Health monitoring method, device, equipment and storage medium for tower crane structure

Abstract

The present application discloses a health monitoring method, device, electronic device and storage medium for a tower crane structure, the method comprising: obtaining tower crane information of a target tower crane; determining whether there is a structural state analysis model matching the target tower crane based on the tower crane identification of the target tower crane; when it is determined that there is no structural state analysis model that does not match the target tower crane, constructing a tower crane simulation model of the target tower crane, and simulating the tower crane simulation model based on simulation data to obtain a simulation result of the target tower crane; loading an initial analysis model, and fine-tuning the initial analysis model based on the simulation result to obtain a target analysis model matching the target tower crane; inputting the tower crane information into the target analysis model, and outputting the health monitoring result of the target tower crane. The accuracy and efficiency of health and safety monitoring of tower cranes are improved.

Description

Technical Field

[0001] The present application relates to the technical field of safety monitoring of tower cranes, and in particular to a method, device, electronic equipment and storage medium for health monitoring of a tower crane structure. Background Art

[0002] With continuous development, tower cranes are widely used in the construction of high-rise buildings, bridges and other buildings, and the safe operation of tower cranes is an important link, such as the operating safety of operators and the application safety of tower cranes. Among them, the operating safety of operators is reflected in the standardization of tower crane operation, and the application safety of tower cranes is reflected in the health and safety of the tower crane's own structure. When the tower crane structure is abnormal, even if the operators operate in a standardized manner, there will be safety hazards. Therefore, it is extremely important to monitor the health and safety of the tower crane structure.

[0003] At present, when monitoring the health and safety of the tower crane structure, in addition to the traditional manual inspection method, it also includes the use of certain measurement methods to realize the diagnosis of the tower steel structure, such as by comparing the monitoring data with the safety data. However, there are certain shortcomings. For example, the manual inspection method is time-consuming and labor-intensive. For example, the early warning based on the comparison of monitoring data will only alarm when the threshold is reached. At the same time, it is necessary to set corresponding judgment conditions for all tower cranes, which is not applicable.

[0004] Therefore, there is an urgent need for a health monitoring method for tower crane structures that can improve the accuracy and applicability of health and safety monitoring of tower cranes. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a health monitoring method, device, electronic device and storage medium for a tower crane structure, so as to solve the technical problems of low accuracy and applicability of health and safety monitoring of tower cranes in related technologies.

[0006] In a first aspect, an embodiment of the present application provides a health monitoring method for a tower crane structure, comprising:

[0007] Acquire tower crane information of a target tower crane, wherein the tower crane information includes sensor data and tower crane characteristics collected in real time by various sensors arranged on the target tower crane, and the tower crane characteristics include a tower crane identification and tower crane structural characteristics;

[0008] Based on the tower crane identification of the target tower crane, determining whether there is a structural state analysis model matching the target tower crane;

[0009] When it is determined that there is no structural state analysis model that does not match the target tower crane, a tower crane simulation model of the target tower crane is constructed, and the tower crane simulation model is simulated based on simulation data to obtain a simulation result of the target tower crane, wherein the simulation data is working condition data and the simulation result is damage data;

[0010] Loading an initial analysis model, and performing model migration fine-tuning on the initial analysis model based on the simulation results to obtain a target analysis model that matches the target tower crane;

[0011] The tower crane information is input into the target analysis model, and the health monitoring result of the target tower crane is output.

[0012] In a second aspect, an embodiment of the present application provides a health monitoring device for a tower crane structure, comprising:

[0013] An information acquisition module is used to acquire tower crane information of a target tower crane, wherein the tower crane information includes sensor data and tower crane features collected in real time by various sensors arranged on the target tower crane, and the tower crane features include a tower crane identification and tower crane structural characteristics;

[0014] A matching judgment module, used for determining whether there is a structural state analysis model matching the target tower crane based on the tower crane identification of the target tower crane;

[0015] A data simulation module is used for constructing a tower crane simulation model of the target tower crane when it is determined that there is no structural state analysis model that does not match the target tower crane, and simulating the tower crane simulation model based on simulation data to obtain a simulation result of the target tower crane, wherein the simulation data is working condition data and the simulation result is damage data;

[0016] A model fine-tuning module is used to load an initial analysis model and perform model migration fine-tuning on the initial analysis model based on the simulation results to obtain a target analysis model that matches the target tower crane;

[0017] The analysis and prediction module is used to input the tower crane information into the target analysis model and output the health monitoring result of the target tower crane.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in any one of the above-mentioned tower crane structure health monitoring methods when executing the computer program.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the health monitoring method of a tower crane structure described in any one of the above items are implemented.

[0020] The embodiment of the present application provides a health monitoring method, device, electronic device and storage medium for tower crane structure. When performing health monitoring of the tower crane structure, tower crane information of the target tower crane to be monitored is obtained, including sensor data collected by the set sensor, tower crane working conditions and tower crane characteristics, and then it is determined whether there is a structural state analysis model matching the target tower crane according to the tower crane identification in the tower crane characteristics. When it is determined that there is no such model, a tower crane simulation model of the target tower crane is constructed to simulate the data to obtain the simulation result corresponding to the target tower crane, and then the pre-trained initial analysis model is loaded to perform model migration fine-tuning to obtain a target analysis model suitable for health analysis of the target tower crane, and finally the tower crane information is input into the target analysis model to output the health monitoring result of the target tower crane. When performing real-time monitoring of the structural health of the tower crane, the accuracy of monitoring and analysis is improved by integrating multi-distance data, and at the same time, the efficiency of model training is improved based on data migration, and tower cranes of different specifications can be quickly adapted, thereby improving the safety of tower crane operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a health monitoring method for a tower crane structure provided in an embodiment of the present application;

[0022] Figure 2 It is a flow chart of the steps of obtaining an initial analysis model provided in an embodiment of the present application;

[0023] Figure 3 It is a flowchart of the steps of obtaining a structural state analysis model provided in an embodiment of the present application;

[0024] Figure 4 It is a flowchart of the steps of obtaining a target analysis model provided in an embodiment of the present application;

[0025] Figure 5 is another flow chart of the steps of obtaining a target analysis model provided in an embodiment of the present application;

[0026] Figure 6 is another flow chart of the steps of the tower crane structure health monitoring method provided in an embodiment of the present application;

[0027] Figure 7 It is a structural schematic diagram of a health monitoring device for a tower crane structure provided in an embodiment of the present application;

[0028] Figure 8 is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0029] Fig. 9 This is another structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] It should be understood that the various steps described in the method embodiments disclosed in the present application can be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0032] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0033] In the relevant technology, when monitoring the health and safety of the tower crane structure, in addition to the traditional manual inspection method, it also includes the use of certain measurement methods to realize the diagnosis of the tower steel structure, such as by comparing the monitoring data with the safety data. However, there are certain shortcomings. For example, the manual inspection method is time-consuming and labor-intensive. For example, the early warning based on the comparison of monitoring data will only alarm when the threshold is reached. At the same time, the corresponding judgment conditions need to be set for all tower cranes, which is not applicable.

