Method, device, equipment and storage medium for determining the life of construction machinery

Abstract

The present invention relates to the field of computer technology, and provides a method, device, equipment and storage medium for determining the life of an engineering machinery, wherein the method comprises: obtaining real-time load information of the engineering machinery; inputting the real-time load information into a first machine learning model to obtain the stress value of each dangerous point of each target component in the engineering machinery; inputting the stress values ​​of all dangerous points into a second machine learning model to obtain the fatigue life of each target component; and determining the remaining life of the target component based on the fatigue life of the target component. In this way, the stress value of each dangerous point can be obtained through the real-time load information and the first machine learning model, and then the remaining life of the target component can be quickly obtained through the second machine learning model, avoiding the problem of pasting sensors at each dangerous point on the engineering machinery for real-time collection, which is not only fast and accurate, but also simple to implement and reduces costs.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for determining the life of an engineering machinery. Background Art

[0002] At present, many construction machinery have harsh working environments, high working levels, complex structures and high safety requirements. However, as the service life of construction machinery continues, the life of its various components will inevitably deteriorate, and accordingly, the life of the entire construction machinery will also decrease, which will not only affect normal operation, but also cause safety hazards. Timely repair and replacement of various components is an effective way to extend the life of the components and thus the life of the entire machine. For this reason, the determination of the life of construction machinery is a very important link, among which the determination of the life of construction machinery includes the determination of the life of the components of the construction machinery, and further, the determination of the life of the entire machine affected by the life of the components. However, how to evaluate the condition of each component, monitor the life of the component, and determine the optimal entry period for the repair and replacement of each component is a key issue.

[0003] In the prior art, sensors are mainly attached to dangerous points of engineering machinery to collect real-time stress and strain values ​​of dangerous points when the chassis of the engineering machinery is in driving state, and then the cumulative damage of vibration dangerous points is calculated according to the damage accumulation method, so as to monitor the life of corresponding components. However, due to the harsh working environment of engineering machinery, the accuracy of sensor measurement results is low, and the measurement operation is complicated and costly. Summary of the invention

[0004] The present invention provides a method, device, equipment and storage medium for determining the life of engineering machinery, which are used to solve the problems in the prior art of monitoring the life of corresponding parts of engineering machinery, such as the low accuracy of the measurement results of real-time stress values ​​and strain values ​​by sensors attached to dangerous points due to the harsh working environment of the engineering machinery, the complex measurement operation and high cost, etc., so as to achieve the goal of quickly and accurately obtaining the remaining life of the target parts, and the implementation is simple, which reduces the cost.

[0005] The present invention provides a method for determining the life of an engineering machinery, comprising:

[0006] Obtain real-time load information of construction machinery;

[0007] The real-time load information is input into a first machine learning model to obtain a stress value of each dangerous point of each target component in the engineering machinery; the first machine learning model is trained based on load information samples and stress value samples of all the dangerous points;

[0008] Inputting the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; the second machine learning model is trained based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components;

[0009] Based on the fatigue life of the target component, a remaining life of the target component is determined.

[0010] According to a method for determining the life of an engineering machinery provided by the present invention, the first machine learning model is obtained in the following manner:

[0011] Constructing a finite element model of the engineering machinery;

[0012] Inputting the load information sample into the finite element model to obtain a first stress value of each node of each component in the engineering machinery;

[0013] If the node is the dangerous point, taking the first stress value of the node as a stress value sample of the dangerous point;

[0014] Based on the load information samples and the stress value samples of all the dangerous points, a first initial machine learning model is trained to obtain the first machine learning model.

[0015] According to a method for determining the life of an engineering machinery provided by the present invention, the finite element model is constructed in the following manner:

[0016] constructing an initial finite element model of the engineering machinery;

[0017] Inputting preset load information into the initial finite element model, and outputting a second stress value and a second strain value of the node;

[0018] If the second stress value of the node is greater than or equal to the first threshold, and / or the second strain value is greater than or equal to the second threshold, determine that the node is the dangerous point and the component where the node is located is the target component;

[0019] Collecting actual stress values ​​and actual strain values ​​of the dangerous points;

[0020] Based on the actual stress value and the actual strain value of the dangerous point, the initial finite element model is optimized to obtain the finite element model.

