Method and device for predicting remaining life of structural member, and working machine

Abstract

The application provides a structural member residual life prediction method, device and working machine, and relates to the technical field of engineering machinery.The method comprises the following steps: inputting target data of the working machine into a residual life prediction model, so that the residual life prediction model outputs the residual life of a to-be-predicted structural member in the working machine; wherein the target data comprises pressure of a hydraulic cylinder in the working machine and action data of the to-be-predicted structural member in a preset period; the residual life prediction model is obtained based on sample data and corresponding labels after training; the sample data comprises pressure of a hydraulic cylinder in a sample working machine and action data of a sample structural member in the sample working machine in a sample period; and the labels corresponding to the sample data comprise fault information of the sample structural member in the sample period.The structural member residual life prediction method, device and working machine provided by the application can more accurately predict the residual life of the to-be-predicted structural member, and have higher reliability and stronger practicability.

Description

Technical Field

[0001] This invention relates to the field of engineering machinery technology, and in particular to a method, device and operating machinery for predicting the remaining life of structural components. Background Technology

[0002] The structural components to be predicted refer to the various parts that make up the physical structure of the working machinery, such as the boom, stick, and bucket in an excavator. The inspection and maintenance of these structural components are crucial for the normal operation of the machinery. Based on the remaining lifespan of these structural components, more accurate and efficient inspection and maintenance can be performed.

[0003] In existing technologies, the remaining life of a structural component can be predicted based on its high-frequency vibration data. However, due to the numerous factors influencing the high-frequency vibration data of the component, the accuracy of predicting the remaining life of the component using existing methods is not high. Summary of the Invention

[0004] This invention provides a method, device, and machine for predicting the remaining life of structural components, which solves the problem of low accuracy in predicting the remaining life of structural components in the prior art, and achieves more accurate prediction of the remaining life of structural components.

[0005] This invention provides a method for predicting the remaining life of structural components, comprising:

[0006] Acquire target data for the operating machinery;

[0007] The target data is input into the remaining life prediction model so that the remaining life prediction model outputs the remaining life of the structural component to be predicted in the operating machinery.

[0008] The target data includes: the pressure of the hydraulic cylinder in the machine and the motion data of the structural component to be predicted within a preset time period; the remaining life prediction model is obtained after training based on sample data and corresponding labels; the sample data includes the pressure of the hydraulic cylinder in the sample machine and the motion data of the sample structural component in the sample machine within the sample time period; the labels corresponding to the sample data include the fault information of the sample structural component within the sample time period.

[0009] According to the structural component remaining life prediction method provided by the present invention, the sample data further includes at least one of the following: the output power of the engine in the sample machinery, the output torque of the engine, the flow rate of the hydraulic pump in the sample machinery, the pressure of the hydraulic pump, and the oil temperature of the hydraulic oil in the sample machinery during the sample time period.

[0010] Accordingly, the target data also includes at least one of the following during the preset time period: the output power of the engine in the operating machinery, the output torque of the engine, the flow rate of the hydraulic pump in the operating machinery, the pressure of the hydraulic pump, and the oil temperature of the hydraulic oil in the operating machinery; the target data is of the same type as the data included in the sample data.

[0011] According to the present invention, a method for predicting the remaining useful life of structural components is provided, which trains the remaining useful life prediction model based on the sample data and corresponding labels, specifically including:

[0012] Based on the design parameters and materials science test results of the sample structural component, a sample attenuation sub-model corresponding to the sample structural component is obtained; wherein, the sample attenuation sub-model is used to describe the relationship between the stress condition and the remaining life of the sample structural component.

[0013] Based on the sample decay sub-model, the sample data, and the corresponding labels, the remaining lifetime prediction model is trained to obtain a trained remaining lifetime prediction model.

[0014] According to the present invention, a method for predicting the remaining service life of structural components, the step of acquiring target data of the operating machinery specifically includes:

[0015] The original pressure of the hydraulic cylinder in the machine and the original motion data of the structural component to be predicted are obtained within the preset time period, and used as the original data of the machine.

[0016] The raw data is processed, and the processed raw data is used as the target data.

[0017] The data processing includes: data filtering and / or feature engineering processing.

[0018] According to a method for predicting the remaining service life of a structural component provided by the present invention, after inputting the target data into a remaining service life prediction model so that the remaining service life prediction model outputs the remaining service life of the structural component to be predicted in the operating machinery, the method further includes:

[0019] Based on the remaining lifespan of the structural component to be predicted, a maintenance plan for the structural component to be predicted is obtained.

[0020] The present invention also provides a structural component remaining life prediction device, comprising:

[0021] The data acquisition module is used to acquire target data of the operating machinery;

[0022] The life prediction module is used to input the target data into the remaining life prediction model so that the remaining life prediction model can output the remaining life of the structural component to be predicted in the working machinery.

