Model training method, engineering machinery monitoring method, computing equipment and storage medium
Through the combination of data prediction agent model and twin three-dimensional model, the problem of the inability to obtain accurate stress and displacement data by using engineering machinery for a long time is solved, and efficient and accurate data monitoring and real-time rendering are achieved.
Patent Information
- Application Number
- CN202411665040.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-20
- Publication Date
- 2025-03-11
AI Technical Summary
In the prior art, long-term use of construction machinery cannot obtain accurate stress and displacement data, resulting in the inability to provide reliable quality monitoring.
By obtaining real-time operation data of the engineering machinery, input it to the data prediction agent model to obtain the predicted target data, including stress and/or displacement. A three-dimensional twin model of construction machinery is constructed, and rendered based on the predicted target data to generate a data twin image.
There is no need to set up a sensor, which avoids problems such as zero point drift of the sensor, and can accurately obtain stress and displacement data of long-term use of engineering machinery. The data prediction agent model has high prediction efficiency, few computing resources, and the rendered data twin images have high real-time performance.
Smart Images
Figure CN119598634A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of equipment detection technology, and specifically to a model training method, an engineering machinery monitoring method, a computing device and a storage medium. Background Art
[0002] With the rapid development of engineering machinery manufacturing technology, engineering machinery is widely used in various scenarios. After engineering machinery such as tower cranes are put into use, fatigue damage to the structure of the components is likely to occur due to the fact that some structures of the components are weak points in terms of static strength and fatigue strength, as well as the difference between the actual use conditions and the preset use conditions. Usually, a variety of sensors are installed at the key components of engineering machinery to detect data such as displacement and stress during the operation of the engineering machinery. The remaining life of the engineering machinery is predicted based on the data detected by the sensors to obtain the quality analysis results of the engineering machinery and avoid safety accidents.
[0003] However, the stress sensors and acceleration sensors installed in the key parts of engineering machinery are sensitive devices, and the deformable parts such as stress sheets included in the sensors themselves will also suffer fatigue damage. As the working time of the sensor to collect signals continues to accumulate, the signals collected by the sensor will usually drift, thereby affecting the measurement accuracy of data such as stress and displacement. It is impossible to obtain accurate displacement and stress data for engineering machinery that has been used for a long time, and it is difficult to provide reliable quality monitoring for the engineering machinery put into use. Summary of the invention
[0004] The purpose of the embodiments of the present application is to provide a model training method, an engineering machinery monitoring method, a computing device and a storage medium, so as to solve the problem in the prior art that accurate data cannot be obtained for engineering machinery that has been used for a long time.
[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a construction machinery monitoring method, which includes:
[0006] Obtain real-time operation data of construction machinery;
[0007] Inputting the real-time operation data of the construction machinery into the data prediction agent model to obtain the predicted target data of the construction machinery output by the data prediction agent model, wherein the predicted target data includes stress and / or displacement;
[0008] Construct twin 3D models of construction machinery;
[0009] Based on the predicted target data, the twin 3D model is rendered to obtain the data twin image of the construction machinery.
[0010] In an embodiment of the present application, the construction machinery monitoring method further includes:
[0011] At least one of fatigue damage monitoring results, target data monitoring results, digital inspection recommendation results and maintenance recommendation results of the engineering machinery is obtained according to the predicted target data.
[0012] In an embodiment of the present application, the real-time operation data of the construction machinery is input into the data prediction agent model to obtain the predicted target data of the construction machinery output by the data prediction agent model, including:
[0013] Preprocessing the real-time operation data of the construction machinery to obtain preprocessed operation data;
[0014] Cleaning the preprocessed operation data to obtain cleaned operation data;
[0015] The cleaned operating data is input into the data prediction agent model to obtain the predicted target data of the construction machinery output by the data prediction agent model.