[0021] According to a method for determining the life of an engineering machinery provided by the present invention, the second machine learning model is obtained in the following manner:

[0022] Inputting stress value samples of all the dangerous points into the fatigue model to calculate the fatigue life samples of each target component;

[0023] Based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components, the second initial machine learning model is trained to obtain the second machine learning model.

[0024] A method for determining the life of an engineering machinery provided by the present invention further includes:

[0025] When the remaining life of the target component is less than or equal to a third threshold, a prompt message for prompting to replace the target component is issued.

[0026] According to a method for determining the life of an engineering machinery provided by the present invention, the first machine learning model and the second machine learning model are the first machine learning model and the second machine learning model corresponding to the current working condition of the engineering machinery; before inputting the real-time load information into the first machine learning model to obtain the stress value of each dangerous point of each target component in the engineering machinery, the method further includes:

[0027] The current working condition of the engineering machinery is determined according to the real-time working condition information of the engineering machinery.

[0028] A method for determining the life of an engineering machinery provided by the present invention further includes:

[0029] The minimum value of the remaining life of all the target components is taken as the remaining life of the entire engineering machinery.

[0030] The present invention also provides a device for determining the life of an engineering machinery, comprising:

[0031] A load information acquisition module is used to obtain real-time load information of construction machinery;

[0032] A stress acquisition module, used for inputting the real-time load information into a first machine learning model to obtain the stress value of each dangerous point of each target component in the engineering machinery; the first machine learning model is trained based on load information samples and stress value samples of all the dangerous points;

[0033] A fatigue acquisition module, used for inputting the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; the second machine learning model is trained based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components;

[0034] The life determination module is used to determine the remaining life of the target component based on the fatigue life of the target component.

[0035] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any one of the above-described methods for determining the life of engineering machinery is implemented.

[0036] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for determining the life of an engineering machinery as described in any one of the above is implemented.

[0037] The method for determining the life of engineering machinery provided by the present invention obtains real-time load information of the engineering machinery and inputs it into a first machine learning model to obtain the stress value of each dangerous point of each target component in the engineering machinery. Then, the stress values ​​of all dangerous points are input into a second machine learning model to obtain the fatigue life of each target component, and then the remaining life of the target component is quickly obtained. In this way, the stress value of each dangerous point can be obtained through real-time load information and the first machine learning model. There is no need to stick sensors at each dangerous point on the engineering machinery for real-time collection. This is not only fast and accurate, but also simple to implement and reduces costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 This is one of the flow charts of the method for determining the life of engineering machinery provided by the present invention;

[0040] Figure 2 This is the second flow chart of the method for determining the life of engineering machinery provided by the present invention;

[0041] Figure 3 This is the third flow chart of the method for determining the life of engineering machinery provided by the present invention;

[0042] Figure 4 It is a structural schematic diagram of the device for determining the life of engineering machinery provided by the present invention;

[0043] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Combine the following Figures 1 to 3 The method for determining the life of an engineering machinery according to the present invention is described.

[0046] The method for determining the life of construction machinery provided in the embodiment of the present invention can be executed by the construction machinery or the software and / or hardware therein, or can be executed by a server or the software and / or hardware therein. The server can be a cloud server or a physical server. The construction machinery can be a crane, for example, a truck crane, a crawler crane, a tower crane, etc., and can also be a pump truck, a rotary drilling rig, a high-altitude vehicle, etc.

[0047] Figure 1 It is one of the flow charts of the engineering machinery determination method provided by the present invention.

[0048] like Figure 1 As shown, this embodiment provides a method for determining the life of an engineering machinery, which at least includes:

[0049] Step 101: Acquire real-time load information of construction machinery.

[0050] In practical applications, a data acquisition system is provided in the construction machinery, and the data acquisition system is used to collect various parameters of the construction machinery, such as load information. If the construction machinery is a crane, the load information may be information that can characterize the mass of the heavy object lifted by the construction machinery, such as the force signal required to lift the heavy object. If the construction machinery life determination method is applied to the construction machinery, the real-time load information of the construction machinery can be directly obtained through the data acquisition system. If the construction machinery life determination method is applied to a server, the construction machinery can upload the real-time load information collected by the data acquisition system to a server, such as a cloud server, that is, a cloud platform. In this way, the server can obtain the real-time load information of the construction machinery.

[0051] Step 102: input the real-time load information into the first machine learning model to obtain the stress value of each dangerous point of each target component in the engineering machinery; the first machine learning model is trained based on the load information samples and the stress value samples of all the dangerous points.