[0023] The target data includes: the pressure of the hydraulic cylinder in the machine and the motion data of the structural component to be predicted within a preset time period; the remaining life prediction model is obtained after training based on sample data and corresponding labels; the sample data includes the pressure of the hydraulic cylinder in the sample machine and the motion data of the sample structural component in the sample machine within the sample time period; the labels corresponding to the sample data include the fault information of the sample structural component within the sample time period.

[0024] The present invention also provides a working machine, including: a structural component remaining life prediction device as described above.

[0025] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the structural component remaining life prediction method as described above.

[0026] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the structural component remaining life prediction method as described above.

[0027] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the structural component remaining life prediction method as described above.

[0028] The present invention provides a method, device, and machine tool for predicting the remaining life of structural components. By acquiring target data, including the pressure of the hydraulic cylinder in the machine tool and the motion data of the structural component to be predicted in the machine tool, and inputting the target data into a trained remaining life prediction model, the remaining life of the structural component to be predicted is obtained from the output of the remaining life prediction model. This method can more accurately predict the remaining life of the structural component to be predicted, and can detect abnormalities in the structural component to be predicted in advance, thereby allowing sufficient time for inspection and maintenance of the machine tool. The method has higher reliability, greater practicality, and greater universality in predicting the remaining life of the structural component to be predicted. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0030] Figure 1 This is one of the flowcharts illustrating the structural component remaining life prediction method provided by the present invention;

[0031] Figure 2 This is a schematic diagram of the structural component remaining life prediction device provided by the present invention;

[0032] Figure 3 This is the second flowchart illustrating the structural component remaining life prediction method provided by the present invention;

[0033] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0035] In the description of the invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0036] It should be noted that in traditional methods for predicting the remaining life of structural components, a sample structural component can be tested under design conditions to obtain a performance curve describing the relationship between high-frequency vibration data and the remaining life of the sample structural component. Based on the aforementioned performance curve and the high-frequency vibration data of the structural component to be predicted in the operating machinery, the remaining life of the structural component to be predicted can be obtained. Specifically, the structural component to be predicted is the same type and model of structural component to be predicted in the operating machinery as the sample structural component.

[0037] However, traditional methods for predicting the remaining life of structural components have the following drawbacks: First, the performance curves mentioned above are obtained under design conditions, while the high-frequency vibration data of the structural components to be predicted in the actual working machinery are greatly affected by external factors. The performance curves mentioned above cannot accurately describe the relationship between the high-frequency vibration data and the remaining life of the structural components to be predicted under actual working conditions. Therefore, the accuracy of the remaining life of the structural components to be predicted based on the performance curves mentioned above is not high.

[0038] Secondly, obtaining the above performance curves requires extensive testing of sample structural components under design conditions, which is costly. Usually, only a small number of sample structural components with high cost, difficult maintenance, or important characteristics are tested to obtain the corresponding performance curves. For other types of structural components to be predicted, it is difficult to obtain the remaining life of the above-mentioned other types of structural components based on traditional structural component remaining life prediction methods. The universality of traditional structural component remaining life prediction methods is not strong.

[0039] Finally, when predicting the remaining life of the above-mentioned structural components based on the traditional structural component remaining life prediction method, it is often only when the vibration spectrum of the above-mentioned structural component is abnormal or the above-mentioned structural component has obvious faults that it can be determined that the above-mentioned structural component is abnormal. It is difficult to reserve enough time for the above-mentioned structural component to be repaired or controlled. The existing structural component remaining life prediction method has weak practicality.

[0040] To address this issue, the present invention provides a method for predicting the remaining life of structural components. Based on this method, the remaining life of the structural component to be predicted can be obtained more accurately, reliably, and universally. Furthermore, based on the obtained remaining life of the structural component, a maintenance plan for the structural component can be derived.

[0041] Figure 1 This is one of the flowcharts illustrating the structural component remaining life prediction method provided by this invention. The following is a combination of... Figure 1 The present invention describes a method for predicting the remaining life of structural components. For example... Figure 1 As shown, the method includes: step 101, acquiring target data of the operating machinery; wherein, the target data includes: the pressure of the hydraulic cylinders in the operating machinery and the motion data of the structural components to be predicted within a preset time period.

[0042] It should be noted that, based on the structural component remaining life prediction method provided by this invention, the remaining life of a structural component to be predicted in a working machine can be predicted, and the remaining life of the structural component to be predicted can be obtained. The following uses an excavator as the working machine and the boom of the excavator as the structural component to be predicted as an example to illustrate the structural component remaining life prediction method provided by this invention.

[0043] An excavator, also known as a digging machine or excavator, is a piece of construction machinery that uses a bucket to excavate materials above or below the machine's bearing surface and load them into transport vehicles or unload them into a stockpile. The boom is the core structural component of an excavator, and the movements of the stick and bucket both rely on the stable operation of the boom. Under high-intensity digging conditions, the boom experiences accelerated fatigue wear. Excessive boom fatigue wear can lead to cracks and other malfunctions, ending the boom's remaining service life.