[0016] In the embodiment of the present application, the data prediction agent model is obtained by the following steps:
[0017] Constructing a relational database between operation data of an engineering machine and target data, wherein the engineering machine includes a plurality of components and the target data includes stress and / or displacement of the components;
[0018] Based on the relational database, a first proxy model of each component is obtained respectively;
[0019] Assembling all the first proxy models to obtain a second proxy model of the construction machinery;
[0020] The second agent model is trained to obtain a data prediction agent model for construction machinery.
[0021] In an embodiment of the present application, a relationship database between operation data of engineering machinery and target data is constructed, including:
[0022] Construct a rigid-flexible coupling dynamics simulation model for construction machinery;
[0023] The rigid-flexible coupling dynamics simulation model is used to perform simulation based on the operation data of the engineering machinery to obtain the load data of each target component, wherein the target component is the component whose target data is to be predicted;
[0024] Constructing finite element simulation models of each target component respectively;
[0025] For each target component, a finite element simulation model corresponding to the target component is used to perform simulation based on the load data to obtain simulation target data of the target component;
[0026] According to the operation data and the simulation target data of each target component, a relational database between the operation data and the target data of the construction machinery is constructed.
[0027] In an embodiment of the present application, a rigid-flexible coupling dynamics simulation model of an engineering machinery is constructed, including:
[0028] Based on the geometric data of construction machinery, the rigid body dynamics model and flexible body dynamics model of construction machinery are constructed;
[0029] Based on the control system data of construction machinery, establish the control system simulation model of construction machinery;
[0030] The rigid body dynamics model, the flexible body dynamics model and the control system simulation model are coupled and simulated to obtain a rigid-flexible coupling dynamics simulation model of the construction machinery.
[0031] In the embodiment of the present application, a rigid-flexible coupling dynamics simulation model is used to perform simulation based on the operation data of the engineering machinery to obtain the load data of each target component, including:
[0032] Calibrate the rigid-flexible coupling dynamics simulation model and determine the calibrated accuracy of the rigid-flexible coupling dynamics simulation model;
[0033] When the accuracy after calibration is greater than the preset accuracy, the rigid-flexible coupling dynamics simulation model is used to perform simulation based on the operation data of the construction machinery to obtain the load data of each component.
[0034] In the embodiment of the present application, based on the relational database, a first proxy model of each component is obtained respectively, including:
[0035] Determine the initial neural network for each component;
[0036] Based on the relational database, the initial neural network of each component is trained separately to obtain the first proxy model of each component.
[0037] A second aspect of the present application provides a computing device, including:
[0038] a memory configured to store instructions;
[0039] The processor is configured to call instructions from the memory and implement the above-mentioned construction machinery monitoring method when executing the instructions.
[0040] A third aspect of the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned engineering machinery monitoring method.
[0041] The present application provides a method for monitoring construction machinery, including: obtaining real-time operation data of construction machinery; inputting the real-time operation data of construction machinery into a data prediction agent model to obtain predicted target data of construction machinery output by the data prediction agent model; constructing a twin three-dimensional model of construction machinery; based on the predicted target data, rendering the twin three-dimensional model to obtain a data twin image of the construction machinery. By using the constructed data prediction agent model to obtain data such as stress and displacement of construction machinery, since there is no need to set up sensors, the zero drift of sensors is avoided, and accurate stress and displacement can be obtained for construction machinery that is used for a long time. At the same time, the data prediction agent model has high prediction efficiency and requires less computing resources, and can quickly obtain the stress and displacement of construction machinery, thereby making the rendered data twin image highly real-time.
[0042] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:
[0044] Figure 1 A schematic diagram of a flow chart of a method for monitoring construction machinery according to an embodiment of the present application is schematically shown;
[0045] Figure 2 An example diagram of a data twin image according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION
[0046] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0047] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.
[0048] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.
[0049] Figure 1 The following schematically shows a flow chart of a method for monitoring construction machinery according to an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a construction machinery monitoring method, which may include the following steps:
[0050] S110, acquiring real-time operation data of the construction machinery.
