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

Abstract

The invention relates to a multi-source environment sensing data-based steel structure building state evaluation method and system, and the method comprises the steps: firstly carrying out the multiple differential evolution processes of M groups of historical multi-source environment sensing data of a steel structure building, any difference comprises the following steps: randomly selecting a set number of groups of historical multi-source environment sensing data from M groups of historical multi-source environment sensing data as an initial population, executing differential evolution to obtain a descendant population, and capturing nonlinear correlation among multi-source environment factors by introducing numerical auxiliary differential evolution of a steel structure building state factor so as to obtain a multi-source environment sensing data set; selecting more representative historical multi-source environment sensing data as training data of the model; and then clustering is performed according to the offspring population to obtain a plurality of clustering centers, the individuals as the clustering centers are highly representative individuals in the corresponding data clusters and have relatively high training values, and the accuracy of model training can be improved by taking the plurality of clustering centers as the training data set.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of steel structure safety assessment, and in particular to a method and system for assessing the status of steel structure buildings based on multi-source environmental sensor data.

[0002] Background technology Steel structures, owing to their high strength and recyclability, have become a mainstream form of modern architecture. However, steel structures are subject to the coupling effects of complex factors during their long-term service life. Traditional assessment methods primarily focus on the direct impact of structural damage on the state of steel structures (such as stress and load conditions), while ignoring the correlation between multi-source environmental sensor data and building conditions. In actual projects, environmental parameters such as wind speed, humidity, and air pressure can indirectly alter the stress state of a building by affecting its vibration characteristics, and the impact of different environmental factors on the structure varies significantly. Summary of the Invention

[0003] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0004] The main purpose of the embodiments of the present disclosure is to propose a method for assessing the condition of a steel structure building based on multi-source environmental sensor data, the method comprising: Obtain M groups of historical multi-source environmental sensor data of the steel structure building; Performing multiple differential evolution processes on the M groups of historical multi-source environmental sensor data, wherein any one of the differential evolution processes includes: randomly selecting m groups of historical multi-source environmental sensor data from the M groups of historical multi-source environmental sensor data as an initial population, and performing differential evolution to obtain a progeny population; wherein each individual in the population is a group 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, wherein the second value is a 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; Clustering the offspring population obtained in each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1; The K cluster centers are used as a training data set, and a steel structure building state prediction model is trained according to the training data set to obtain a trained steel structure building state prediction model; The current steel structure state of the steel structure building is evaluated according to the trained steel structure building state prediction model.

[0005] The present disclosure provides a method for assessing the condition of a steel structure building based on multi-source environmental sensor data, which has at least the following beneficial effects: This method first obtains M groups of historical multi-source environmental sensor data of steel structure buildings. In order to capture the nonlinear correlation between multi-source environmental factors and screen out more representative training data, the M groups of historical multi-source environmental sensor data of steel structure buildings are subjected to multiple differential evolution processes. Any differential evolution process includes randomly selecting a set number of groups of historical multi-source environmental sensor data from the M groups of historical multi-source environmental sensor data as the initial population, and performing differential evolution to obtain an offspring population. The individual fitness value is calculated based on the difference between the actual value of the steel structure building state factor and the individual's predicted value of the steel structure building state factor. The historical multi-source environmental sensor data are screened by introducing the numerical value of the steel structure building state factor to assist differential evolution, because the steel structure building state factor is The state factor can directly affect the state of the steel structure building. Therefore, the parameter is introduced to assist in screening, which can select more representative historical multi-source environmental sensor data as the training data of the model to improve the accuracy of model training; then, the offspring population obtained according to each differential evolution process is clustered to obtain multiple cluster centers. After clustering here, multiple data clusters will be obtained. The individuals serving as cluster centers are highly representative individuals in the corresponding data clusters and have greater training value. By using the core points in multiple data clusters as training data sets, the accuracy of model training can be improved; finally, the current steel structure building state of the steel structure building is evaluated based on the trained steel structure building state prediction model, which can obtain more accurate evaluation results.