[0044] It is understood that the remaining lifespan of the excavator's boom is related to the stress conditions on the boom, and the pressure of the hydraulic cylinders in the excavator can reflect these stress conditions. The remaining lifespan of the excavator's boom is also related to the actions performed by the boom. Therefore, in this embodiment of the invention, the target data for the excavator may include the pressure of the hydraulic cylinders in the excavator and the action data of the boom within a preset time period. By acquiring the target data of the excavator, the remaining lifespan of the boom can be predicted based on this data.

[0045] Target data for excavators can be obtained in various ways. For example, the original pressure of the hydraulic cylinders and the original movement data of the boom in the excavator within a preset time period can be obtained based on big data technology and used directly as the target data for the excavator. Alternatively, the original pressure of the hydraulic cylinders and the original movement data of the boom in the excavator within a preset time period can be obtained based on big data technology and used as the original data for the excavator. After data processing of the above original data, the processed original data can be used as the target data for the excavator.

[0046] It should be noted that the preset time period can be determined based on actual circumstances. For example, the preset time period can be a time period of a preset duration prior to the current moment. In this embodiment of the invention, the preset time period is not specifically limited.

[0047] Optionally, the preset time can be a period of 100 hours prior to the current time.

[0048] It should be noted that the boom's motion data within the preset time period may include the type, timing, and amplitude of each motion performed by the boom within the preset time period. This motion data can be coded.

[0049] Step 102: Input the target data into the remaining life prediction model so that the remaining life prediction model can output the remaining life of the structural components to be predicted in the working machinery.

[0050] The remaining life prediction model is obtained by training based on sample data and corresponding labels. The sample data includes the pressure of hydraulic cylinders in the sample machinery and the motion data of sample structural components in the sample machinery during the sample period. The labels corresponding to the sample data include the fault information of sample structural components during the sample period.

[0051] It should be noted that before inputting the target data of the excavator into the remaining life prediction model and obtaining the remaining life of the boom of the excavator output by the remaining life prediction model, the remaining life prediction model can be trained based on the sample data and the corresponding labels to obtain a trained remaining life prediction model.

[0052] Specifically, the sample excavator can be the same as or different from the excavator containing the boom to be predicted. If the sample excavator is different from the excavator containing the boom to be predicted, an excavator of the same model as the excavator containing the boom to be predicted and in normal working condition can be used as the sample excavator.

[0053] The original pressure of the hydraulic cylinders in the sample excavator and the original motion data of the sample boom in the sample working machinery can be obtained based on big data technology within the sample period, and used as sample data. Alternatively, the original pressure of the hydraulic cylinders in the sample excavator and the original motion data of the sample boom in the sample working machinery can also be obtained based on big data technology within the sample period, and used as sample raw data. After data processing, the above-mentioned sample raw data is used as sample data. Normal operating state can refer to the operating state of the sample excavator under normal operating scenarios and conditions.

[0054] It should be noted that the sample time period can be determined based on actual circumstances. For example, the sample time period can be a preset duration preceding a certain historical moment. In this embodiment of the invention, the sample time period is not specifically limited.

[0055] Optionally, the data processing performed on the aforementioned raw sample data may include, but is not limited to, data filtering and / or feature engineering. Data filtering can remove invalid data from the raw sample data, such as raw sample data of the excavator engine idling during the sample period. Feature engineering can obtain sample feature data from the raw sample data, which can better describe the raw sample data.

[0056] It should be noted that feature engineering refers to the process of selecting better data features from raw data through a series of engineered methods. Feature engineering can include feature extraction, feature construction, and feature selection. The sample features of the original sample data may include, but are not limited to, the maximum, minimum, mean, slope, and variance of the original sample data.

[0057] Fault information of the sample boom within the above sample period can be obtained based on big data technology and used as the corresponding label for the sample data.

[0058] It should be noted that the fault information of the sample boom may include the time when the sample boom failed, the type of fault, and the severity of the fault.

[0059] After obtaining the sample data and corresponding labels, the remaining life prediction model can be trained based on the sample data and corresponding labels to obtain a trained remaining life prediction model.

[0060] After obtaining the trained remaining life prediction model, the target data of the excavator can be input into the trained remaining life prediction model to obtain the remaining life of the boom of the excavator output by the trained remaining life prediction model.

[0061] Optionally, after obtaining the remaining lifespan of the excavator's boom, the remaining lifespan can be sent to a display device for display, or a notification message carrying the remaining lifespan of the boom can be sent to an electronic device used by the user. After receiving the notification message, the user's electronic device can display the notification message on its screen, so that the user can know the remaining lifespan of the boom. The user can be the excavator operator and / or maintenance personnel.

[0062] Optionally, after the remaining life prediction model outputs the remaining life of the structural component to be predicted in the working machinery, the above method further includes: updating the remaining life prediction model to obtain the updated remaining life prediction model.