[0051] The type of engineering machinery is set according to actual needs and is not limited here. For ease of understanding, the engineering machinery in the embodiment of the present application is a tower crane. According to the structure, load transfer path and strength verification results of the tower crane, the main load-bearing components and dangerous components of the main tower crane are determined as key components.
[0052] Acquire the real-time operation data of the construction machinery. The type of operation data is set according to actual needs, and can include the tower crane's lifting weight, amplitude, height, rotation speed, wind speed and wind direction, etc., which are not limited here. Perform fatigue damage analysis on key components based on the real-time operation data of the construction machinery.
[0053] S120, inputting the real-time operation data of the construction machinery into the data prediction agent model to obtain the predicted target data of the construction machinery output by the data prediction agent model, wherein the predicted target data includes stress and / or displacement.
[0054] A data prediction proxy model is pre-built, and when real-time operation data is obtained, the real-time operation data of the construction machinery is input into the data prediction proxy model. The data prediction proxy model outputs the predicted target data of the construction machinery, and the predicted target data includes stress and / or displacement. It should be understood that the difference in predicted target data will result in a different structure of the data prediction proxy model, which will not be elaborated here.
[0055] S130, constructing a twin three-dimensional model of the construction machinery.
[0056] Build a twin 3D model of construction machinery. The twin 3D model is a 3D model of construction machinery created by digital technology, which can monitor the structure or components of construction machinery.
[0057] According to the stress results, the areas with higher stress levels of each key component are determined, and then these dangerous areas are set as key nodes of the key components. In this embodiment, the output nodes of the data prediction agent model are the predicted target data of the key points, and the twin 3D model is associated with the output nodes of the data prediction agent model to obtain a data twin image based on the output rendering of the data prediction agent model.
[0058] S140, based on the predicted target data, rendering the twin three-dimensional model to obtain a data twin image of the construction machinery.
[0059] Figure 2 An example diagram of a data twin image according to an embodiment of the present application is schematically shown.
[0060] When the twin 3D model is associated with the output node of the data prediction proxy model, the twin 3D model is rendered based on the predicted target data. The predicted target data output by the data prediction proxy model is used to control the position of each component of the twin 3D model of the engineering machinery and the rendered display color, thereby generating a data twin image of the engineering machinery.
[0061] As shown in the figure, different values of predicted target data will be rendered in different display colors. Based on the display color of each component in the data twin image, the stress and / or displacement of each component of the engineering machinery can be quickly confirmed, and then the fatigue damage analysis results of the component can be obtained based on the stress and / or displacement of the component. The data such as stress and displacement of the engineering machinery are obtained by constructing a data prediction agent model. Since there is no need to set up sensors, the zero drift of the sensor is avoided, and accurate stress and displacement can be obtained for engineering machinery that is used for a long time. At the same time, the data prediction agent model has high prediction efficiency and requires less computing resources. It can quickly obtain the stress and displacement of engineering machinery, thereby making the rendered data twin image highly real-time.
[0062] In an embodiment of the present application, the construction machinery monitoring method further includes:
[0063] At least one of fatigue damage monitoring results, target data monitoring results, digital inspection recommendation results and maintenance recommendation results of the engineering machinery is obtained according to the predicted target data.
[0064] After long-term use of engineering machinery, key nodes of key components are prone to fatigue damage. According to the predicted target data, the fatigue damage monitoring results of the engineering machinery are obtained. Based on the fatigue damage monitoring results, it is determined whether the key nodes of the key components have fatigue damage, and then the key components with fatigue damage are replaced to ensure the long-term reliable operation of the engineering machinery. In addition, the obtained predicted target data can also be used to build a health monitoring and management system for engineering machinery. At least one of the target data monitoring results, digital inspection recommendation results and maintenance recommendation results is obtained through the health monitoring and management system. Through the target data monitoring results, early warnings can be issued for areas with large stress and / or displacement levels of engineering machinery during the life cycle. Through the digital inspection recommendation results, the areas that need to be inspected during the recommended inspection can be quickly determined. Through the maintenance recommendation results, the recommended structural components of the engineering machinery that need to be repaired and replaced can be quickly determined.