[0006] In some embodiments, the calculation function of the fitness value is: ; ; in, For individuals The fitness value of is the weight, For individuals The Euclidean distance to the closest individual with a higher fitness value, is the true value of the steel structure building status factor, Based on individual Predicted values ​​of steel structure building status factors, is the logarithmic function with base 10, for The 2-norm of .

[0007] In some embodiments, the process of obtaining a predicted value of the steel structure building status factor based on the individual includes: Calculating a historical environmental characteristic value of the individual based on a set of historical multi-source environmental sensor data corresponding to the individual; Based on the regression model, the predicted value of the steel structure building status factor corresponding to the historical environmental characteristic value is calculated; wherein the regression model has a mapping relationship between the historical environmental characteristic value and the corresponding value of the steel structure building status factor.

[0008] 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.

[0009] In some embodiments, the steel structure building state factor is a vibration factor.

[0010] In some embodiments, clustering the offspring population obtained from each differential evolution process comprises: K-means clustering is performed on the offspring population obtained in each differential evolution process.

[0011] In some embodiments, the steel structure building state prediction model is a gated recurrent neural network; The step of evaluating the current state of the steel structure building according to the trained steel structure building state prediction model includes: 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 of the steel structure building output by the trained steel structure building state prediction model.

[0012] A second aspect of the embodiments of the present application provides a steel structure building condition assessment system based on multi-source environmental sensing data, the system comprising: A data acquisition module is used to acquire M groups of historical multi-source environmental sensor data of the steel structure building; A differential evolution module is configured to perform multiple differential evolution processes on the M groups of historical multi-source environmental sensor data, wherein any one of the differential evolution processes comprises: randomly selecting m groups of historical multi-source environmental sensor data from the M groups of historical multi-source environmental sensor data as an initial population, and performing differential evolution to obtain a progeny population; wherein each individual in the population is a group 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, wherein the second value is a 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; A population clustering module, configured to cluster the offspring populations obtained in each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1; A model training module is used to use K cluster centers as a training data set, and train a steel structure building state prediction model according to the training data set to obtain a trained steel structure building state prediction model; The state prediction module is used to evaluate the current state of the steel structure building according to the trained steel structure building state prediction model.

[0013] A third aspect of an embodiment of the present application proposes an electronic device, at least one controller and a memory for communicating with the at least one controller; the memory stores instructions that can be executed by the at least one controller, and the instructions are executed by the controller to enable the controller to execute the steel structure building status assessment method based on multi-source environmental sensing data as described in the first aspect.

[0014] A fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned steel structure building status assessment method based on multi-source environmental sensing data.

[0015] It can be understood that the beneficial effects of the second to fourth aspects compared with the relevant technologies are the same as the beneficial effects of the first aspect compared with the relevant technologies. Please refer to the relevant description in the first aspect and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 This is a flow chart of an embodiment of a method for assessing the condition of a steel structure building based on multi-source environmental sensing data provided by the present application; Figure 2 This is a schematic structural diagram of an embodiment of a steel structure building condition assessment system based on multi-source environmental sensing data provided by the present application; Figure 3 It is a structural diagram of an embodiment of an electronic device provided by the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0019] It should be noted that although the device schematics illustrate functional module divisions and the flowcharts illustrate logical sequences, in certain circumstances, the steps shown or described may be performed in a sequence that differs from the module divisions in the device or the sequence in the flowcharts. The terms "first," "second," and so on, in the specification, claims, and drawings, are used to distinguish similar items and are not necessarily used to describe a specific sequence or precedence.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application. like Figure 1 One embodiment of the present application provides a method for assessing the condition of a steel structure building based on multi-source environmental sensor data, the method comprising the following steps S110 to S150: Step S110 , obtaining M groups of historical multi-source environmental sensor data of the steel structure building.

[0021] In this step, a set of historical multi-source environmental sensor data refers to multi-source environmental sensor data collected at a certain moment, and M sets of historical multi-source environmental sensor data refers to multi-source environmental sensor data collected at M moments. A set of multi-source environmental sensor data refers to multiple types of environmental sensor data, for example, atmospheric pressure sensor data collected by a pressure sensor, humidity sensor data collected by a humidity sensor, and wind speed sensor data collected by a wind speed sensor.