[0052] The target component here refers to the component with dangerous points among the various components of the construction machinery. Dangerous points refer to the nodes in the components that are prone to damage such as cracks. There can be one dangerous point or multiple dangerous points in the target component.

[0053] Step 103: input the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; the second machine learning model is trained based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components.

[0054] The number of stress cycles required for a material to produce fatigue failure is called fatigue life. Therefore, the second machine learning model can output the number of stress cycles for each target component.

[0055] Step 104: Determine the remaining life of the target component based on the fatigue life of the target component.

[0056] Specifically, the number of stress cycles of the target component can be directly used as the remaining life of the target component, or the remaining life of the target component can be determined based on the ratio of the number of stress cycles of the target component to the number of stress cycles per unit time. The unit time can be a year, etc. For example, if the number of stress cycles of the target component is 10,000 and the number of stress cycles per year is 1,000, then the remaining life of the target component is 10,000 / 1,000=10 years.

[0057] Digital twin is a conceptual system of interaction between the physical world and digital space. It is a digital twin technology that presents real-world physical entities in a virtual digital form. In this embodiment, the first machine learning model and the second machine learning model are models in the digital space. For the dangerous points of the target components of the physical entity of the engineering machinery, the first machine learning model and the second machine learning model can obtain the stress values ​​and fatigue life corresponding to the dangerous points of the target components of the physical entity of the engineering machinery. It can be considered that the first machine learning model and the second machine learning model constitute the digital twin of the engineering machinery in the digital space. Figure 2 ,Exemplarily, the cloud platform inputs the acquired real-time load information into the ,digital twin and outputs the fatigue life of the target component.

[0058] In this embodiment, the real-time load information of the construction machinery is obtained and input into the first machine learning model to obtain the stress value of each dangerous point of each target component in the construction machinery. Then, the stress values ​​of all dangerous points are input into the second machine learning model to obtain the fatigue life of each target component, and then the remaining life of the target component is quickly obtained. In this way, the stress value of each dangerous point can be obtained through the real-time load information and the first machine learning model. There is no need to stick sensors at each dangerous point on the construction machinery for real-time collection. This is not only fast and accurate, but also simple to implement, which reduces costs.

[0059] As mentioned above, in addition to determining the life of the target component, the life of the engineering machinery also includes determining the life of the entire engineering machinery. Based on this, the method for determining the life of the engineering machinery provided in this embodiment may also include: taking the minimum value of the remaining life of all the target components as the remaining life of the entire engineering machinery. In practical applications, we can focus on the dangerous points of the components that affect the life of the entire engineering machinery. Accordingly, the target component here can be a component that affects the life of the engineering machinery. Then, among all the target components of the engineering machinery, if the life of one of the target components ends, the life of the entire engineering machinery ends. Based on this, the remaining life of the target component with the smallest remaining life among all the target components can be used as the remaining life of the entire engineering machinery, so as to accurately obtain the remaining life of the entire engineering machinery.

[0060] Based on the above embodiments, the first machine learning model and the second machine learning model are the first machine learning model and the second machine learning model corresponding to the current working condition of the engineering machinery. In practical applications, the first machine learning model and the second machine learning model corresponding to each working condition can be trained separately for different working conditions of the engineering machinery, such as tamping and hoisting conditions.

[0061] Based on this, before the real-time load information is input into the first machine learning model to obtain the stress value of each dangerous point of each target component in the engineering machinery, the engineering machinery life determination method of this embodiment may also include: determining the current working condition of the engineering machinery according to the real-time working condition information of the engineering machinery. Exemplarily, if the engineering machinery is a crane, the real-time working condition information may include real-time load information, etc., and may also include boom combination information, working radius, ground slope, etc. The boom combination information is information input by the user. In practical applications, an input control may be provided. The user can input working condition information such as boom combination information in advance through the input control. Based on this, the real-time load information is input into the first machine learning model corresponding to the current working condition, and the stress values ​​of all the dangerous points are input into the second machine learning model corresponding to the current working condition. In this way, the first machine learning model and the second machine learning model match the specific working condition, and the remaining life of the target component finally obtained is more accurate.

[0062] Based on the above embodiment, the first machine learning model is obtained in the following manner:

[0063] The first step is to construct a finite element model of the engineering machinery.

[0064] In practical applications, a finite element model corresponding to each working condition of the construction machinery can be constructed. The finite element model here is a three-dimensional simulation model.