[0034] In order to solve the technical problems existing in the related art, the present application embodiment provides a health monitoring method for a tower crane structure, see Figure 1 , Figure 1 It is a flow chart of a health monitoring method for a tower crane structure provided in an embodiment of the present application. The method includes steps 101 to 105.

[0035] Step 101, obtaining tower crane information of a target tower crane, wherein the tower crane information includes sensor data collected in real time by various sensors arranged on the target tower crane and tower crane characteristics, and the tower crane characteristics include a tower crane identification and tower crane structural characteristics.

[0036] In one embodiment, when health monitoring of the tower crane structure is performed on a target tower crane, tower crane information of the target tower crane is obtained, and the obtained tower crane information includes sensor data collected in real time by various sensors installed on the target tower crane, the tower crane operating condition of the current target tower crane, and tower crane characteristics of the target tower crane, wherein the tower crane characteristics at least include a tower crane identification and a tower crane structure characteristic.

[0037] Specifically, during the operation of the tower crane, the differences in working conditions brought about by different operations will cause different changes in the tower crane. For example, different lifting weights will have different forces on the boom of the tower crane, which will in turn cause different deformations of the boom. At the same time, different tower crane structural characteristics will also have different changes under the same working conditions. Therefore, by combining the characteristics of the tower crane and the current working conditions, the health and safety of the tower crane can be accurately analyzed. When determining the current working condition of the tower crane, data collection is performed based on the sensors installed on the tower crane to obtain the working condition information of the tower crane.

[0038] Step 102: Based on the tower crane identifier of the target tower crane, determine whether there is a structural state analysis model matching the target tower crane.

[0039] In one embodiment, after obtaining the tower crane information of the target tower crane, subsequent analysis and judgment processing will be performed to determine the current health monitoring result of the target tower crane. Specifically, after obtaining the tower crane information of the target tower crane, it is determined whether there is a structural state analysis model that matches the target tower crane according to the obtained tower crane identification, wherein the structural state analysis model is used to analyze whether there is a safety hazard in the target tower crane.

[0040] For example, there are multiple tower cranes operating at a construction site, and there may be multiple tower cranes of different specifications. For tower cranes of different specifications, due to the differences in the tower crane structures, the applied operating scenarios will be very different, such as the maximum lifting weight, the maximum operating height, etc. Therefore, the structural state analysis models adapted to tower cranes of different rules will also be different. Therefore, after obtaining the tower crane information of the target tower crane, determine the structural state analysis model that can be used directly. When it exists, the structural state analysis model will be directly used for analysis and processing to determine the real-time health status result of the target tower crane. When it does not exist, the structural state analysis model matching the target tower crane will be obtained through relevant training processing.

[0041] In practical applications, for example, the tower cranes already operating in the current construction site include tower crane 1, tower crane 2, tower crane 3 and tower crane 4. At this time, a new tower crane is needed to be added to the current construction site to complete the corresponding operation. If the new tower crane is tower crane 1, then when performing health and safety monitoring on the new tower crane, the structural state analysis model matching the new tower crane can be directly obtained, that is, the structural state analysis model matching tower crane 1. If the new tower crane is tower crane 5, then when performing health and safety monitoring on the new tower crane, since tower crane 5 is introduced for the first time in the current construction site, there is no structural state analysis model matching tower crane 5.

[0042] When determining whether there is a structural state analysis model that matches the target tower crane, a query and match can be performed through the tower crane identifier to determine whether there is a matching structural state analysis model, specifically including: obtaining the currently configured structural state analysis model, and identifying the adaptation identifier of the tower crane to which the configured structural state analysis model is adapted; matching the tower crane identifier with the adaptation identifier to determine whether the tower crane identifier is included in the adaptation identifier; if it is determined that the tower crane identifier is not included in the adaptation identifier, it is determined that there is no structural state analysis model that matches the target tower crane; if it is determined that the tower crane identifier is included in the adaptation identifier, it is determined that there is a structural state analysis model that matches the target tower crane.

[0043] In fact, for each specification of tower crane, a model for health and safety analysis can be pre-trained and stored, and can be directly called when needed. Therefore, when determining whether there is a matching structural state analysis model for the target tower crane, the tower crane identification of the target tower crane is obtained, where the tower crane identification can be set based on the tower crane specifications, that is, tower cranes of the same specifications are set with the same tower crane identification, and then query and match based on the tower crane identification to determine whether there is a structural state analysis model that matches the target tower crane. In order to achieve query matching based on the tower crane identification, the currently configured structural state analysis model can be associated with the corresponding tower crane identification, that is, the stored structural state analysis model can be marked based on the tower crane identification for subsequent application.

[0044] Step 103, when it is determined that there is no structural state analysis model that does not match the target tower crane, a tower crane simulation model of the target tower crane is constructed, and the tower crane simulation model is simulated based on the simulation data to obtain a simulation result of the target tower crane, wherein the simulation data is working condition data and the simulation result is damage data.

[0045] In one embodiment, when query matching is performed based on the tower crane identification of the target tower crane, if it is determined that there is no structural state analysis model matching the target tower crane, it is necessary to re-train the corresponding model to obtain a structural state analysis model matching the target tower crane. Therefore, when it is determined that there is no structural state analysis model matching the target tower crane, a tower crane simulation model of the target tower crane is constructed, and the tower crane simulation model is simulated based on the set simulation data to obtain a simulation result of the target tower crane, and the set simulation data is the working condition data of the tower crane, and the working condition data can be obtained based on the data setting of the set sensor, and the obtained simulation result is the damage data of the tower crane.

[0046] It should be noted that the damage data is obtained by simulation based on the set operating condition data. Since the set operating condition data can be normal operating condition data or abnormal operating condition data, the damage data obtained can be good data, that is, data without damage, or it can be specific damage data of each part when damage occurs.

[0047] In addition, when it is determined that there is currently a structural state analysis model that matches the target tower crane, the matched structural state analysis model will be directly used for analysis and prediction processing, specifically including: when it is determined that there is a structural state analysis model that matches the target tower crane, the matched structural state analysis model is loaded, and the tower crane information is input into the matched structural state analysis model, and the analysis result is output; if the analysis result is no damage, the no damage result is output; if the analysis result is damage, the damage location and the damage offset value are output, and a damage analysis report is generated based on the damage offset value, wherein the damage analysis report at least includes a damage risk value.