[0063] Specifically, after obtaining the remaining life of the boom in the excavator output by the remaining life prediction model, the sample data and corresponding labels can be updated based on the actual operating data of the excavator and the fault information of the boom. The remaining life prediction model can also be updated based on the updated sample data and corresponding labels to obtain the updated remaining life prediction model.

[0064] After obtaining the updated remaining life prediction model, the remaining life of the boom in the excavator can be predicted based on the updated model the next time. By updating the remaining life prediction model, the prediction accuracy can be further improved, thereby increasing the accuracy of predicting the remaining life of the structural components being predicted.

[0065] This invention acquires target data, including the pressure of the hydraulic cylinder in the working machinery and the motion data of the structural component to be predicted in the working machinery, and inputs the target data into a trained remaining life prediction model to obtain the remaining life of the structural component to be predicted output by the remaining life prediction model. This can more accurately predict the remaining life of the structural component to be predicted, and can detect abnormalities of the structural component to be predicted in advance, thereby allowing sufficient time for inspection and maintenance of the working machinery. The prediction of the remaining life of the structural component to be predicted is more reliable, more practical, and more universal.

[0066] Based on the above embodiments, the sample data also includes at least one of the following: the output power of the engine in the sample machinery, the output torque of the engine, the flow rate of the hydraulic pump in the sample machinery, the pressure of the hydraulic pump, and the oil temperature of the hydraulic oil in the sample machinery during the sample time period.

[0067] Accordingly, the target data also includes at least one of the following: the output power of the engine in the operating machinery, the output torque of the engine, the flow rate of the hydraulic pump in the operating machinery, the pressure of the engine, and the oil temperature of the hydraulic oil in the operating machinery within a preset time period; the data types of the target data and the sample data are the same.

[0068] It should be noted that some or all of the following parameters—engine output power, engine output torque, hydraulic pump flow rate, hydraulic pump pressure, and hydraulic oil temperature—can reflect the force on the boom of the excavator to a certain extent. Therefore, the sample data in this embodiment may also include some or all of the following parameters within the sample time period: engine output power, engine output torque, hydraulic pump flow rate, hydraulic pump pressure, and hydraulic oil temperature. Based on the sample data including the above-mentioned sample data and corresponding labels, the remaining life prediction model is trained, and the trained remaining life prediction model has a higher prediction accuracy.

[0069] Preferably, the sample data may include all of the following during the sample period: the pressure of the hydraulic cylinder in the sample excavator, the output power of the engine in the sample excavator, the output torque of the engine, the flow rate of the hydraulic pump in the excavator, the pressure of the hydraulic pump, and the oil temperature of the hydraulic oil in the excavator.

[0070] It should be noted that the target data for the excavator is of the same data type as the sample data mentioned above. However, the sample data may contain more data types than the target data. For example, if the sample data includes all of the following during the sample period: hydraulic cylinder pressure in the sample excavator, engine output power, engine output torque, hydraulic pump flow rate, hydraulic pump pressure, and hydraulic oil temperature, the target data may include at least one of the following during a preset period: hydraulic cylinder pressure, engine output power, engine output torque, hydraulic pump flow rate, hydraulic pump pressure, and hydraulic oil temperature. Alternatively, if the sample data includes hydraulic cylinder pressure, engine output power, and engine output torque during the sample period, the target data may include hydraulic cylinder pressure, engine output power, and engine output torque during a preset period.

[0071] Optionally, the aforementioned sample data and target data can be obtained based on big data technology. The specific process for obtaining the aforementioned sample data and target data can be found in the descriptions of the above embodiments, and will not be repeated here in this embodiment.

[0072] In this embodiment of the invention, the sample data also includes part or all of the following: the output power of the engine in the sample machine during the sample time period, the output torque of the engine, the flow rate of the hydraulic pump in the sample machine, the pressure of the hydraulic pump, and the oil temperature of the hydraulic oil in the sample machine. When the sample data corresponds to the target data of the machine, the target data includes part or all of the following: the output power of the engine in the machine during the preset time period, the output torque of the engine, the flow rate of the hydraulic pump in the machine, the pressure of the hydraulic pump, and the oil temperature of the hydraulic oil in the machine. Based on the above sample data, a remaining life prediction model with higher prediction accuracy can be trained, which can further improve the accuracy of predicting the remaining life of the structural component to be predicted.

[0073] Based on the above embodiments, the remaining life prediction model is trained based on sample data and corresponding labels, specifically including: obtaining the sample attenuation sub-model corresponding to the sample structural component based on the design parameters and materials science test results of the sample structural component; wherein, the sample attenuation sub-model is used to describe the relationship between the stress condition of the sample structural component and the remaining life.

[0074] It is understandable that the remaining lifespan of the excavator boom is also related to the boom's design parameters and materials science test results. Therefore, in this embodiment of the invention, when training the remaining lifespan prediction model, a sample attenuation sub-model corresponding to the sample structural component can first be obtained based on the design parameters and materials science test results of the sample structural component. Then, the remaining lifespan prediction model is trained based on the sample attenuation sub-model, sample data, and corresponding labels to obtain a trained remaining lifespan prediction model. The sample attenuation sub-model can be used to describe the relationship between the stress condition of the sample structural component and its remaining lifespan.