[0065] In an embodiment of the present application, the real-time operation data of the construction machinery is input into the data prediction agent model to obtain the predicted target data of the construction machinery output by the data prediction agent model, including:
[0066] Preprocessing the real-time operation data of the construction machinery to obtain preprocessed operation data;
[0067] Cleaning the preprocessed operation data to obtain cleaned operation data;
[0068] The cleaned operating data is input into the data prediction agent model to obtain the predicted target data of the construction machinery output by the data prediction agent model.
[0069] The operation data of tower cranes include data such as hoisting weight and rotation angle. The amount of data collected is huge, and the sampling frequency and data format of different types of operation data are different. At the same time, during the transmission of operation data, it is also affected by other factors such as noise, which is prone to data loss and abnormal data mutation.
[0070] Usually, in fatigue damage analysis scenarios of construction machinery, complete data without abnormalities is required, and the data is required to have the same sampling frequency and data format in order to obtain reliable construction machinery life analysis results. The real-time operation data of the construction machinery is preprocessed to obtain preprocessed operation data. Specifically, according to the characteristics of various types of collected operation data, it is intended to analyze and judge the data noise and blank values. Through analysis by threshold algorithms and reasonable space setting algorithms, data filtering and blank value compensation preprocessing are achieved to obtain preprocessed operation data. The preprocessed operation data is transformed and analyzed to obtain operation data with the same data format and sampling frequency.
[0071] The collected operation data is usually transmitted back in segments at a certain frequency. Since a complete time domain history signal of the tower crane hoisting action is not formed, the segmented operation data affects the stress damage accuracy. At the same time, the pre-processed operation data usually still has some abnormal values. The types of abnormalities in the operation data such as hoisting weight and rotation angle are different, and the distribution of abnormal data is irregular. For the pre-processed operation data, in this embodiment, the pre-processed operation data is cleaned by data splicing and fusion algorithms to obtain cleaned operation data. After cleaning the abnormal data and obtaining the cleaned operation data, the cleaned operation data is input into the data prediction agent model to obtain the predicted target data of the engineering machinery output by the data prediction agent model, so that the prediction agent model can output more accurate predicted target data.
[0072] In the embodiment of the present application, the data prediction agent model is obtained by the following steps:
[0073] Constructing a relational database between operation data of an engineering machine and target data, wherein the engineering machine includes a plurality of components and the target data includes stress and / or displacement of the components;
[0074] Based on the relational database, a first proxy model of each component is obtained respectively;
[0075] Assembling all the first proxy models to obtain a second proxy model of the construction machinery;
[0076] The second agent model is trained to obtain a data prediction agent model for construction machinery.
[0077] A large amount of operation data of engineering machinery is collected, and then a relational database between the operation data and the target data of the engineering machinery is constructed according to the mapping relationship between the operation data and the target data. Based on the relational database, a first proxy model of each component is obtained respectively. In this embodiment, the input of the first proxy model is the operation data of the engineering machinery, and the output of the first proxy model is the predicted target data of the engineering machinery.
[0078] All the first proxy models are assembled to obtain a second proxy model of the engineering machinery. The first proxy models are assembled to obtain a second proxy model of the entire engineering machinery. The second proxy model is trained to obtain a data prediction proxy model of the engineering machinery. Since the neural network of the first proxy model and the second proxy model reduces the scale of network parameters, it not only improves the model training efficiency, but also reduces the requirements of the proxy model for training data, so that a higher performance proxy model can be obtained, and more accurate data such as stress and displacement of the engineering machinery can be obtained through the proxy model. By training the assembled second proxy model, the performance of the proxy model can be further improved, thereby obtaining more accurate prediction target data.