[0065] The finite element model is used to perform transient dynamic analysis on the current working condition of the construction machinery through the finite element analysis method based on the load information, and obtain the stress and strain values ​​of each node of each component of the construction machinery.

[0066] Finite element analysis is an analysis method that uses the finite element method to analyze static or dynamic physical objects or physical systems. It is also called the finite element method. This method is a numerical technique for solving approximate solutions to boundary value problems of partial differential equations. In this method, an object or system is decomposed into a geometric model composed of multiple interconnected, simple parts. The number of these simple parts is limited, so it is called a finite element.

[0067] Transient dynamic analysis is a method used to determine the dynamic response of a structure subjected to arbitrary time-varying loads, and can output stress and strain values ​​that vary with time.

[0068] In addition, the finite element model also needs to input the current working environment (such as ground slope), the weight center of gravity of the entire machine and motion planning, etc.

[0069] The second step is to input the load information sample into the finite element model to obtain the first stress value of each node of each component in the engineering machinery.

[0070] In practical applications, the rated load information of the engineering machinery can be used as a load information sample. Of course, more load information samples can be constructed based on the rated load information. The load information sample is input into the finite element model, and the first stress value and the first strain value of each node of each component in the engineering machinery are output. The stress value of each node forms a stress cloud diagram.

[0071] Step 3: If the node is the dangerous point, the first stress value of the node is used as a stress value sample of the dangerous point.

[0072] Step 4: Based on the load information samples and the stress value samples of all the dangerous points, the first initial machine learning model is trained to obtain the first machine learning model.

[0073] Specifically, the load information sample can be input into the first initial machine learning model to obtain the predicted stress values ​​of all dangerous points. Based on the predicted stress values ​​of the dangerous points and the stress value samples, the first loss function is determined. When the first loss function is less than or equal to the first preset value, the training is stopped to obtain the first machine learning model.

[0074] The first initial machine learning model may be a neural network model. The specific value of the first preset value may be set according to actual conditions and is not specifically limited here.

[0075] In practical applications, see Figure 3 , exemplarily, the curve of the load information sample of the dangerous point over time and the curve of the stress value sample of the dangerous point over time are imported into ansys Twinbuilder, and the finite element model is reduced to obtain a reduced-order model of the finite element model, that is, a first machine learning model, which is a one-dimensional simulation model. ansys Twinbuilder is a finite element analysis software that can perform automatic machine learning under set parameters to reduce the three-dimensional simulation model to a one-dimensional simulation model.

[0076] In this embodiment, the input and output of the finite element model are used in combination with machine learning technology to train a first machine learning model, that is, the finite element model is reduced in order, and the first machine learning model is also a reduced-order model of the finite element model. Because although the finite element model can also accurately calculate the stress value of the dangerous point, as mentioned above, the essence of finite element analysis is to solve partial differential equations, and high-order partial differential equations only have approximate solutions. The process of solving approximate solutions requires continuous iterations. This process takes a lot of time and is not suitable for real-time calculations. The first machine learning model obtained after reducing the order of the finite element model can quickly obtain the stress value of the dangerous point, thereby realizing real-time calculation of the stress value of the dangerous point, and then adapting to the real-time requirements of determining the remaining life of the target component.

[0077] Exemplarily, the finite element model is constructed in the following manner:

[0078] The first step is to construct an initial finite element model of the engineering machinery.

[0079] The second step is to input the preset load information into the initial finite element model, and output the second stress value and the second strain value of the node.

[0080] Step 3: If the second stress value of the node is greater than or equal to the first threshold, and / or the second strain value is greater than or equal to the second threshold, determine that the node is the dangerous point and the component where the node is located is the target component.

[0081] In this step, nodes whose second stress value is greater than or equal to the first threshold value and / or whose second strain value is greater than or equal to the second threshold value are selected as dangerous points, which can cover more dangerous points, that is, the dangerous points are covered more comprehensively.

[0082] The specific values ​​of the first threshold and the second threshold can be set according to actual conditions and are not specifically limited here.

[0083] Step 4: Collect the actual stress value and actual strain value of the dangerous point.

[0084] In practical applications, sensors, such as strain gauges, can be set at each dangerous point of the engineering machinery in advance to collect the actual stress value and actual strain value of each dangerous point. The dangerous points of the same type of engineering machinery are similar, so the actual stress value and actual strain value of each dangerous point can be collected once for one engineering machinery of the same type, and the collected results can be used in all engineering machinery of the same type.