[0022] In actual engineering projects, environmental parameters such as wind speed, humidity, and air pressure will indirectly change the state of steel structure buildings (such as force, load state, etc.) by affecting the structural vibration characteristics. Therefore, this implementation screens historical multi-source environmental sensor data to select representative historical multi-source environmental sensor data as training data to explore the relationship between multi-source environmental sensor data and the state of steel structure buildings.

[0023] Furthermore, a set of historical multi-source environmental sensor data corresponding to the individual includes: historical wind speed sensor data, historical humidity sensor data, and historical air pressure sensor data.

[0024] 1) Historical wind speed sensor data refers to the time series measurement values ​​of the air flow velocity in the building environment collected by the wind speed sensor, which can be implemented using an ultrasonic anemometer or a mechanical anemometer.

[0025] 2) Historical humidity sensing data refers to the time series measurement of the water vapor content in the ambient air of the building collected by the humidity sensor, which can be implemented using a capacitive or resistive humidity sensor.

[0026] 3) Historical air pressure sensing data refers to the time series measurement values ​​of the atmospheric pressure in the building’s environment collected by air pressure sensors, which can be implemented using piezoelectric or piezoresistive sensors.

[0027] Specifically, when constructing a steel building condition assessment model, it is necessary to screen out the core factors that significantly impact the condition of steel structures from a multi-dimensional set of environmental parameters. During the data collection phase, wind speed sensors can be deployed on the building's exterior, humidity sensors at steel structure joints, and air pressure sensors within the building's interior, forming a multi-source monitoring network. These sensors continuously record environmental data at a fixed sampling frequency (e.g., once per second). After data cleaning, a structured dataset with a timestamp is generated, which serves as the input individuals for the subsequent differential evolution process.

[0028] Compared with the existing technology, this solution can capture the nonlinear correlation between environmental factors by fusing three types of heterogeneous sensor data: wind speed, humidity, and air pressure. For example, sudden changes in air pressure in a high-humidity environment may aggravate fatigue damage to steel components, and strong winds combined with humidity fluctuations may trigger resonance effects. Such composite effects cannot be effectively identified in a single data dimension. This application can establish a multidimensional correlation model between environmental parameters and the state of steel structures, solving the problem of prediction bias caused by incomplete coverage of environmental factors in the existing technology. For example, in typhoon-prone areas, the risk of loosening of steel structure connection nodes can be more accurately predicted by considering the combination of data on sudden changes in wind speed and sudden increases in humidity. This multi-source data fusion mechanism enhances the environmental adaptability of the state assessment model, making the prediction results have higher engineering reference value.

[0029] Step S120, performing multiple differential evolution processes on M groups of historical multi-source environmental sensor data, wherein any differential evolution process includes: randomly selecting m groups of historical multi-source environmental sensor data from the M groups of historical multi-source environmental sensor data as the initial population, and performing differential evolution to obtain an offspring population; wherein each individual in the population is a group 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, the second value is a 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.

[0030] To capture the nonlinear correlations between environmental factors and select more representative training data, a global optimization algorithm, differential evolution, was used to dynamically adjust the search direction to retain the global optimal information. Differential evolution is an optimization algorithm based on swarm intelligence. It iteratively generates high-quality populations through mutation, crossover, and selection, which are used to select environmental data combinations that are sensitive to building conditions. Fitness calculation is a quantitative indicator that evaluates the ability of individual data to predict building conditions.

[0031] In addition, this embodiment also introduces numerically assisted differential evolution of steel structure building state factors (such as vibration factors) to screen historical multi-source environmental sensor data. Because the steel structure building state factor can directly affect the state of the steel structure building, the introduction of this parameter-assisted screening can select more representative historical multi-source environmental sensor data as model training data to improve the accuracy of model training.

[0032] Step S130 , clustering the offspring population obtained in each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1.