[0048] In actual application, when there is no structural state analysis model matching the target tower crane, further training and other processing will be required. When it is determined that there is a structural state analysis model matching the target tower crane, the model will be directly called for direct use. When in use, the tower crane information of the target tower crane is input into the matched structural state analysis model to output the analysis result. The analysis result can be that the tower crane is normal, that is, there is no damage, or that the tower crane is abnormal, that is, there is damage. At the same time, when it is determined that there is damage, the location of the damage will be determined and whether there is a risk of the existing damage will be determined.

[0049] For example, when it is determined that there is damage, a corresponding damage analysis report will be generated based on the determined damage location and damage offset value. The damage analysis report can point out the specific location of the damage, analyze the risk of the damage, and determine whether to perform further processing, such as tower crane maintenance. For the damaged location, during the subsequent use of the tower crane, real-time monitoring and feedback will be carried out so that the operator can check the damage status of the damaged location in a timely manner.

[0050] Step 104 , loading the initial analysis model, and performing model migration fine-tuning on the initial analysis model based on the simulation results, to obtain a target analysis model that matches the target tower crane.

[0051] In one embodiment, after completing the simulation processing of the target tower crane and obtaining the simulation results, the model will be trained according to the obtained simulation results. Specifically, the pre-stored initial analysis model is loaded to perform model migration fine-tuning on the initial analysis model based on the obtained simulation results, so as to obtain a structural state analysis model matching the target tower crane as the target analysis model, so as to perform real-time health and safety monitoring and analysis of the target tower crane based on the target analysis model.

[0052] Exemplarily, when a target analysis model matching the target tower crane is trained, data migration technology is used to perform model migration and fine-tuning processing on the pre-trained and stored initial analysis model according to the obtained simulation results, so as to quickly obtain a target analysis model matching the target tower crane, thereby improving the efficiency of health and safety monitoring.

[0053] In practical applications, the initial analysis model is obtained by pre-training and is stored in the corresponding memory together with the structural state analysis model of each tower crane. Therefore, it is necessary to train the initial analysis model in advance. Figure 2 , Figure 2 It is a flowchart of the steps of obtaining an initial analysis model provided in an embodiment of the present application, wherein the steps include steps 201 to 204.

[0054] Step 201, obtaining real-time tower crane information of each tower crane in the construction site, wherein the real-time tower crane information includes tower crane characteristics of each tower crane and sensor data collected by each sensor of each tower crane during operation, and the sensor data is used to determine the tower crane working condition of the tower crane;

[0055] Step 202, performing data analysis on the real-time tower crane information, and determining the central tower crane among all tower cranes;

[0056] Step 203, establishing a central simulation model of the central tower crane and setting initial simulation data of the central tower crane, and simulating the central simulation model based on the initial simulation data to obtain an initial simulation result of the central tower crane, wherein the initial simulation data is the working condition data of the central tower crane, and the initial simulation result is the damage data of the central tower crane;

[0057] Step 204: training the constructed initial model based on the initial simulation result to obtain a central simulation analysis model corresponding to the central tower crane, and using the central simulation analysis model as the initial analysis model.

[0058] Specifically, when the initial analysis model is trained, it is obtained based on the analysis and training of all tower cranes in the current construction site. For all tower cranes in the current construction site, the real-time tower crane data of each tower crane is obtained. The real-time tower crane data includes tower crane characteristics and sensor data, and the sensor data can be used to determine the tower crane working condition of the tower crane. After obtaining the real-time tower crane data, data analysis is performed to determine the central tower crane among all tower cranes, and then the initial simulation result of the central tower crane is obtained through simulation processing of the central tower crane. Finally, the constructed initial model is trained based on the initial simulation result to obtain the central simulation analysis model corresponding to the central tower crane, and the central simulation analysis model is stored as the initial analysis model.

[0059] Among them, the initial model is a model constructed based on deep learning, and the initial analysis model is updated in real time. When a tower crane of a new specification is added to the construction site, the stored initial analysis model is updated after the newly added tower crane has been operating for a certain period of time. For example, when the construction site includes tower cranes of different specifications, including tower crane 1, tower crane 2, tower crane 3 and tower crane 4, the initial analysis model can be obtained based on the four tower cranes included. After a tower crane 5 of a new specification is added, the initial analysis model will be updated based on the five tower cranes included after a certain period of operation.

[0060] When determining the initial analysis model currently used, the real-time tower crane information of each tower crane (excluding the target tower crane) in the construction site is obtained, and then one is selected as the central tower crane from all the tower cranes according to the real-time tower crane information, and then the model simulated and trained based on the central tower crane will be stored as the initial analysis model. When determining the central tower crane, it can be determined by cluster analysis, which specifically includes: obtaining the tower crane features in the real-time tower crane information, and clustering the tower crane features to obtain the first cluster center point corresponding to each tower crane; analyzing the first cluster center point to determine the second cluster center point of the first cluster center point; calculating the distance value between the first cluster center point and the second cluster center point, and taking the tower crane to which the first cluster center point corresponding to the minimum distance value belongs as the central tower crane.

[0061] In fact, when the central tower crane is determined based on the clustering method, it is to improve the training efficiency of the subsequent training to obtain the structural status analysis model for each tower crane. Therefore, when performing clustering processing, the tower crane features in the real-time tower crane information are obtained, and the tower crane features of each tower crane are clustered to obtain the first cluster center point, where the first cluster center point is the feature center point of each tower crane, and then the first cluster center point is clustered again to obtain the second cluster center point, and then by calculating the distance value between the second cluster center point and the first cluster center point, the distance between the feature center of each tower crane and the center of the feature set is obtained, and then the tower crane to which the minimum distance value belongs is taken as the central tower crane.

[0062] By determining the central tower crane, the distance between each tower crane and the central tower crane can be realized, and then when further model fine-tuning training is carried out, the structural state analysis model matching each tower crane can be obtained more quickly, thereby improving the efficiency of model training.

[0063] It should be noted that after obtaining the initial analysis model of the central tower crane, the initial analysis model can be fine-tuned based on the real-time tower crane information of all tower cranes to obtain the structural state analysis model corresponding to each tower crane. Specifically, refer to Figure 3 , Figure 3 It is a flowchart diagram of the steps of obtaining a structural state analysis model provided in an embodiment of the present application, wherein the steps include steps 301 to 303.

[0064] Step 301, obtaining first real-time tower crane information of a first tower crane in real-time tower crane information, wherein the first tower crane is a tower crane in a construction site, and the construction site includes multiple tower cranes;

[0065] Step 302: fine-tune the initial analysis model based on the first real-time tower crane information to obtain a first structural state analysis model that matches the first tower crane, and mark the first structural state analysis model based on the tower crane identifier of the first tower crane;

[0066] Step 303, obtaining second real-time tower crane information of the second tower crane from the real-time tower crane information, and fine-tuning the initial analysis model based on the second real-time tower crane information to obtain a second structural state analysis model matching the second tower crane, until a structural state analysis model of each tower crane in the construction site is obtained.