[0085] Step 5: Based on the actual stress value and actual strain value of the dangerous point, the initial finite element model is optimized to obtain the finite element model.

[0086] Among them, the initial finite element model can be optimized by selecting different unit types, unit sizes, connection methods between components, and modeling of welds. For details, please refer to relevant technologies and will not be described here. The optimized finite element model outputs stress values ​​and strain values ​​of dangerous points that are closer to actual stress values ​​and actual strain values.

[0087] In this embodiment, the stress values ​​and strain values ​​of the nodes output by the constructed initial finite element model are used to determine the dangerous points, which can cover more dangerous points and be more comprehensive. The initial finite element model is optimized using the actual stress values ​​and actual strain values ​​of the dangerous points collected to obtain a more accurate finite element model.

[0088] Based on the above embodiment, the second machine learning model is obtained in the following manner:

[0089] The first step is to input the stress value samples of all the dangerous points into the fatigue model to calculate the fatigue life samples of each target component.

[0090] The fatigue model also uses the finite element method to calculate the fatigue life sample of the target component where the dangerous point is located based on the stress value sample of the dangerous point. If there are multiple dangerous points in the target component, the minimum value of the fatigue life samples corresponding to the multiple dangerous points is used as the final fatigue life sample of the target component. Based on this, the stress value samples of all the dangerous points are input into the fatigue model, and the fatigue life sample of each target component is output.

[0091] In practical applications, existing fatigue analysis software can be used to implement this. A fatigue model is built in the fatigue analysis software. The stress values ​​of all dangerous points are read into the fatigue analysis software, and the material SN curve of each target component is input to determine the stress time history for fatigue assessment. The fatigue solution parameters are set to perform fatigue solution, and the fatigue life of the target component can be output.

[0092] The fatigue performance of a material is described by the relationship between the applied stress range S and the life N until failure, that is, the S (stress)-N (life) curve.

[0093] The second step is to train the second initial machine learning model based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components to obtain the second machine learning model.

[0094] Specifically, the stress value samples of all the dangerous points can be input into the second initial machine learning model to obtain the predicted fatigue life of all the target components. Based on the predicted fatigue life and fatigue life samples of the target components, the second loss function is determined. When the second loss function is less than or equal to the second preset value, the training is stopped to obtain the second machine learning model.

[0095] The second initial machine learning model may be a neural network model. The specific value of the second preset value may be set according to actual conditions and is not specifically limited here.

[0096] In this embodiment, the input and output of the fatigue model are used in combination with machine learning technology to train a second machine learning model, that is, the fatigue model is reduced in order, and the second machine learning model is also a reduced-order model of the fatigue model. Although the fatigue model can accurately calculate the fatigue life of the target component, the calculation process also takes a lot of time and is not suitable for real-time calculation. The second machine learning model obtained after reducing the order of the fatigue model can quickly obtain the fatigue life of the target component, and then meet the real-time requirements of determining the remaining life of the target component. In implementation, the calculation speed was reduced from 30 hours to within 3 seconds with an accuracy reduction of less than 10%.

[0097] Based on the above embodiments, the method for determining the life of engineering machinery provided in this embodiment may also include: when the remaining life of the target component is less than or equal to a third threshold, issuing a prompt message for prompting the replacement of the target component. In practical applications, the specific value of the third threshold can be set according to actual needs, and is not specifically limited here. Specifically, the above prompt message can be issued to the engineering machinery for the operator to view. In this embodiment, when the remaining life of the target component is small, a prompt is issued to replace the target component, thereby achieving early warning for timely processing.

[0098] The present invention provides a method for determining the life of engineering machinery based on digital twins. The method analyzes all working conditions of normal operation through finite elements, thereby determining the location of target components and dangerous points. Based on a distributed data acquisition system of sensors, the stress value and strain value at the dangerous point are collected, and the finite element model is optimized. The result of the optimized finite element model is input into fatigue analysis software to perform fatigue analysis. The finite element model and the fatigue model are reduced in order through machine learning, thereby constructing a digital twin. Based on a data acquisition system of a physical entity of engineering machinery, a force signal representing load information is collected to achieve real-time output of fatigue life of dangerous points. When the fatigue life of the output target component is less than or equal to a third threshold, the user is prompted to replace the target component. And the minimum value of the remaining life of all target components is used as the remaining life of the entire engineering machinery.