[0079] In an embodiment of the present application, a relationship database between operation data of engineering machinery and target data is constructed, including:
[0080] Construct a rigid-flexible coupling dynamics simulation model for engineering equipment;
[0081] The rigid-flexible coupling dynamics simulation model is used to perform simulation based on the operation data of the engineering machinery to obtain the load data of each target component, wherein the target component is the component whose target data is to be predicted;
[0082] Constructing finite element simulation models of each target component respectively;
[0083] For each target component, a finite element simulation model corresponding to the target component is used to perform simulation based on the load data to obtain simulation target data of the target component;
[0084] According to the operation data and the simulation target data of each target component, a relational database between the operation data and the target data of the construction machinery is constructed.
[0085] Generally, engineering machinery includes rigid components and flexible components, and a rigid-flexible coupling dynamics simulation model of engineering equipment is constructed. The rigid-flexible coupling dynamics simulation model is used to simulate the operation data of the engineering machinery, simulate the operation state of the tower crane, and obtain the load data of each target component. The target component is the component whose target data is to be predicted. In this embodiment, the target component is the key component of the engineering machinery.
[0086] At the same time, a finite element simulation model of each target component is constructed respectively. For each target component, the finite element simulation model corresponding to the target component is used to perform simulation based on load data to obtain simulation target data of the target component.
[0087] It should be understood that the stress and displacement of the target component can also be obtained through the finite element simulation model without using sensors. However, the finite element simulation model is computationally inefficient and requires a large amount of computing resources, so it is not suitable for twin rendering of engineering machinery. In this embodiment, the simulation target data of the target component is obtained through the finite element simulation model, and a relationship database between the operation data and the target data of the engineering machinery is constructed based on the operation data and the simulation target data of each target component. The data prediction agent model obtained through relational database training has high prediction efficiency and requires few computing resources. It can quickly obtain the stress and displacement of engineering machinery, thereby making the rendered data twin image highly real-time.
[0088] In an embodiment of the present application, a rigid-flexible coupling dynamics simulation model of engineering equipment is constructed, including:
[0089] Based on the geometric data of construction machinery, the rigid body dynamics model and flexible body dynamics model of construction machinery are constructed;
[0090] Based on the control system data of construction machinery, establish the control system simulation model of construction machinery;
[0091] The rigid body dynamics model, the flexible body dynamics model and the control system simulation model are coupled and simulated to obtain a rigid-flexible coupling dynamics simulation model of the engineering equipment.
[0092] The rigid parts of construction machinery refer to the parts that hardly deform under the action of external forces, while the flexible parts refer to the parts that deform significantly under the action of external forces. Based on the geometric data of construction machinery, the rigid body dynamics model and flexible body dynamics model of construction machinery are constructed. The rigid body dynamics model and flexible body dynamics model can be used to accurately calculate the acceleration, stiffness and connection hinge force of the tower crane, and then obtain the load data of the key components of the tower crane.
[0093] It should be understood that the type of control system of the construction machinery is set according to actual needs, and can be a PLC (Programmable Logic Controller), etc., which is not limited here. The control system data is the data generated and recorded by the control system of the construction machinery in the running state, which can be the control current value of the hydraulic cylinder, etc., which will not be elaborated here. Based on the control system data of the construction machinery, a control system simulation model of the construction machinery is established. The rigid body dynamics model, the flexible body dynamics model and the control system simulation model are coupled and simulated to obtain a rigid-flexible coupling dynamics simulation model of the electromechanical-hydraulic coupling of the entire engineering equipment.