[0075] Specifically, based on the design parameters of the sample structural components and the results of materials science tests, the relationship between the stress condition and remaining life of the sample boom can be obtained through numerical calculation, mathematical statistics, and other methods. In this way, a sample attenuation sub-model can be generated to describe the relationship between the stress condition and remaining life of the sample boom.

[0076] Optionally, the above-mentioned sample attenuation sub-model may be represented in the form of, but is not limited to, mapping tables, fitting functions, and fitting curves.

[0077] Based on the sample decay sub-model, sample data, and corresponding labels, the remaining lifetime prediction model is trained to obtain a trained remaining lifetime prediction model.

[0078] Specifically, after obtaining the sample attenuation sub-model corresponding to the sample boom, the sample attenuation sub-model and sample data can be input into the remaining life prediction model in training to obtain the predicted remaining life of the excavator boom output by the remaining life prediction model in training.

[0079] Based on the predicted remaining life of the boom in the excavator and the corresponding labels of the sample data, the model parameters of the remaining life prediction model in training can be continuously updated, thereby obtaining a well-trained remaining life prediction model.

[0080] This invention constructs a sample attenuation sub-model corresponding to the sample structural component based on the design parameters and materials science test results. Based on the above sample attenuation sub-model, sample data, and corresponding labels, the remaining lifetime prediction model is trained to obtain a remaining lifetime prediction model with higher prediction accuracy, which can further improve the accuracy of predicting the remaining lifetime of the structural component to be predicted.

[0081] Based on the above embodiments, the target data of the operating machinery is obtained, specifically including: obtaining the original pressure of the hydraulic cylinder and the original motion data of the structural component to be predicted in the operating machinery within a preset time period, as the original data of the operating machinery.

[0082] Specifically, the raw pressure of the hydraulic cylinders and the raw motion data of the boom in the excavator within a preset time period can be obtained based on big data technology, and used as the raw data of the excavator.

[0083] It should be noted that, in this embodiment of the invention, at least one of the following can be obtained based on big data technology within a preset time period: the original pressure of the hydraulic cylinder in the excavator, the original output power of the engine in the excavator, the original output torque of the engine, the original flow rate of the hydraulic pump in the excavator, the original pressure of the hydraulic pump, and the original oil temperature of the hydraulic oil in the excavator, as the original data of the excavator.

[0084] The raw data is processed, and the processed raw data is used as the target data; the data processing includes: data filtering and / or feature engineering.

[0085] After obtaining the excavator's raw data, the raw data can be processed, and the processed raw data can be used as the excavator's target data.

[0086] Optionally, the data processing performed on the aforementioned raw data may include data filtering and / or feature engineering. Data filtering can remove invalid data from the raw data, such as data on when the excavator's engine is idling within a preset time period. Feature engineering can obtain feature data corresponding to the raw data, which can better describe the raw data.

[0087] Preferably, the data processing performed on the above-mentioned raw data may include data filtering and feature engineering.

[0088] This invention obtains the pressure of the hydraulic cylinder and the movement data of the boom in the excavator within a preset time period as the excavator's raw data. After processing the raw data, the processed raw data is used as the target data of the working machinery. The data processing includes data filtering and / or feature engineering processing, which can further improve the accuracy of predicting the remaining life of the structural components to be predicted by removing invalid data from the raw data and / or obtaining the feature data corresponding to the raw data.

[0089] Based on the above embodiments, after inputting the target data into the remaining life prediction model so that the remaining life prediction model outputs the remaining life of the structural component to be predicted in the working machinery, the above method further includes: obtaining a maintenance plan for the structural component to be predicted based on the remaining life of the structural component to be predicted.

[0090] Specifically, after obtaining the remaining lifespan of the excavator's boom from the remaining lifespan prediction model, a maintenance plan for the boom can be derived based on this remaining lifespan, providing rational suggestions for its maintenance. For example, if the remaining lifespan of the boom is less than a preset value, the maintenance plan can be determined as immediate shutdown for maintenance. Another example: Normally, the boom requires on-site maintenance by specialized personnel. If the remaining lifespan of the boom is not less than a preset value, a maintenance plan can be derived based on the remaining lifespan of the boom and the distance between the excavator's location and the location of the maintenance personnel, determining the appropriate time for the maintenance personnel to perform the maintenance.

[0091] Optionally, after obtaining the remaining life of the boom in the excavator output by the remaining life prediction model, the severity of the abnormality of the boom or the probability of the boom failing can be assessed based on the remaining life of the boom.

[0092] This invention, through obtaining the remaining life of a structural component to be predicted in the operating machinery from the output of the remaining life prediction model, obtains a maintenance plan for the structural component to be predicted based on the remaining life of the structural component. By predicting the remaining life of the structural component to be predicted in the operating machinery, a maintenance plan for the structural component to be predicted can be obtained, providing more reasonable maintenance suggestions for the maintenance of the structural component to be predicted, reducing maintenance workload, lowering maintenance costs, and improving user experience.