[0067] Specifically, the structural state analysis model matched by each tower crane is trained based on the initial analysis model of the central tower crane, and the real-time tower crane data of each tower crane is used to fine-tune the model to obtain the structural state analysis model matched by each tower crane.

[0068] Exemplarily, after obtaining an initial analysis model based on each tower crane in the construction site, the model is trained again based on the tower crane data of each tower crane, and the first real-time tower crane information of the first tower crane is obtained in the real-time tower crane information, so as to fine-tune the initial analysis model based on the first real-time tower crane information. Specifically, a certain amount of data is obtained from the first real-time tower crane information to fine-tune the initial analysis model, and when the training is completed, the first structural state analysis model matching the first tower crane is marked based on the tower crane identification of the first tower crane, and then the second real-time tower crane information of the second tower crane is obtained in the real-time tower crane information, and the initial analysis model is fine-tuned based on the second real-time tower crane information to obtain a second structural state analysis model matching the second tower crane, and through continuous loop processing, the structural state analysis model corresponding to each tower crane is obtained.

[0069] Based on the above method, the central tower crane and the initial analysis model corresponding to the central tower crane are determined through multi-source data, and then the model is fine-tuned based on the data of each tower crane itself. The structural state analysis model adapted to each tower crane can be obtained more quickly. At the same time, the preprocessing of multi-source data improves the accuracy of the subsequent use of the model.

[0070] In addition, in addition to fine-tuning the initial analysis model to obtain the structural state analysis model adapted to all tower cranes included, it is also used to subsequently obtain the structural state analysis model that matches the target tower crane, that is, to obtain the target analysis model. Specifically, the initial analysis model is fine-tuned based on the simulation results obtained by the simulation to obtain the target analysis model that matches the target tower crane. Therefore, referring to Figure 4 , Figure 4 It is a flowchart of the steps of obtaining the target analysis model provided in an embodiment of the present application, wherein the steps include steps 401 to 407.

[0071] Step 401, obtaining a first model, a second model and a third model in a currently configured model set, wherein the first model matches the first tower crane, the second model matches the second tower crane and the third model matches the third tower crane, and the model set includes at least the first model, the second model and the third model;

[0072] Step 402, obtaining a first tower crane feature of the first tower crane, a second tower crane feature of the second tower crane, and a third tower crane feature of the third tower crane, and performing feature analysis to obtain a first feature difference between the first tower crane feature and the second tower crane feature, a second feature difference between the second tower crane feature and the third tower crane feature, and a third feature difference between the third tower crane feature and the first tower crane feature;

[0073] Step 403, performing difference fusion on the first feature difference, the second feature difference and the third feature difference to obtain a fusion difference feature;

[0074] Step 404, optimizing the tower crane features of the target tower crane based on the fused difference features to obtain optimized tower crane features;

[0075] Step 405, inputting the optimized tower crane features into the first model, the second model and the third model respectively, obtaining the first predicted tower crane information, the second predicted tower crane information and the third predicted tower crane information, and performing information fusion to obtain the predicted sensor data of the target tower crane;

[0076] Step 406, loading the initial analysis model, and performing model migration on the initial analysis model according to the simulation results to obtain the migrated initial analysis model;

[0077] Step 407 , optimizing the migrated initial analysis model based on the tower crane characteristics and the predicted sensor data, and obtaining a target analysis model that matches the target tower crane when the optimization is completed.

[0078] Specifically, when the initial analysis model is migrated and fine-tuned based on the simulation results, the first model, the second model and the third model are obtained in the currently configured model combination, wherein the first model matches the first tower crane, the second model matches the second tower crane, and the third model matches the third tower crane, and the model set at least includes the first model, the second model and the third model, and then the first tower crane feature of the first tower crane, the second tower crane feature of the second tower crane and the third tower crane feature of the third tower crane are obtained, and then feature analysis processing is performed to obtain feature differences between the two tower cranes, including the first feature difference between the first tower crane and the second tower crane, the second feature difference between the second tower crane and the third tower crane, and the third tower crane difference between the third tower crane and the first tower crane, and then the obtained three tower crane differences are subjected to difference fusion to obtain fused difference features, and then the tower crane features of the target tower crane are feature optimized based on the fused difference features to obtain optimized tower crane features.

[0079] Based on the process of obtaining the structural state analysis model recorded above, after completing the training based on the simulation results, it is necessary to train the model obtained based on the simulation results again based on the tower crane information of the tower crane itself, that is, after completing the data migration of the initial analysis model, it is necessary to train the initial analysis model after completing the data migration based on the tower crane data itself. Therefore, after loading the initial analysis model, in addition to the need to migrate the data, it is also necessary to obtain the tower crane data adapted to the target tower crane, and when obtaining the tower crane data of the target tower crane, the optimized tower crane features based on the standard tower crane are analyzed to obtain the input data for training the migrated initial analysis model. At this time, the optimized tower crane features are respectively input into the first model, the second model and the third model to obtain the first predicted tower crane information, the second predicted tower crane information and the third predicted tower crane information, and the predicted sensor data of the target tower crane is obtained by fusing the predicted tower crane information, and finally the migrated initial analysis model is further optimized using the tower crane features and the predicted sensor data of the target tower crane to obtain the target analysis model matching the target tower crane when the optimization process is completed.

[0080] In actual application, by analyzing the feature differences between tower cranes, the differences in sensor data under different feature differences are obtained, and then the differences in sensor data under different feature differences are used to predict the sensor data of the target tower crane. In the case of unknown tower crane information, the sensor data of the target tower crane can be analyzed based on the differences in tower crane features, and then the initial analysis model after migration can be further fine-tuned based on the sensor data, thereby improving the versatility of the model.

[0081] It should be noted that the number of models included in the model set can be more than three, and the number of models selected for differential analysis can be more than three, and can be four, five, or even more. The more models analyzed, the more accurate the differentiated information obtained, that is, the better the accuracy of the target analysis model that matches the target tower crane. The specific number of models used is determined based on actual needs.

[0082] Furthermore, after obtaining the first model, the second model and the third model, in addition to determining the target analysis model matching the target tower crane by analyzing the differences in features and sensor data, the target analysis model can also be obtained by analyzing the feature differences and model differences. Figure 5 , Figure 5 This is another flowchart diagram of the steps of obtaining the target analysis model provided in an embodiment of the present application, wherein the steps include steps 501 to 503.