[0094] In the embodiment of the present application, a rigid-flexible coupling dynamics simulation model is used to perform simulation based on the operation data of the engineering machinery to obtain the load data of each target component, including:
[0095] Calibrate the rigid-flexible coupling dynamics simulation model and determine the calibrated accuracy of the rigid-flexible coupling dynamics simulation model;
[0096] When the accuracy after calibration is greater than the preset accuracy, the rigid-flexible coupling dynamics simulation model is used to perform simulation based on the operation data of the construction machinery to obtain the load data of each component.
[0097] After obtaining the rigid-flexible coupling dynamics simulation model, the test data of the engineering machinery dynamics simulation is obtained. The rigid-flexible coupling dynamics simulation model is calibrated according to the test data, and the calibrated accuracy of the rigid-flexible coupling dynamics simulation model is determined to ensure the accuracy of the simulation model.
[0098] When the accuracy after calibration is greater than the preset accuracy, the rigid-flexible coupling dynamics simulation model is used to simulate the operation data of the engineering machinery to obtain the load data of each component. In this embodiment, based on dynamic simulation, statics simulation, finite element simulation and electromechanical hydraulic joint simulation, the engineering machinery data is integrated to build a reliable relationship database between the operation data of the engineering machinery and the target data, thereby improving the training of high-performance proxy models based on the relationship database.
[0099] In the embodiment of the present application, based on the relational database, a first proxy model of each component is obtained respectively, including:
[0100] Determine the initial neural network for each component;
[0101] Based on the relational database, the initial neural network of each component is trained separately to obtain the first proxy model of each component.
[0102] Determine the initial neural network of each component, specifically, obtain the number of data types corresponding to the operating data. For ease of understanding, the number of types of operating data in the embodiment of the present application is 4, that is, the operating data also includes the lifting weight, lifting amplitude, rotation angle and wind speed of the tower crane, and the number of input nodes of the proxy model is 4. An input node of the neural network is obtained corresponding to each data type, and the inputs of the proxy model are the lifting weight, lifting amplitude, rotation angle and wind speed of the tower crane.
[0103] Determine the number of key points where the predicted target data needs to be obtained. For ease of understanding, in this embodiment, there are 5 key points in the key component that need to obtain predicted target data. The initial neural network includes output nodes corresponding to the 5 key points, and the output of each output node is the stress and / or displacement of a key point. Based on the relational database, the initial neural network of each component is trained separately to obtain the first proxy model of each component. It should be understood that after the first proxy model is trained, the proxy model needs to be tested for accuracy. When the accuracy of the proxy model does not meet the accuracy requirements, the neural network hyperparameters of the proxy model are adjusted, and the neural network hyperparameters of the proxy model can be optimized through an optimization algorithm to obtain a proxy model of the component that meets the usage accuracy.
[0104] The present application provides a method for monitoring construction machinery, including: obtaining real-time operation data of construction machinery; inputting the real-time operation data of construction machinery into a data prediction agent model to obtain predicted target data of construction machinery output by the data prediction agent model; constructing a twin three-dimensional model of construction machinery; based on the predicted target data, rendering the twin three-dimensional model to obtain a data twin image of the construction machinery. By using the constructed data prediction agent model to obtain data such as stress and displacement of construction machinery, since there is no need to set up sensors, the zero drift of sensors is avoided, and accurate stress and displacement can be obtained for construction machinery that is used for a long time. At the same time, the data prediction agent model has high prediction efficiency and requires less computing resources, and can quickly obtain the stress and displacement of construction machinery, thereby making the rendered data twin image highly real-time.
[0105] The present application also provides a computing device, including:
[0106] a memory configured to store instructions;
[0107] The processor is configured to call instructions from the memory and implement the above-mentioned construction machinery monitoring method when executing the instructions.
[0108] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the problem of inability to obtain accurate data for long-term construction machinery can be solved by adjusting kernel parameters.
[0109] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0110] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned engineering machinery monitoring method.
[0111] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0112] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0113] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0114] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0115] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0116] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0117] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0118] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0119] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.