[0033] In this step, the offspring population obtained in each differential evolution process is clustered to obtain multiple cluster centers. After clustering here, multiple data clusters will be obtained. The individuals serving as cluster centers are highly representative individuals in the corresponding data clusters and have greater training value. By using the core points in multiple data clusters as training data sets, the accuracy of model training can be improved.

[0034] Step S140: Use the K cluster centers as a training data set, and train the steel structure building state prediction model according to the training data set to obtain a trained steel structure building state prediction model.

[0035] Step S150: evaluating the current state of the steel structure building according to the trained steel structure building state prediction model.

[0036] The beneficial effects of the steel structure building condition assessment method based on multi-source environmental sensor data provided in this application include: This method first obtains M groups of historical multi-source environmental sensor data of steel structure buildings. In order to capture the nonlinear correlation between multi-source environmental factors and screen out more representative training data, the M groups of historical multi-source environmental sensor data of steel structure buildings are subjected to multiple differential evolution processes. Any differential evolution process includes randomly selecting a set number of groups of historical multi-source environmental sensor data from the M groups of historical multi-source environmental sensor data as the initial population, and performing differential evolution to obtain an offspring population. The individual fitness value is calculated based on the difference between the actual value of the steel structure building state factor and the individual's predicted value of the steel structure building state factor. The historical multi-source environmental sensor data are screened by introducing the numerical value of the steel structure building state factor to assist differential evolution, because the steel structure building state factor is The state factor can directly affect the state of the steel structure building. Therefore, the parameter is introduced to assist in screening, which can select more representative historical multi-source environmental sensor data as the training data of the model to improve the accuracy of model training; then, the offspring population obtained according to each differential evolution process is clustered to obtain multiple cluster centers. After clustering here, multiple data clusters will be obtained. The individuals serving as cluster centers are highly representative individuals in the corresponding data clusters and have greater training value. By using the core points in multiple data clusters as training data sets, the accuracy of model training can be improved; finally, the current steel structure building state of the steel structure building is evaluated based on the trained steel structure building state prediction model, which can obtain more accurate evaluation results.

[0037] Furthermore, the calculation function of the fitness value is: ; ; in, For individuals Fitness value, is the weight, For individuals The Euclidean distance to the closest individual with a higher fitness value, is the true value of the steel structure building status factor, Based on individual Predicted values ​​of steel structure building status factors, is the logarithmic function with base 10, for The 2-norm of .

[0038] Among them, the weight It refers to the coefficient used to adjust the contribution ratio of the distance between individuals and the prediction error to the fitness value. Specifically, it can be achieved by using a value in the range of 0.3 to 0.7. By adjusting the weight, the relationship between population diversity and model accuracy can be balanced. Distance metric used to measure diversity information. Euclidean distance refers to individuals The geometric distance between the population and other individuals with higher fitness in the data space can be achieved by calculating the Euclidean norm between multi-dimensional sensor data vectors to prevent the population from converging to a local optimal solution too early. It refers to the modulus of the error vector between the true value and the predicted value. It refers to the mathematical operation of nonlinear compression of the error magnitude, which is used to reduce the impact of abnormal errors on the fitness value.

[0039] Specifically, in the differential evolution process, each individual represents a set of historical environmental sensor data, which is mapped into the predicted value of the steel structure state factor through the regression model. True value and predicted value The 2-norm error is transformed into Component, reflecting the prediction accuracy of the individual. At the same time, the minimum Euclidean distance between the individual and the higher fitness individual in the population is calculated. Component, used to maintain population diversity. By weighted fusion of these two components, the final fitness value It not only guides the population to evolve towards high precision, but also avoids the problem of insufficient search space coverage due to too many similar individuals.

[0040] Compared with the existing technology, the present application can balance the dual needs of optimizing accuracy and maintaining data diversity during model training, and effectively screen out high-quality samples with both prediction accuracy and data diversity during the training stage of the steel structure state prediction model, thereby improving the reliability and generalization ability of the final steel structure building state assessment results.