[0083] Step 501, performing model difference analysis on the first model and the second model, the second model and the third model, and the third model and the first model, and analyzing the obtained model differences to obtain a model difference optimization index;

[0084] Step 502, adjusting the first model, the second model, and the third model based on the model difference optimization index and the feature difference to obtain the adjusted first model, the second model, and the third model, wherein the feature difference includes the first feature difference, the second feature difference, and the third feature difference;

[0085] Step 503, performing model fusion based on the adjusted first model, the adjusted second model and the adjusted third model, and training the fused model based on the tower crane characteristics to obtain a target analysis model that matches the target tower crane.

[0086] Specifically, after obtaining the first model, the second model and the third model, the model differentiation between the two models can be analyzed. By comparing the models, the first model difference index between the first model and the second model, the second model difference index between the second model and the third model, and the third model difference index between the third model and the first model can be obtained. The model difference index is analyzed to obtain the model difference optimization index. Then, the model difference optimization index and the first feature difference, the second feature difference and the third feature difference are used to optimize and adjust the first model, the second model and the third model respectively to obtain the adjusted first model, the second model and the third model. Finally, the adjusted first model, the second model and the third model are fused and the model obtained after the fusion processing is trained by using the tower crane characteristics of the target tower crane to obtain a target analysis model matching the target tower crane.

[0087] Exemplarily, the difference between models is mainly reflected in the difference in model parameters, and the difference in model parameters will lead to different analysis results. By performing model differentiation analysis on the selected first model, second model and third model, the difference in models under different tower crane characteristics can be obtained. Based on the combination of model differences and feature differences, the impact of different features on the model can be analyzed. Then, when obtaining the target analysis model that matches the target tower crane, the first model, second model and third model are fused based on the feature differences and model differences. Finally, the model is optimized using the tower crane characteristics of the target tower crane to obtain the target analysis model.

[0088] Step 105, input tower crane information into the target analysis model, and output the health monitoring result of the target tower crane.

[0089] In one embodiment, after obtaining a target analysis model that matches the target tower crane, the acquired tower crane information is input into the target analysis model to output a health monitoring result of the target tower crane.

[0090] Exemplarily, the health monitoring results obtained by analyzing based on the target analysis model are the same as the analysis results recorded above. When the analysis result is no damage, the no damage result is output; when the analysis result is damage, the damage location and the damage offset value are output, and a damage analysis report is generated based on the damage offset value, and the damage analysis report at least includes the damage risk value.

[0091] Further, refer to Figure 6 , Figure 6 It is another flow chart of the steps of the tower crane structure health monitoring method provided in an embodiment of the present application.

[0092] Specifically, when conducting a health and safety analysis of a tower crane at a construction site, it includes:

[0093] S1: Data collection.

[0094] By installing a variety of sensors (weight sensor, amplitude sensor, height sensor, angle sensor, tower crane top displacement sensor, inclination sensor, etc.) on tower crane A, tower crane B and other tower cranes, multi-source data is collected in real time, and the collected tower crane data is preprocessed, including data cleaning, denoising, normalization and other processing to improve data quality, and divide the fine-tuning training data and test data.

[0095] S2: Get the simulation data of tower crane A.

[0096] A simulation model of the target tower crane A is established, and simulation modeling is performed on tower cranes under various working conditions (different lifting weights, trolley amplitude changes, rotation angles, etc.) and different structural damage conditions (different main limbs, different degrees of damage). Sufficient and complete simulation data of tower crane A is generated, including intact data and various damage data.

[0097] S3: Modeling based on the simulation data of tower crane A to obtain an intelligent identification model M1 based on the simulation data.

[0098] Based on the simulation data in S2, deep learning modeling is performed to build an intelligent identification model M1 for simulation data under complex working conditions and different damage conditions.

[0099] S4: Model fine-tuning of the intelligent identification model M1.

[0100] A small amount of measured data of tower crane A in S1 is used to fine-tune the intelligent identification model M1 obtained in S3 to generate an intelligent health status identification model M2 based on the measured data of tower crane A. The obtained model M2 can be used to analyze and diagnose the real-time health status of tower crane A.

[0101] S5: Get simulation data of tower crane B.

[0102] A simulation model of the target tower crane B is established, and simulation modeling is performed on tower cranes under various working conditions (different lifting weights, trolley amplitude changes, rotation angles, etc.) and different structural damage conditions (different main limbs, different degrees of damage). A small amount of simulation data of tower crane B is generated, including intact data and various damage data.

[0103] S6: Based on the simulation data of tower crane B, the intelligent recognition model M1 of tower crane A under the simulation data is subjected to model migration and fine-tuning processing.

[0104] The intelligent identification model M1 obtained in S3 is migrated and fine-tuned using the simulation data of tower crane B in S5 to generate an intelligent identification model M3 for the simulation data under complex working conditions and different damage conditions of tower crane B.

[0105] S7: Fine-tuning of the intelligent identification model M3.

[0106] The intelligent identification model M3 obtained in S6 is migrated and fine-tuned using a small amount of measured data of tower crane B in S1 to generate an intelligent health status identification model M4 based on the measured data of tower crane B, which can realize real-time diagnosis of the health status of tower crane B.

[0107] In summary, the present application discloses a method for health monitoring of a tower crane structure. When performing health monitoring of a tower crane structure, the tower crane information of the target tower crane to be monitored is obtained, including sensor data collected by the set sensor, tower crane working conditions and tower crane characteristics. Then, according to the tower crane identification in the tower crane characteristics, it is determined whether there is a structural state analysis model that matches the target tower crane. When it is determined that there is no such model, a tower crane simulation model of the target tower crane is constructed to simulate the data, and the simulation result corresponding to the target tower crane is obtained. Then, the pre-trained initial analysis model is loaded to perform model migration and fine-tuning to obtain a target analysis model suitable for health analysis of the target tower crane. Finally, the tower crane information is input into the target analysis model to output the health monitoring result of the target tower crane. When performing real-time monitoring of the structural health of the tower crane, the accuracy of monitoring and analysis is improved by integrating multi-distance data. At the same time, the efficiency of model training is improved based on data migration, and tower cranes of different specifications can be quickly adapted, thereby improving the safety of tower crane operations.

[0108] According to the method described in the above embodiment, this embodiment will be further described from the perspective of a health monitoring device for a tower crane structure. The health monitoring device for a tower crane structure can be implemented as an independent entity or integrated into an electronic device, such as a terminal. The terminal may include a mobile phone, a tablet computer, etc.