[0099] The following is a description of the device for determining the life of an engineering machinery provided by the present invention. The device for determining the life of an engineering machinery described below and the method for determining the life of an engineering machinery described above can be referred to in correspondence with each other.

[0100] Figure 4 It is a structural schematic diagram of the device for determining the life of engineering machinery provided by the present invention.

[0101] like Figure 4 As shown, this embodiment provides a device for determining the life of an engineering machinery, comprising:

[0102] The load information acquisition module 401 is used to acquire the real-time load information of the construction machinery;

[0103] A stress acquisition module 402 is used to input the real-time load information into a first machine learning model to obtain the stress value of each dangerous point of each target component in the engineering machinery; the first machine learning model is trained based on the load information sample and the stress value samples of all the dangerous points;

[0104] A fatigue acquisition module 403 is used to input the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; the second machine learning model is trained based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components;

[0105] The life determination module 404 is used to determine the remaining life of the target component based on the fatigue life of the target component.

[0106] Based on the above embodiment, the first machine learning model is obtained in the following manner:

[0107] Constructing a finite element model of the engineering machinery;

[0108] Inputting the load information sample into the finite element model to obtain a first stress value of each node of each component in the engineering machinery;

[0109] If the node is the dangerous point, taking the first stress value of the node as a stress value sample of the dangerous point;

[0110] Based on the load information samples and the stress value samples of all the dangerous points, a first initial machine learning model is trained to obtain the first machine learning model.

[0111] Based on the above embodiments, the finite element model is constructed in the following manner:

[0112] constructing an initial finite element model of the engineering machinery;

[0113] Inputting preset load information into the initial finite element model, and outputting a second stress value and a second strain value of the node;

[0114] If the second stress value of the node is greater than or equal to the first threshold, and / or the second strain value is greater than or equal to the second threshold, determine that the node is the dangerous point and the component where the node is located is the target component;

[0115] Collecting actual stress values ​​and actual strain values ​​of the dangerous points;

[0116] Based on the actual stress value and the actual strain value of the dangerous point, the initial finite element model is optimized to obtain the finite element model.

[0117] Based on the above embodiment, the second machine learning model is obtained in the following manner:

[0118] Inputting stress value samples of all the dangerous points into the fatigue model to calculate the fatigue life samples of each target component;

[0119] Based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components, the second initial machine learning model is trained to obtain the second machine learning model.

[0120] Based on the above embodiment, it also includes:

[0121] The life prompt module is used to issue a prompt message for prompting replacement of the target component when the remaining life of the target component is less than or equal to a third threshold.

[0122] Based on the above embodiment, the first machine learning model and the second machine learning model are the first machine learning model and the second machine learning model corresponding to the current working condition of the engineering machinery; further comprising:

[0123] The working condition determination module is used to determine the current working condition of the engineering machinery according to the real-time working condition information of the engineering machinery.

[0124] Based on the above embodiment, the lifespan determination module is further used for:

[0125] The minimum value of the remaining life of all the target components is taken as the remaining life of the entire engineering machinery.

[0126] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the engineering machinery life determination method, which includes:

[0127] Obtain real-time load information of construction machinery;

[0128] The real-time load information is input into a first machine learning model to obtain a stress value of each dangerous point of each target component in the engineering machinery; the first machine learning model is trained based on load information samples and stress value samples of all the dangerous points;

[0129] Inputting the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; the second machine learning model is trained based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components;

[0130] Based on the fatigue life of the target component, a remaining life of the target component is determined.

[0131] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0132] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer can execute the engineering machinery life determination method provided by the above methods, the method comprising:

[0133] Obtain real-time load information of construction machinery;

[0134] The real-time load information is input into a first machine learning model to obtain a stress value of each dangerous point of each target component in the engineering machinery; the first machine learning model is trained based on load information samples and stress value samples of all the dangerous points;

[0135] Inputting the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; the second machine learning model is trained based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components;

[0136] Based on the fatigue life of the target component, a remaining life of the target component is determined.

[0137] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for determining the life of an engineering machinery provided by the above methods is implemented, and the method comprises:

[0138] Obtain real-time load information of construction machinery;

[0139] The real-time load information is input into a first machine learning model to obtain a stress value of each dangerous point of each target component in the engineering machinery; the first machine learning model is trained based on load information samples and stress value samples of all the dangerous points;

[0140] Inputting the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; the second machine learning model is trained based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components;

[0141] Based on the fatigue life of the target component, a remaining life of the target component is determined.