[0041] Furthermore, the step S120 of obtaining the predicted value of the steel structure building status factor based on the individual includes the following steps S210 and S220: Step S210 , calculating the historical environmental characteristic value of the individual based on a set of historical multi-source environmental sensor data corresponding to the individual.

[0042] Step S220, based on the regression model, calculate the predicted value of the steel structure building status factor corresponding to the historical environmental characteristic value; wherein the regression model has a mapping relationship between the historical environmental characteristic value and the corresponding value of the steel structure building status factor.

[0043] Historical environmental characteristic values ​​refer to indicators reflecting the comprehensive state of the environment extracted from multi-source environmental sensor data. This can be achieved by weighted calculations or statistical extraction of historical wind speed, humidity, air pressure, and other data, such as calculating mean values, variances, or peak values ​​to characterize environmental fluctuations. Regression models are predictive tools used to establish mathematical relationships between environmental characteristics and state factors. These can be implemented using linear regression, support vector regression, or neural network models, fitting the nonlinear relationship between characteristic values ​​and true influencing factors using training data.

[0044] Specifically, key features are first extracted from a set of historical multi-source environmental sensor data corresponding to the individual. For example, wind speed, humidity, and air pressure data at different time points are normalized and their statistical features are calculated to form a multidimensional feature vector. This feature vector is then input into a pre-trained regression model, which outputs a predicted value based on the correspondence between the feature values ​​in the historical data and the actual influencing factors. For example, if the state factor of 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 the noise interference problem caused by directly using raw sensor data by quantifying the complex relationship between environmental data and building status.

[0045] This application can more accurately predict the numerical value of the impact factor of environmental sensor data on the status of steel structure buildings, provide reliable input for subsequent status assessment, and solve the prediction deviation problem caused by multi-source data redundancy and linear assumptions in the existing technology, thereby improving the accuracy and reliability of building status assessment.

[0046] Furthermore, clustering is performed based on the offspring population obtained from each differential evolution process, including: K-means clustering is performed based on the offspring population obtained in each differential evolution process.

[0047] K-means clustering is an unsupervised machine learning method that divides data into K clusters. This is achieved by using iterative optimization to assign each data point to the nearest cluster center and update the cluster center position. The final clustering result is determined by minimizing the intra-cluster squared error. In this solution, K-means clustering is used to group data from the offspring population generated by differential evolution. After generating a large number of offspring individuals through multiple differential evolution cycles, K-means clustering can effectively select representative data samples as training sets, reducing the impact of redundant data on model training.

[0048] After completing multiple differential evolution processes, the population data generated in each evolution is merged to form an overall dataset. When performing K-means clustering on this dataset, it is first necessary to set the target number of clusters, which can be set based on the scale of historical data or the accuracy requirements of building condition assessment. Subsequently, by randomly initializing the cluster center points, the Euclidean distance between each data point and each center point is iteratively calculated, the data points are assigned to the nearest cluster, and the cluster center coordinates are recalculated until the cluster assignment no longer changes or the maximum number of iterations is reached. The final set of cluster center points can be used as the core samples of the training dataset. These samples not only retain the distribution characteristics of the original data, but also eliminate the interference of repeated or similar data on model training.

[0049] Compared with the existing technology, this method improves the model training efficiency by reducing data redundancy, while ensuring the uniform distribution of training samples in the feature space, so that the finally trained steel structure building state prediction model has higher generalization ability and evaluation accuracy, thereby realizing accurate prediction of key indicators such as building vibration state.

[0050] Furthermore, the steel structure building state prediction model is a gated recurrent neural network; The current state of the steel structure building is evaluated based on the trained steel structure building state prediction model, including: 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 of the steel structure building output by the trained steel structure building state prediction model.

[0051] Among them, the gated recurrent neural network refers to a recurrent neural network with an update gate and a reset gate structure, which controls the transmission and forgetting of temporal information through a gating mechanism. Specifically, it 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 sensor data.