[0109] See also Figure 7 , Figure 7 is a structural schematic diagram of a health monitoring device for a tower crane structure provided in an embodiment of the present application, such as Figure 7 As shown, the health monitoring device 700 of the tower crane structure provided in the embodiment of the present application includes:

[0110] The information acquisition module 701 is used to acquire the tower crane information of the target tower crane, wherein the tower crane information includes sensor data and tower crane characteristics collected in real time by various sensors installed on the target tower crane, and the tower crane characteristics include tower crane identification and tower crane structural characteristics;

[0111] A matching judgment module 702 is used to determine whether there is a structural state analysis model that matches the target tower crane based on the tower crane identifier of the target tower crane;

[0112] The data simulation module 703 is used to construct a tower crane simulation model of the target tower crane when it is determined that there is no structural state analysis model that does not match the target tower crane, and simulate the tower crane simulation model based on the simulation data to obtain a simulation result of the target tower crane, wherein the simulation data is working condition data and the simulation result is damage data;

[0113] A model fine-tuning module 704 is used to load the initial analysis model and perform model migration fine-tuning on the initial analysis model based on the simulation results to obtain a target analysis model that matches the target tower crane;

[0114] The analysis and prediction module 705 is used to input the tower crane information into the target analysis model and output the health monitoring result of the target tower crane.

[0115] In one embodiment, the health monitoring device 700 for the tower crane structure further includes a first training module for:

[0116] Acquire real-time tower crane information of each tower crane in the construction site, wherein the real-time tower crane information includes tower crane characteristics of each tower crane and sensor data collected by each sensor of each tower crane when it is running, and the sensor data is used to determine the tower crane working condition of the tower crane;

[0117] Conduct data analysis on real-time tower crane information and identify the central tower crane among all tower cranes;

[0118] Establishing a central simulation model of a central tower crane and setting initial simulation data of the central tower crane, and simulating the central simulation model based on the initial simulation data to obtain an initial simulation result of the central tower crane, wherein the initial simulation data is the working condition data of the central tower crane, and the initial simulation result is the damage data of the central tower crane;

[0119] The constructed initial model is trained based on the initial simulation results to obtain a central simulation analysis model corresponding to the central tower crane, and the central simulation analysis model is used as the initial analysis model.

[0120] In one embodiment, the first training module is further used for:

[0121] Acquire tower crane features in real-time tower crane information, and perform clustering processing on the tower crane features to obtain a first cluster center point corresponding to each tower crane;

[0122] Analyze the first cluster center point to determine a second cluster center point of the first cluster center point;

[0123] The distance between the first cluster center point and the second cluster center point is calculated, and the tower crane to which the first cluster center point corresponding to the minimum distance value belongs is taken as the central tower crane.

[0124] In one embodiment, the health monitoring device 700 for the tower crane structure further includes a second training module for:

[0125] Acquire first real-time tower crane information of a first tower crane in the real-time tower crane information, wherein the first tower crane is a tower crane in a construction site, and the construction site includes a plurality of tower cranes;

[0126] Fine-tune the initial analysis model based on the first real-time tower crane information to obtain a first structural state analysis model that matches the first tower crane, and mark the first structural state analysis model based on the tower crane identifier of the first tower crane;

[0127] Second real-time tower crane information of the second tower crane is obtained from the real-time tower crane information, and the initial analysis model is fine-tuned based on the second real-time tower crane information to obtain a second structural state analysis model matching the second tower crane, so as to obtain the structural state analysis model of each tower crane in the construction site.

[0128] In one embodiment, the matching determination module 702 is further configured to:

[0129] Acquire the currently configured structural state analysis model, and identify the adaptation identifier of the tower crane adapted by the configured structural state analysis model;

[0130] Matching the tower crane identification with the adaptation identification to determine whether the tower crane identification is included in the adaptation identification;

[0131] If it is determined that the tower crane identifier is not included in the adaptation identifier, it is determined that there is no structural state analysis model that matches the target tower crane;

[0132] If it is determined that the tower crane identifier is included in the adaptation identifier, it is determined that there is a structural state analysis model that matches the target tower crane.

[0133] In one embodiment, the model fine-tuning module 704 is further configured to:

[0134] Acquire a first model, a second model and a third model in a currently configured model set, wherein the first model matches the first tower crane, the second model matches the second tower crane and the third model matches the third tower crane, and the model set includes at least the first model, the second model and the third model;

[0135] Acquire a first tower crane feature of the first tower crane, a second tower crane feature of the second tower crane, and a third tower crane feature of the third tower crane, and obtain a first feature difference between the first tower crane feature and the second tower crane feature, a second feature difference between the second tower crane feature and the third tower crane feature, and a third feature difference between the third tower crane feature and the first tower crane feature by performing feature analysis;

[0136] Performing differential fusion on the first feature difference, the second feature difference and the third feature difference to obtain a fusion difference feature;

[0137] Based on the fusion difference features, the tower crane features of the target tower crane are optimized to obtain the optimized tower crane features;

[0138] The optimized tower crane features are respectively input into the first model, the second model and the third model to obtain the first predicted tower crane information, the second predicted tower crane information and the third predicted tower crane information, and the information is fused to obtain the predicted sensor data of the target tower crane;

[0139] Loading the initial analysis model, and performing model migration on the initial analysis model according to the simulation results to obtain the migrated initial analysis model;

[0140] The migrated initial analysis model is optimized based on the tower crane characteristics and predicted sensor data, and a target analysis model matching the target tower crane is obtained when the optimization is completed.

[0141] In one embodiment, the model fine-tuning module 704 is further configured to:

[0142] Performing model difference analysis between the first model and the second model, between the second model and the third model, and between the third model and the first model, and analyzing the obtained model differences to obtain a model difference optimization index;

[0143] Based on the model difference optimization index and the feature difference, the first model, the second model and the third model are respectively adjusted to obtain the adjusted first model, the second model and the third model, wherein the feature difference includes the first feature difference, the second feature difference and the third feature difference;

[0144] Model fusion is performed based on the adjusted first model, the adjusted second model and the adjusted third model, and the fused model is trained based on the tower crane characteristics to obtain a target analysis model that matches the target tower crane.

[0145] Also, see Figure 8 , Figure 8 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application, and the electronic device may be a mobile terminal such as a smart phone, a tablet computer, or the like. Figure 8 As shown, the electronic device 800 includes a processor 801 and a memory 802. The processor 801 is electrically connected to the memory 802.

[0146] The processor 801 is the control center of the electronic device 800. It uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device 800 and processes data by running or loading applications stored in the memory 802 and calling data stored in the memory 802, thereby monitoring the electronic device 800 as a whole.

[0147] In this embodiment, the processor 801 in the electronic device 800 will load the instructions corresponding to the processes of one or more applications into the memory 802 according to the following steps, and the processor 801 will run the application stored in the memory 802, thereby implementing any step in the tower crane structure health monitoring method provided in the above embodiment.

[0148] The electronic device 800 can implement the steps in any embodiment of the tower crane structure health monitoring method provided in the embodiments of the present application. Therefore, it can achieve the beneficial effects that can be achieved by any tower crane structure health monitoring method provided in the embodiments of the present application. Please refer to the previous embodiments for details and will not be repeated here.