Claims
1. A method for monitoring construction machinery, characterized in that: The engineering machinery monitoring method comprises: Obtain real-time operation data of construction machinery; Inputting the real-time operation data of the construction machinery into the data prediction agent model to obtain the predicted target data of the construction machinery output by the data prediction agent model, wherein the predicted target data includes stress and / or displacement; Constructing a twin three-dimensional model of the engineering machinery; Based on the predicted target data, the twin three-dimensional model is rendered to obtain a data twin image of the engineering machinery.
2. The construction machinery monitoring method according to claim 1, characterized in that: The engineering machinery monitoring method further comprises: At least one of fatigue damage monitoring results, target data monitoring results, digital inspection recommendation results and maintenance recommendation results of the engineering machinery is obtained according to the predicted target data.
3. The construction machinery monitoring method according to claim 1, characterized in that: The step of inputting the real-time operation data of the construction machinery into the data prediction agent model to obtain the predicted target data of the construction machinery output by the data prediction agent model comprises: Preprocessing the real-time operation data of the engineering machinery to obtain preprocessed operation data; Cleaning the preprocessed operation data to obtain cleaned operation data; The cleaned operation data is input into a data prediction agent model to obtain predicted target data of the construction machinery output by the data prediction agent model.
4. The construction machinery monitoring method according to claim 1, characterized in that: The data prediction agent model is obtained by the following steps: Constructing a relational database between operation data of an engineering machine and target data, wherein the engineering machine includes a plurality of components, and the target data includes stress and / or displacement of the components; Based on the relational database, obtaining a first proxy model of each component respectively; Assembling all the first proxy models to obtain a second proxy model of the engineering machinery; The second agent model is trained to obtain a data prediction agent model of the engineering machinery.
5. The construction machinery monitoring method according to claim 4, characterized in that: The step of constructing a relational database between the operation data of the construction machinery and the target data includes: Construct a rigid-flexible coupling dynamics simulation model for construction machinery; Using the rigid-flexible coupling dynamics simulation model to perform simulation based on the operation data of the engineering machinery to obtain load data of each target component, wherein the target component is a component for which the target data is to be predicted; Constructing finite element simulation models of each target component respectively; For each of the target components, use the finite element simulation model corresponding to the target component to perform simulation based on the load data to obtain simulation target data of the target component; A relational database between the operation data and the target data of each target component is constructed according to the operation data and the simulation target data of each target component.
6. The construction machinery monitoring method according to claim 5, characterized in that: The construction of the rigid-flexible coupling dynamics simulation model of the engineering machinery includes: Based on the geometric data of the engineering machinery, constructing a rigid body dynamics model and a flexible body dynamics model of the engineering machinery; Based on the control system data of the engineering machinery, establishing a control system simulation model of the engineering machinery; The rigid body dynamics model, the flexible body dynamics model and the control system simulation model are coupled to simulate each other to obtain a rigid-flexible coupling dynamics simulation model of the engineering machinery.
7. The construction machinery monitoring method according to claim 5, characterized in that: The method of using the rigid-flexible coupling dynamics simulation model to perform simulation based on the operation data of the engineering machinery to obtain load data of each target component includes: Calibrate the rigid-flexible coupling dynamics simulation model, and determine the calibrated accuracy of the rigid-flexible coupling dynamics simulation model; When the calibrated accuracy is greater than the preset accuracy, the rigid-flexible coupling dynamics simulation model is used to perform simulation based on the operation data of the engineering machinery to obtain the load data of each component.
8. The construction machinery monitoring method according to claim 4, characterized in that: The first proxy model of each component is obtained based on the relational database, including: Determine the initial neural network for each component; Based on the relational database, the initial neural network of each component is trained respectively to obtain a first proxy model of each component.
9. A computing device, characterized in that include: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the construction machinery monitoring method according to any one of claims 1 to 8 when executing the instructions.
10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions, which are used to enable a machine to execute the engineering machinery monitoring method according to any one of claims 1 to 8.