[0093] Figure 2 This is a structural schematic diagram of the structural component remaining life prediction device provided by the present invention. The following is in conjunction with... Figure 2 The remaining life prediction device for structural components provided by this invention will be described below. The remaining life prediction device for structural components described below can be referred to in correspondence with the remaining life prediction method for structural components provided by this invention described above. For example... Figure 2 As shown, the device includes a data acquisition module 201 and a lifetime prediction module 202.

[0094] The data acquisition module 201 is used to acquire target data of the operating machinery.

[0095] The life prediction module 202 is used to input target data into the remaining life prediction model so that the remaining life prediction model can output the remaining life of the structural component to be predicted in the working machinery.

[0096] The target data includes: the pressure of the hydraulic cylinders in the machine and the motion data of the structural components to be predicted within a preset time period; the remaining life prediction model is obtained after training based on the sample data and corresponding labels; the sample data includes the pressure of the hydraulic cylinders in the sample machine and the motion data of the sample structural components in the sample machine within the sample time period; the labels corresponding to the sample data include the fault information of the sample structural components within the sample time period.

[0097] Specifically, the data acquisition module 201 and the lifetime prediction module 202 are electrically connected.

[0098] The data acquisition module 201 can be used to acquire target data of the excavator in various ways. For example, it can acquire the original pressure of the hydraulic cylinder and the original movement data of the boom in the excavator within a preset time period based on big data technology, and directly use them as the target data of the excavator; or, it can acquire the original pressure of the hydraulic cylinder and the original movement data of the boom in the excavator within a preset time period based on big data technology, and use them as the original data of the excavator. After processing the above original data, the processed original data is used as the target data of the excavator.

[0099] The life prediction module 202 can be used to input the target data of the excavator into the trained remaining life prediction model to obtain the remaining life of the boom of the excavator output by the trained remaining life prediction model.

[0100] Optionally, the data acquisition module 201 can also be specifically used to acquire the original pressure of the hydraulic cylinder in the working machinery and the original motion data of the structural component to be predicted within a preset time period, as the original data of the working machinery; to process the original data, and to use the processed original data as the target data; wherein, the data processing includes: data filtering and / or feature engineering processing.

[0101] Optionally, the structural component remaining life prediction device may also include a maintenance plan generation module.

[0102] The maintenance plan generation module can be used to obtain maintenance plans for structural components based on their remaining lifespan.

[0103] Optionally, the structural component remaining life prediction device may also include a cloud-based model update module.

[0104] The cloud-based model update module can be used to refresh the remaining life prediction model with one click via T-box and download and update the remaining life prediction model from the cloud after the user has been authenticated and responded to the user's input. It can also load the remaining life prediction model onto a specified electronic device in response to the user's input, thereby adapting to working conditions where the communication conditions of the operating machinery are poor. The aforementioned electronic devices can be smartphones, laptops, tablets, etc. used by maintenance personnel.

[0105] Optionally, the structural component remaining life prediction device may also include an edge computing module.

[0106] The edge computing module can be used for the actual deployment and execution of the remaining life prediction model. By performing modeling of complex parameter relationships, it provides computing power for structural strength calculation, life prediction and anomaly early warning.

[0107] Optionally, the structural component remaining life prediction device may also include a maintenance information push module.

[0108] The maintenance information push module can be used to send the predicted remaining life of structural components to a display device for display, and can also be used to send a notification message carrying the remaining life of the aforementioned structural components to a designated electronic device; wherein, after receiving the notification message, the designated electronic device can display the notification message on the display screen of the electronic device, so that the user can know the remaining life of the boom.

[0109] It should be noted that the structural component remaining life prediction device provided by this invention can be deployed in the cloud and / or at the edge. The edge can be a controller for the operating machinery, a T-box, or electronic equipment used by maintenance personnel, etc.

[0110] This invention acquires target data, including the pressure of the hydraulic cylinder in the working machinery and the motion data of the structural component to be predicted in the working machinery, and inputs the target data into a trained remaining life prediction model to obtain the remaining life of the structural component to be predicted output by the remaining life prediction model. This can more accurately predict the remaining life of the structural component to be predicted, and can detect abnormalities of the structural component to be predicted in advance, thereby allowing sufficient time for inspection and maintenance of the working machinery. The prediction of the remaining life of the structural component to be predicted is more reliable, more practical, and more universal.

[0111] To facilitate understanding of the structural component remaining life prediction method and apparatus provided by the present invention, an example is provided below to illustrate the structural component remaining life prediction method and apparatus provided by the present invention. Figure 3 This is the second schematic flowchart of the structural component remaining life prediction method provided by the present invention. For example... Figure 3As shown, based on the design parameters and materials science test results of the sample structural components, the sample attenuation sub-model corresponding to the sample structural components is obtained. The above sample attenuation sub-model is represented by a fitting curve, that is, the sample attenuation curve corresponding to the sample structural components is obtained based on the design parameters and materials science test results of the sample structural components.