[0052] The trained steel structure state prediction model uses a gated recurrent neural network to extract time series features from the input multi-source environmental sensor data. 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 forgetting of historical information. The model recursively processes the sensor data sequence layer by layer along the time dimension, ultimately outputting a predicted value for the steel structure's vibration factor through a fully connected layer. This predicted value is then mapped into a safety level assessment result for the steel structure. For example, if the vibration factor exceeds a set threshold, the model can output a structural stability warning signal.

[0053] Compared with existing technologies, this method achieves high-precision time-series modeling of steel structure health. The unique gating structure of the gated recurrent neural network effectively suppresses the vanishing gradient problem during long-term series training, enabling the model to accurately identify the impact of sudden environmental parameter changes on building safety status. Furthermore, through its end-to-end prediction mechanism, this method avoids the error accumulation caused by manual feature engineering, significantly improving the real-time and reliability of steel structure health assessment.

[0054] like Figure 2 As shown, one embodiment of the present application provides a steel structure building status assessment system based on multi-source environmental sensor data, the system comprising: The data acquisition module 1100 is used to acquire M groups of historical multi-source environmental sensor data of the steel structure building.

[0055] The differential evolution module 1200 is used to perform multiple differential evolution processes on M groups of historical multi-source environmental sensor data, wherein any differential evolution process includes: randomly selecting m groups of historical multi-source environmental sensor data from the M groups of historical multi-source environmental sensor data as the initial population, and performing differential evolution to obtain an offspring population; wherein each individual in the population is a group 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, the second value is based on the individual's predicted value of 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.

[0056] The population clustering module 1300 is used to cluster the offspring populations obtained in each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1.

[0057] The model training module 1400 is used to use K cluster centers as a training data set, and train the steel structure building state prediction model according to the training data set to obtain a trained steel structure building state prediction model.

[0058] The state prediction module 1500 is used to evaluate the current state of the steel structure building according to the trained steel structure building state prediction model.

[0059] It should be noted that, since the steel structure building status assessment system based on multi-source environmental sensor data in this embodiment and the above-mentioned steel structure building status assessment method based on multi-source environmental sensor data are based on the same inventive concept, the corresponding contents in the embodiment of the steel structure building status assessment method based on multi-source environmental sensor data are also applicable to the embodiment of the steel structure building status assessment system based on multi-source environmental sensor data, and will not be described in detail here.

[0060] like Figure 3As shown, an embodiment of the present application further provides an electronic device, the electronic device comprising: at least one memory; at least one processor; at least one program; The programs are stored in the memory, and the processor executes at least one program to implement the above-mentioned method for assessing the state of a steel structure building based on multi-source environmental sensing data in the present disclosure.

[0061] The electronic device may be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a car computer, etc.

[0062] The electronic device according to the embodiment of the present application is described in detail below.

[0063] The processor 1600 may be implemented as a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application. Memory 1700 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). Memory 1700 can store an 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 memory 1700 and is called by processor 1600 to execute the method for steel structure building condition assessment based on multi-source environmental sensor data in the embodiments of this application.

[0064] Input / output interface 1800, used for information input and output; Communication interface 1900, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.); Bus 2000 , which transmits information between various components of the device (e.g., processor 1600 , memory 1700 , input / output interface 1800 , and communication interface 1900 ); The processor 1600 , the memory 1700 , the input / output interface 1800 , and the communication interface 1900 are connected to each other in communication within the device via the bus 2000 .

[0065] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned steel structure building status assessment method based on multi-source environmental sensing data.

[0066] 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 can include high-speed random access memory and non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device.

[0067] In some embodiments, the memory may optionally include a memory remotely located relative to the processor, and the remote memory may be connected to the processor via a network. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0068] 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 appreciate 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.

[0069] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0070] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0071] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0072] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0073] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0075] Units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0076] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0077] If the integrated unit is implemented in the form of 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 the present application, 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, which is stored in a storage medium and includes multiple instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0078] The above is a specific description of the preferred implementation of the embodiments of the present application, but the embodiments of the present application are not limited to the above-mentioned implementation methods. Technical personnel familiar with the art can also make various equivalent modifications or substitutions without violating the spirit of the embodiments of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the embodiments of the present application.