[0142] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0143] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining the life of an engineering machinery, characterized in that: include: Obtain real-time load information of construction machinery; Inputting the real-time load information into a first machine learning model to obtain a stress value of each dangerous point of each target component in the engineering machinery; wherein the target component refers to a component having a dangerous point among the components of the engineering machinery; Inputting the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; Determining a remaining life of the target component based on the fatigue life of the target component; Wherein, the first machine learning model is obtained by: Constructing a finite element model of the engineering machinery; Inputting a load information sample into the finite element model to obtain a first stress value of each node of each component in the engineering machinery; If the node is the dangerous point, taking the first stress value of the node as a stress value sample of the dangerous point; Based on the load information samples and the stress value samples of all the dangerous points, training a first initial machine learning model to obtain the first machine learning model; The finite element model is constructed as follows: constructing an initial finite element model of the engineering machinery; Inputting preset load information into the initial finite element model, and outputting a second stress value and a second strain value of the node; If the second stress value of the node is greater than or equal to the first threshold, and / or the second strain value is greater than or equal to the second threshold, determine that the node is the dangerous point and the component where the node is located is the target component; Collecting actual stress values ​​and actual strain values ​​of the dangerous points; Based on the actual stress value and the actual strain value of the dangerous point, the initial finite element model is optimized to obtain the finite element model.

2. The method for determining the life of construction machinery according to claim 1, characterized in that: The second machine learning model is obtained by: Inputting stress value samples of all the dangerous points into the fatigue model to calculate the fatigue life samples of each target component; Based on the stress value samples of all the dangerous points and the fatigue life samples of all the target components, the second initial machine learning model is trained to obtain the second machine learning model.

3. The method for determining the life of construction machinery according to claim 1, characterized in that: Also includes: When the remaining life of the target component is less than or equal to a third threshold, a prompt message for prompting to replace the target component is issued.

4. The method for determining the life of construction machinery according to claim 1, characterized in that: The first machine learning model and the second machine learning model are the first machine learning model and the second machine learning model corresponding to the current working condition of the engineering machinery; before inputting the real-time load information into the first machine learning model to obtain the stress value of each dangerous point of each target component in the engineering machinery, it also includes: The current working condition of the engineering machinery is determined according to the real-time working condition information of the engineering machinery.

5. The method for determining the life of an engineering machinery according to any one of claims 1 to 4, characterized in that: Also includes: The minimum value of the remaining life of all the target components is taken as the remaining life of the entire engineering machinery.

6. A device for determining the life of an engineering machinery, characterized in that: include: A load information acquisition module is used to obtain real-time load information of construction machinery; A stress acquisition module, used for inputting the real-time load information into a first machine learning model to obtain a stress value of each dangerous point of each target component in the engineering machinery; wherein the target component refers to a component with a dangerous point among the components of the engineering machinery; A fatigue acquisition module, used for inputting the stress values ​​of all the dangerous points into a second machine learning model to obtain the fatigue life of each of the target components; A life determination module, configured to determine the remaining life of the target component based on the fatigue life of the target component; Wherein, the first machine learning model is obtained by: Constructing a finite element model of the engineering machinery; Inputting a load information sample into the finite element model to obtain a first stress value of each node of each component in the engineering machinery; If the node is the dangerous point, taking the first stress value of the node as a stress value sample of the dangerous point; Based on the load information samples and the stress value samples of all the dangerous points, training a first initial machine learning model to obtain the first machine learning model; The finite element model is constructed as follows: constructing an initial finite element model of the engineering machinery; Inputting preset load information into the initial finite element model, and outputting a second stress value and a second strain value of the node; If the second stress value of the node is greater than or equal to the first threshold, and / or the second strain value is greater than or equal to the second threshold, determine that the node is the dangerous point and the component where the node is located is the target component; Collecting actual stress values ​​and actual strain values ​​of the dangerous points; Based on the actual stress value and the actual strain value of the dangerous point, the initial finite element model is optimized to obtain the finite element model.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for determining the life of construction machinery as described in any one of claims 1 to 5 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the life of a construction machinery as claimed in any one of claims 1 to 5 is implemented.

Images