[0149] See also Fig. 9 , Fig. 9 is another structural schematic diagram of an electronic device provided in an embodiment of the present application, such as Fig. 9 As shown, Fig. 9 The specific structural block diagram of the electronic device provided in the embodiment of the present application is shown, and the electronic device can be used to implement the health monitoring method of the tower crane structure provided in the above embodiment. The electronic device 900 can be a mobile terminal such as a smart phone or a laptop computer.

[0150] The RF circuit 910 is used to receive and send electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, and thus communicate with a communication network or other devices. The RF circuit 910 may include various existing circuit elements for performing these functions, such as antennas, radio frequency transceivers, digital signal processors, encryption / decryption chips, user identity module (SIM) cards, memories, etc. The RF circuit 910 can communicate with various networks such as the Internet, corporate intranets, wireless networks, or communicate with other devices through wireless networks. The above-mentioned wireless networks may include cellular telephone networks, wireless local area networks, or metropolitan area networks. The above-mentioned wireless networks may use various communication standards, protocols and technologies, including but not limited to Global System for Mobile Communication (GSM), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (WCDMA), Code Division Access (CDMA), Time Division Multiple Access (TDMA), Wireless Fidelity (Wi-Fi) (such as Institute of Electrical and Electronics Engineers standards IEEE 802.11a, IEEE 802.11b, IEEE802.11g and / or IEEE802.11n), Voice over Internet Protocol (VoIP), Worldwide Interoperability for Microwave Access (Wi-Max), other protocols for email, instant messaging and short messages, and any other suitable communication protocols, even those that have not yet been developed.

[0151] The memory 920 can be used to store software programs and modules, such as the program instructions / modules corresponding to the health monitoring method of the tower crane structure in the above-mentioned embodiment. The processor 980 executes various functional applications and the health monitoring method of the tower crane structure by running the software programs and modules stored in the memory 920.

[0152] The memory 920 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 920 may further include a memory remotely arranged relative to the processor 980, and these remote memories may be connected to the electronic device 900 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0153] The input unit 930 can be used to receive uploaded digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. Specifically, the input unit 930 may include a touch-sensitive surface 931 and other input devices 932. The touch-sensitive surface 931, also known as a touch display screen or touchpad, can collect user touch operations on or near it (such as operations performed by users using fingers, styluses, or any other suitable objects or accessories on or near the touch-sensitive surface 931), and drive corresponding connection devices according to a pre-set program. Optionally, the touch-sensitive surface 931 may include a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 980, and can receive and execute commands sent by the processor 980. In addition, the touch-sensitive surface 931 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface 931, the input unit 930 may further include other input devices 932. Specifically, the other input devices 932 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like.

[0154] The display unit 940 can be used to display information input by the user or information provided to the user and various graphical user interfaces of the electronic device 900, which can be composed of graphics, text, icons, videos and any combination thereof. The display unit 940 may include a display panel 941, and optionally, the display panel 941 may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. Further, the touch-sensitive surface 931 may cover the display panel 941, and when the touch-sensitive surface 931 detects a touch operation on or near it, it is transmitted to the processor 980 to determine the type of the touch event, and then the processor 980 provides corresponding visual output on the display panel 941 according to the type of the touch event. Although in the figure, the touch-sensitive surface 931 and the display panel 941 are implemented as two independent components to implement input and output functions, in some embodiments, the touch-sensitive surface 931 and the display panel 941 can be integrated to implement input and output functions.

[0155] The electronic device 900 may also include at least one sensor 950, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 941 according to the brightness of the ambient light, and the proximity sensor may generate an interrupt when the flip cover is closed or closed. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the posture of the mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; As for other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that can also be configured in the electronic device 900, they will not be repeated here.

[0156] The audio circuit 960, the speaker 961, and the microphone 962 can provide an audio interface between the user and the electronic device 900. The audio circuit 960 can transmit the electrical signal converted from the received audio data to the speaker 961, which is converted into a sound signal for output; on the other hand, the microphone 962 converts the collected sound signal into an electrical signal, which is received by the audio circuit 960 and converted into audio data, and then the audio data is output to the processor 980 for processing, and then sent to another terminal through the RF circuit 910, or the audio data is output to the memory 920 for further processing. The audio circuit 960 may also include an earplug jack to provide communication between an external headset and the electronic device 900.

[0157] The electronic device 900 can help users receive requests, send information, etc. through the transmission module 970 (such as a Wi-Fi module), which provides users with wireless broadband Internet access. Although the transmission module 970 is shown in the figure, it can be understood that it is not a necessary component of the electronic device 900 and can be omitted as needed without changing the essence of the invention.

[0158] The processor 980 is the control center of the electronic device 900. It uses various interfaces and lines to connect various parts of the entire mobile phone. By running or executing software programs and / or modules stored in the memory 920, and calling data stored in the memory 920, it executes various functions of the electronic device 900 and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 980 may include one or more processing cores; in some embodiments, the processor 980 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communications. It can be understood that the above-mentioned modem processor may not be integrated into the processor 980.

[0159] The electronic device 900 also includes a power supply 990 (such as a battery) for supplying power to various components. In some embodiments, the power supply can be logically connected to the processor 980 through a power management system, so that the power management system can manage charging, discharging, and power consumption management. The power supply 990 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0160] Although not shown, the electronic device 900 also includes a camera (such as a front camera, a rear camera), a Bluetooth module, etc., which will not be described in detail here. Specifically in this embodiment, the display unit of the electronic device is a touch screen display, and the mobile terminal also includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and are configured to be executed by one or more processors to implement any step of the health monitoring method of the tower crane structure provided in the above embodiment.

[0161] In specific implementation, the above modules can be implemented as independent entities, or can be arbitrarily combined and implemented as the same or several entities. The specific implementation of the above modules can be found in the previous method embodiments, which will not be repeated here.

[0162] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling related hardware through instructions, and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. To this end, an embodiment of the present application provides a storage medium, which stores a plurality of instructions, and when the instructions are executed by the processor, any step in the health monitoring method of the tower crane structure provided in the above embodiments can be implemented.

[0163] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0164] Since the instructions stored in the storage medium can execute the steps in any embodiment of the health monitoring method for the tower crane structure provided in the embodiments of the present application, the beneficial effects that can be achieved by any tower crane structure health monitoring method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0165] The above is a detailed introduction to a tower crane structure health monitoring method, device, electronic device and storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and its core idea of ​​the present application. At the same time, for technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application. Moreover, for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made, and these improvements and modifications are also regarded as the protection scope of the present application.