[0112] Based on real-time cloud-recorded operating data and fault information of the machinery, raw sample data and corresponding tags are obtained. Data filtering and / or feature engineering are then performed on the raw sample data and corresponding tags to obtain the final sample data and corresponding tags.

[0113] Based on the aforementioned sample decay curves, sample data, and corresponding labels, a model is trained to obtain a trained remaining lifetime prediction model. The trained remaining lifetime prediction model can be deployed in the cloud and at the edge.

[0114] Based on real-time cloud-recorded operational data of the machinery, raw data of the machinery is obtained. This raw data is then filtered and / or feature-engineered to obtain the target data for the machinery.

[0115] Based on the target data and the trained remaining life prediction model, the remaining life of the structural components to be predicted in the operating machinery is predicted, and the remaining life of the structural components to be predicted is obtained.

[0116] Determine whether the remaining lifespan of the above-mentioned structural component to be predicted is less than a preset value, for example: whether the remaining lifespan of the above-mentioned structural component to be predicted is less than 200 hours.

[0117] If the remaining lifespan of the aforementioned structural components is less than the preset value, the operating machinery will be shut down for maintenance. After the operating machinery has completed its maintenance and is brought back online, the cloud continues to record the operating data and fault information of the operating machinery in real time.

[0118] If the remaining lifespan of the aforementioned structural component to be predicted is not less than the preset value, the operating machinery will continue to operate and generate a maintenance plan for the aforementioned structural component based on the remaining lifespan of the aforementioned structural component. The cloud will continue to record the operating data and fault information of the operating machinery in real time.

[0119] Based on the above embodiments, a working machine includes: a structural component remaining life prediction device as described above.

[0120] Specifically, the operating machinery includes the aforementioned structural component remaining life prediction device. By combining cloud computing and edge computing, it fully utilizes the big data stored in the cloud to train a more reliable remaining life prediction model, while edge computing ensures the efficient and reliable application of the remaining life prediction model to designated operating machinery. It can establish remaining life predictions based on machine learning and working condition differences based on a large amount of historical data, integrating physical logic relationships and big data, resulting in higher model accuracy. It allows for login and control of edge-end model updates using a mobile phone by scanning a QR code or facial recognition, ensuring high security. It also allows for adding excavator models using a mobile phone, solving the problem of difficult model updates for excavators in special working conditions such as tunnels and mines, and particularly addressing maintenance challenges in scenarios with difficult access and complex scheduling, such as tunnels. Based on the degree of anomaly or failure risk and the spatiotemporal distribution of the excavator and maintenance base, it calculates the lowest-cost maintenance plan, automatically pushing maintenance and structural component reinforcement plans to maintenance engineers, reducing the risk of component damage and adding value to maintenance services, while reducing the pressure and cost of producing additional structural component spare parts for the factory.

[0121] The structure of the above-mentioned structural component remaining life prediction device and the specific steps for predicting the remaining life of the structural component to be predicted can be found in the contents of the above embodiments, and will not be repeated in the embodiments of the present invention.

[0122] Alternatively, the operating machinery can be an excavator.

[0123] In this embodiment of the invention, the working machinery acquires target data including the pressure of the hydraulic cylinders in the working machinery and the motion data of the structural components to be predicted in the working machinery. The target data is then input into a trained remaining life prediction model to obtain the remaining life of the structural components to be predicted, which is output by the remaining life prediction model. This allows for a more accurate prediction of the remaining life of the structural components to be predicted, and enables the early detection of abnormalities in the structural components to be predicted. This allows sufficient time to be reserved for the inspection and maintenance of the working machinery. The prediction of the remaining life of the structural components to be predicted is more reliable, more practical, and more universal.

[0124] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a structural component remaining life prediction method. This method includes: acquiring target data of the operating machinery; inputting the target data into the remaining life prediction model so that the remaining life prediction model outputs the remaining life of the structural component to be predicted in the operating machinery; wherein the target data includes: the pressure of the hydraulic cylinder in the operating machinery and the motion data of the structural component to be predicted within a preset time period; the remaining life prediction model is obtained after training based on sample data and corresponding labels; the sample data includes the pressure of the hydraulic cylinder in the sample operating machinery and the motion data of the sample structural component in the sample operating machinery within the sample time period; the labels corresponding to the sample data include the fault information of the sample structural component within the sample time period.

[0125] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the structural component remaining life prediction method provided by the above methods. The method includes: acquiring target data of the operating machinery; inputting the target data into a remaining life prediction model so that the remaining life prediction model outputs the remaining life of the structural component to be predicted in the operating machinery; wherein, the target data includes: the pressure of the hydraulic cylinder in the operating machinery and the motion data of the structural component to be predicted within a preset time period; the remaining life prediction model is obtained after training based on sample data and corresponding labels; the sample data includes the pressure of the hydraulic cylinder in the sample operating machinery and the motion data of the sample structural component in the sample operating machinery within the sample time period; the labels corresponding to the sample data include the fault information of the sample structural component within the sample time period.