Claims

1. A method for assessing the condition of a steel structure building based on multi-source environmental sensing data, characterized in that: The method comprises: Obtain M groups of historical multi-source environmental sensor data of the steel structure building; Performing multiple differential evolution processes on the M groups of historical multi-source environmental sensor data, wherein any one of the differential evolution processes includes: randomly selecting m groups of historical multi-source environmental sensor data from the M groups of historical multi-source environmental sensor data as an initial population, and performing differential evolution to obtain a progeny population; wherein each individual in the population is a group 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, wherein the second value is a 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; Clustering the offspring population obtained in each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1; The K cluster centers are used as a training data set, and a steel structure building state prediction model is trained according to the training data set to obtain a trained steel structure building state prediction model; The current steel structure state of the steel structure building is evaluated according to the trained steel structure building state prediction model.

2. The steel structure building condition assessment method based on multi-source environmental sensing data according to claim 1 is characterized in that: The calculation function of the fitness value is: ； ； in, For individuals The fitness value of is the weight, For individuals The Euclidean distance to the closest individual with a higher fitness value, is the true value of the steel structure building status factor, Based on individual Predicted values ​​of steel structure building status factors, is the logarithmic function with base 10, for The 2-norm of .

3. The steel structure building condition assessment method based on multi-source environmental sensing data according to claim 2 is characterized in that: The process of obtaining the predicted value of the steel structure building status factor based on the individual includes: Calculating a historical environmental characteristic value of the individual based on a set of historical multi-source environmental sensor data corresponding to the individual; Based on the regression model, the predicted value of the steel structure building status factor corresponding to the historical environmental characteristic value is calculated; wherein the regression model has a mapping relationship between the historical environmental characteristic value and the corresponding value of the steel structure building status factor.

4. The steel structure building status assessment method based on multi-source environmental sensor data according to claim 3 is 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.

5. The steel structure building condition assessment method based on multi-source environmental sensing data according to claim 3 is characterized in that: The steel structure building state factor is a vibration factor.

6. The steel structure building condition assessment method based on multi-source environmental sensor data according to claim 2 is characterized in that: Clustering the offspring population obtained according to each differential evolution process includes: K-means clustering is performed on the offspring population obtained in each differential evolution process.

7. The method for assessing the condition of a steel structure building based on multi-source environmental sensing data according to claim 2, characterized in that: The steel structure building state prediction model is a gated recurrent neural network; The step of evaluating the current state of the steel structure building according to the trained steel structure building state prediction model includes: 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 of the steel structure building output by the trained steel structure building state prediction model.

8. A steel structure building status assessment system based on multi-source environmental sensor data, characterized in that: The system comprises: A data acquisition module is used to acquire M groups of historical multi-source environmental sensor data of the steel structure building; A differential evolution module is configured to perform multiple differential evolution processes on the M groups of historical multi-source environmental sensor data, wherein any one of the differential evolution processes comprises: randomly selecting m groups of historical multi-source environmental sensor data from the M groups of historical multi-source environmental sensor data as an initial population, and performing differential evolution to obtain a progeny population; wherein each individual in the population is a group 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, wherein the second value is a 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; A population clustering module, configured to cluster the offspring populations obtained in each differential evolution process to obtain K cluster centers; K is a positive integer greater than 1; A model training module is used to use K cluster centers as a training data set, and train a steel structure building state prediction model according to the training data set to obtain a trained steel structure building state prediction model; The state prediction module is used to evaluate the current state of the steel structure building according to the trained steel structure building state prediction model.

9. An electronic device, characterized in that: include: at least one controller and a memory for communicatively coupling with the at least one controller; The memory stores instructions that can be executed by the at least one controller, and the instructions are executed by the controller to enable the controller to execute the steel structure building status assessment method based on multi-source environmental sensing data according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the steel structure building status assessment method based on multi-source environmental sensing data according to any one of claims 1 to 7.

Images