablets, personal digital assistants (PDAs), and in-vehicle computers.

[0099] The electronic devices according to embodiments of this application will now be described in detail.

[0100] The processor 1600 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0101] The memory 1700 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1700 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1700 and is called and executed by the processor 1600 to implement the steel structure building condition assessment method based on multi-source environmental sensor data of this application.

[0102] The input / output interface 1800 is used to implement information input and output.

[0103] The communication interface 1900 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0104] Bus 2000 transmits information between various components of the device (e.g., processor 1600, memory 1700, input / output interface 1800, and communication interface 1900);

[0105] The processor 1600, memory 1700, input / output interface 1800 and communication interface 1900 are connected to each other within the device via bus 2000.

[0106] This application embodiment also provides a storage medium, which is a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the above-described method for assessing the condition of steel structure buildings based on multi-source environmental sensing data.

[0107] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device.

[0108] In some implementations, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0109] The embodiments described in this application are intended to more clearly illustrate the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0110] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0111] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0112] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0113] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0114] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0116] 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; that is, 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 according to actual needs.

[0117] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0118] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0119] The above is a detailed description of the preferred embodiments of this application. However, the embodiments of this application are not limited to the above-described implementation methods. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the embodiments of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of the embodiments of this application.

Claims

1. A method for assessing the condition of steel structure buildings based on multi-source environmental sensor data, characterized in that, The method includes: Acquire M sets of historical multi-source environmental sensor data for steel structure buildings; Multiple differential evolution processes are performed on the M sets of historical multi-source environmental sensing data. Each differential evolution process includes: randomly selecting m sets of historical multi-source environmental sensing data from the M sets as the initial population, and performing differential evolution to obtain a descendant population; each individual in the population represents a set of historical multi-source environmental sensing data; the fitness value of each individual in the differential evolution is determined based on the difference between a first value and a second value, where the second value is the individual's predicted value for the steel structure building state factor, and the first value is the actual value of the steel structure building state factor; m is less than M, and m is a positive integer greater than 1; the steel structure building state factor is a vibration factor; the fitness value is calculated using the following function: ； ； in, For individuals fitness value, As weight, For individuals The Euclidean distance between the individual with the higher fitness value and the closest proximity. This represents the actual value of the state factor for steel structure buildings. For individual Predicted numerical values ​​for the state factors of steel structure buildings. It is a logarithmic function with base 10. for The 2-norm; the process of obtaining predicted values ​​of steel structure building state factors based on the individuals includes: Based on a set of historical multi-source environmental sensor data corresponding to the individual, the historical environmental characteristic value of the individual is calculated; Based on the regression model, the predicted values ​​of the steel structure building status factors corresponding to the historical environmental characteristic values ​​are calculated; wherein, the regression model has a mapping relationship between the historical environmental characteristic values ​​and the corresponding values ​​of the steel structure building status factors. Cluster the offspring population obtained from each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1. K cluster centers are used as the training dataset, and the steel structure building condition prediction model is trained based on the training dataset to obtain the trained steel structure building condition prediction model. Based on the trained steel structure building state prediction model, the current steel structure building state is evaluated.

2. The method for assessing the condition of steel structure buildings based on multi-source environmental sensor data according to claim 1, characterized in that, A set of historical multi-source environmental sensor data includes: historical wind speed sensor data, historical humidity sensor data, and historical air pressure sensor data.

3. The method for assessing the condition of steel structure buildings based on multi-source environmental sensor data according to claim 1, characterized in that, The clustering of the offspring population obtained from each differential evolution process includes: K-means clustering is performed on the offspring population obtained from each differential evolution process.

4. The method for assessing the condition of steel structure buildings based on multi-source environmental sensor data according to claim 1, characterized in that, The steel structure building state prediction model is a gated recurrent neural network; The step of evaluating the current steel structure building status based on the trained steel structure building status prediction model includes: The current multi-source environmental sensing data of the steel structure building is input into the trained steel structure building state prediction model to obtain the current steel structure building state output by the trained steel structure building state prediction model.

5. A steel structure building condition assessment system based on multi-source environmental sensor data, characterized in that, The system includes: The data acquisition module is used to acquire M sets of historical multi-source environmental sensor data for steel structure buildings; The differential evolution module is used to perform multiple differential evolution processes on the M sets of historical multi-source environmental sensing data. Each differential evolution process includes: randomly selecting m sets of historical multi-source environmental sensing data from the M sets as an initial population, and performing differential evolution to obtain a descendant population; wherein each individual in the population represents a set of historical multi-source environmental sensing data; the fitness value of each individual in the differential evolution is determined based on the difference between a first value and a second value, where the second value is the individual's predicted value for the steel structure building state factor, and the first value is the actual value of the steel structure building state factor; m is less than M, and m is a positive integer greater than 1; the steel structure building state factor is a vibration factor; the fitness value is calculated using the following function: ； ； in, For individuals fitness value, As weight, For individuals The Euclidean distance between the individual with the higher fitness value and the closest proximity. This represents the actual value of the state factor for steel structure buildings. For individual Predicted numerical values ​​for the state factors of steel structure buildings. It is a logarithmic function with base 10. for The 2-norm; the process of obtaining predicted values ​​of steel structure building state factors based on the individuals includes: Based on a set of historical multi-source environmental sensor data corresponding to the individual, the historical environmental characteristic value of the individual is calculated; Based on the regression model, the predicted values ​​of the steel structure building status factors corresponding to the historical environmental characteristic values ​​are calculated; wherein, the regression model has a mapping relationship between the historical environmental characteristic values ​​and the corresponding values ​​of the steel structure building status factors. The population clustering module is used to cluster the offspring population obtained in each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1. The model training module is used to use K cluster centers as training datasets and train the steel structure building state prediction model based on the training datasets to obtain the trained steel structure building state prediction model. The state prediction module is used to evaluate the current state of the steel structure building based on the trained steel structure building state prediction model.

6. An electronic device, characterized in that, include: At least one controller and a memory for communicatively connecting with said at least one controller; The memory stores instructions that can be executed by the at least one controller, which are executed by the controller to cause the controller to perform the steel structure building condition assessment method based on multi-source environmental sensing data as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the steel structure building condition assessment method based on multi-source environmental sensor data as described in any one of claims 1 to 4.

Images