[0127] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the structural component remaining life prediction method provided by the above methods. The method includes: acquiring target data of the operating machinery; inputting the target data into a remaining life prediction model so that the remaining life prediction model outputs the remaining life of the structural component to be predicted in the operating machinery; wherein, the target data includes: the pressure of the hydraulic cylinder in the operating machinery and the motion data of the structural component to be predicted within a preset time period; the remaining life prediction model is obtained after training based on sample data and corresponding labels; the sample data includes the pressure of the hydraulic cylinder in the sample operating machinery and the motion data of the sample structural component in the sample operating machinery within the sample time period; the labels corresponding to the sample data include the fault information of the sample structural component within the sample time period.

[0128] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0129] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the remaining life of a structural member, characterized by, The method comprises the following steps: obtaining target data of a working machine; inputting the target data into a remaining life prediction model, so that the remaining life prediction model outputs a remaining life of a structure to be predicted in the working machine; wherein the target data comprises pressure of a hydraulic cylinder in the working machine and action data of the structure to be predicted in a preset period; the remaining life prediction model is obtained based on sample data and corresponding labels; the sample data comprises pressure of a hydraulic cylinder in a sample working machine and action data of a sample structure in the sample working machine in a sample period; the labels corresponding to the sample data comprise failure information of the sample structure in the sample period; the action data of the structure to be predicted in the preset period comprises type, time and amplitude of each action of the structure to be predicted in the preset period; training the remaining life prediction model based on the sample data and the corresponding labels, specifically comprising: obtaining a sample attenuation sub-model corresponding to the sample structure based on design parameters and material testing results of the sample structure; wherein the sample attenuation sub-model is used to describe the relationship between the stress condition and the remaining life of the sample structure; training the remaining life prediction model based on the sample attenuation sub-model and the sample data and the corresponding labels to obtain a trained remaining life prediction model.

2. The structural member residual life prediction method according to claim 1, characterized by, The sample data further comprises at least one of output power of an engine in the sample working machine, output torque of the engine, flow of a hydraulic pump in the sample working machine, pressure of the hydraulic pump and oil temperature of hydraulic oil in the sample working machine; Correspondingly, the target data further comprises at least one of output power of an engine in the working machine, output torque of the engine, flow of a hydraulic pump in the working machine, pressure of the hydraulic pump and oil temperature of hydraulic oil in the working machine; the target data and the sample data comprise the same type of data.

3. The structural member residual life prediction method according to claim 1, characterized by, The method further comprises the following steps: obtaining original pressure of a hydraulic cylinder in the working machine and original action data of the structure to be predicted in the preset period as original data of the working machine; performing data processing on the original data, and taking the original data after data processing as the target data; wherein the data processing comprises data screening and / or feature engineering processing.

4. The structural member residual life prediction method according to Claim 1, characterized by, After the target data is input into the remaining life prediction model to make the remaining life prediction model output the remaining life of the structure to be predicted in the working machine, the method further comprises the following steps: obtaining a maintenance scheme of the structure to be predicted based on the remaining life of the structure to be predicted.

5. A structure member residual life prediction device characterized by comprising: The method comprises the following steps: a data acquisition module for obtaining target data of a working machine; a life prediction module for inputting the target data into a remaining life prediction model, so that the remaining life prediction model outputs a remaining life of a structure to be predicted in the working machine; The target data comprises pressure of a hydraulic cylinder in the working machine and action data of the structure to be predicted in a preset period; the remaining life prediction model is obtained based on sample data and corresponding labels; the sample data comprises pressure of a hydraulic cylinder in a sample working machine and action data of a sample structure in the sample working machine in a sample period; the labels corresponding to the sample data comprise failure information of the sample structure in the sample period; the action data of the structure to be predicted in the preset period comprises type, time and amplitude of each action of the structure to be predicted in the preset period; The remaining life prediction model is trained based on the sample data and corresponding labels, and the training specifically comprises: A sample attenuation sub-model corresponding to the sample structure is obtained based on design parameters and material testing results of the sample structure; the sample attenuation sub-model is used to describe a relationship between stress of the sample structure and remaining life; The remaining life prediction model is trained based on the sample attenuation sub-model and the sample data and corresponding labels, and a trained remaining life prediction model is obtained.

6. A work machine characterized by comprising: Comprise: The structure remaining life prediction device of claim 5.

7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the structure remaining life prediction method of any one of claims 1 to 4.

8. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the structure remaining life prediction method of any one of claims 1 to 4.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to realize the structure remaining life prediction method of any one of claims 1 to 4. The computer program is executed by the processor to realize the structure remaining life prediction method of any one of claims 1 to 4.

Images