Claims

1. A tower crane structure health monitoring method, characterized in that: include: Acquire tower crane information of a target tower crane, wherein the tower crane information includes sensor data and tower crane characteristics collected in real time by various sensors arranged on the target tower crane, and the tower crane characteristics include a tower crane identification and tower crane structural characteristics; Based on the tower crane identification of the target tower crane, determining whether there is a structural state analysis model matching the target tower crane; When it is determined that there is no structural state analysis model matching the target tower crane, a tower crane simulation model of the target tower crane is constructed, and the tower crane simulation model is simulated based on simulation data to obtain a simulation result of the target tower crane, wherein the simulation data is working condition data and the simulation result is damage data; Loading an initial analysis model, and performing model migration fine-tuning on the initial analysis model based on the simulation results to obtain a target analysis model that matches the target tower crane; Inputting the tower crane information into the target analysis model, and outputting the health monitoring result of the target tower crane; The training step of the initial analysis model includes: Acquire real-time tower crane information of each tower crane in the construction site, wherein the real-time tower crane information includes tower crane characteristics of each tower crane and sensor data collected by each sensor of each tower crane when the tower crane is running, and the sensor data is used to determine the tower crane working condition of the tower crane; Performing data analysis on the real-time tower crane information to determine a central tower crane among all tower cranes; Establishing a central simulation model of the central tower crane and setting initial simulation data of the central tower crane, and simulating the central simulation model based on the initial simulation data to obtain an initial simulation result of the central tower crane, wherein the initial simulation data is the working condition data of the central tower crane, and the initial simulation result is the damage data of the central tower crane; The constructed initial analysis model is trained based on the initial simulation result to obtain a central simulation analysis model corresponding to the central tower crane, and the central simulation analysis model is used as the initial analysis model.

2. The method according to claim 1, characterized in that The performing data analysis on the real-time tower crane information to determine the central tower crane among all tower cranes includes: Acquire tower crane features in the real-time tower crane information, and perform clustering processing on the tower crane features to obtain a first cluster center point corresponding to each tower crane; Analyze the first cluster center point to determine a second cluster center point of the first cluster center point; The distance between the first cluster center point and the second cluster center point is calculated, and the tower crane to which the first cluster center point corresponding to the minimum distance value belongs is taken as the central tower crane.

3. The method according to claim 1, characterized in that The training step of the structural state analysis model comprises: Acquire first real-time tower crane information of a first tower crane from the real-time tower crane information, wherein the first tower crane is a tower crane in the construction site, and the construction site includes a plurality of tower cranes; Fine-tune the initial analysis model based on the first real-time tower crane information to obtain a first structural state analysis model that matches the first tower crane, and mark the first structural state analysis model based on the tower crane identifier of the first tower crane; Second real-time tower crane information of a second tower crane is obtained from the real-time tower crane information, and the initial analysis model is fine-tuned based on the second real-time tower crane information to obtain a second structural state analysis model matching the second tower crane, so as to obtain the structural state analysis model of each tower crane in the construction site.

4. The method according to claim 1, characterized in that The determining whether there is a structural state analysis model matching the target tower crane based on the tower crane identification of the target tower crane comprises: Acquire the currently configured structural state analysis model, and identify the adaptation identifier of the tower crane adapted by the configured structural state analysis model; Matching the tower crane identifier with the adaptation identifier to determine whether the tower crane identifier is included in the adaptation identifier; If it is determined that the tower crane identifier is not included in the adaptation identifier, it is determined that there is no structural state analysis model that matches the target tower crane; If it is determined that the tower crane identifier is included in the adaptation identifier, it is determined that there is a structural state analysis model that matches the target tower crane.

5. The method according to claim 1, characterized in that The loading of the initial analysis model and fine-tuning of the initial analysis model through model migration based on the simulation result to obtain a target analysis model matching the target tower crane include: Acquire a first model, a second model and a third model from a currently configured model set, wherein the first model matches the first tower crane, the second model matches the second tower crane, and the third model matches the third tower crane, and the model set includes at least the first model, the second model and the third model; Acquire a first tower crane feature of the first tower crane, a second tower crane feature of the second tower crane, and a third tower crane feature of the third tower crane, and obtain a first feature difference between the first tower crane feature and the second tower crane feature, a second feature difference between the second tower crane feature and the third tower crane feature, and a third feature difference between the third tower crane feature and the first tower crane feature by performing feature analysis; Performing differential fusion on the first feature difference, the second feature difference and the third feature difference to obtain a fused difference feature; Based on the fused difference features, feature optimization is performed on the tower crane features of the target tower crane to obtain optimized tower crane features; Inputting the optimized tower crane features into the first model, the second model and the third model respectively, obtaining first predicted tower crane information, second predicted tower crane information and third predicted tower crane information, and performing information fusion to obtain predicted sensor data of the target tower crane; Loading an initial analysis model, and performing model migration on the initial analysis model according to the simulation result to obtain a migrated initial analysis model; The migrated initial analysis model is optimized based on the tower crane characteristics and the predicted sensor data, and a target analysis model matching the target tower crane is obtained when the optimization is completed.

6. The method according to claim 5, characterized in that The method further comprises: Performing model difference analysis on the first model and the second model, the second model and the third model, and the third model and the first model, and analyzing the obtained model differences to obtain a model difference optimization index; Based on the model difference optimization index and the feature difference, the first model, the second model and the third model are respectively adjusted to obtain the adjusted first model, the second model and the third model, wherein the feature difference includes the first feature difference, the second feature difference and the third feature difference; Model fusion is performed based on the adjusted first model, the adjusted second model and the adjusted third model, and the fused model is trained based on the tower crane characteristics to obtain a target analysis model that matches the target tower crane.

7. A health monitoring device for a tower crane structure, used to implement the health monitoring method for a tower crane structure as claimed in claim 1, characterized in that: include: An information acquisition module is used to acquire tower crane information of a target tower crane, wherein the tower crane information includes sensor data and tower crane features collected in real time by various sensors arranged on the target tower crane, and the tower crane features include a tower crane identification and tower crane structural characteristics; A matching judgment module, used for determining whether there is a structural state analysis model matching the target tower crane based on the tower crane identification of the target tower crane; A data simulation module is used for constructing a tower crane simulation model of the target tower crane when it is determined that there is no structural state analysis model matching the target tower crane, and simulating the tower crane simulation model based on simulation data to obtain a simulation result of the target tower crane, wherein the simulation data is working condition data and the simulation result is damage data; A model fine-tuning module is used to load an initial analysis model and perform model migration fine-tuning on the initial analysis model based on the simulation results to obtain a target analysis model that matches the target tower crane; The analysis and prediction module is used to input the tower crane information into the target analysis model and output the health monitoring result of the target tower crane.

8. An electronic device, characterized in that: The electronic device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the steps in the method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 6 are implemented.

Images