CN118793603A - Method and apparatus for predicting the remaining life of a hydraulic pump - Google Patents

Abstract

The invention relates to a method for predicting the remaining life of a hydraulic pump, comprising the steps of: acquiring real-time data of working state parameters of the hydraulic pump, wherein the working state parameters at least comprise the hydraulic oil cleanliness and/or fault codes of the hydraulic pump; predicting a remaining life of the hydraulic pump based on the real-time data of the operating state parameter using a prediction model. The invention also relates to an apparatus for predicting the remaining life of a hydraulic pump.

Description

Method and apparatus for predicting the remaining life of a hydraulic pump

Technical Field

The present invention relates to a data prediction method and device, and in particular to a method and device for predicting the remaining life of a hydraulic pump.

Background Art

In the field of construction machinery, analysis of the after-sales status quo found that agents generally have insufficient after-sales service personnel and service coverage, untimely spare parts management and after-sales service, and only after the construction machinery stops due to a malfunction will they arrange after-sales service personnel to provide repair services based on customer feedback. In particular, as one of the most core components of construction machinery, the hydraulic pump has a complex working environment and harsh working conditions, and there is a large demand for replacement and repair. However, the current situation is that only after the hydraulic pump has failed and stopped can agents arrange after-sales service personnel to repair or replace it based on customer feedback, resulting in long-term shutdown of construction machinery.

If the potential failure mode and failure date of the hydraulic pump can be predicted in advance through technical means, agents and OEMs will be able to manage spare parts and arrange the corresponding after-sales service personnel in advance, which can shorten unnecessary downtime of construction machinery, improve customer satisfaction, and thus achieve growth in the supplier's after-sales business.

Therefore, there is a need to improve the accuracy of the remaining life determination of a hydraulic pump.

Summary of the invention

The present invention is directed to solving at least one of the above problems of the prior art as well as other problems.

According to one aspect of the present invention, a method for predicting the remaining life of a hydraulic pump is provided, the method comprising the following steps:

Acquiring real-time data of working state parameters of the hydraulic pump, wherein the working state parameters at least include hydraulic oil cleanliness and/or a fault code of the hydraulic pump;

A prediction model is used to predict the remaining life of the hydraulic pump based on the real-time data of the operating state parameters.

Advantageously, the operating status parameters include a first operating status parameter set, which includes at least one of the speed, torque, inlet flow, outlet flow, inlet pressure, outlet pressure, cumulative operating time and oil temperature of the hydraulic pump, as well as the hydraulic oil cleanliness and/or fault code of the hydraulic pump.

Advantageously, the method further comprises: using a digital model of the hydraulic pump to determine a second working state parameter set based on the first working state parameter set, wherein the second working state parameter set comprises at least one of a return oil flow rate and a return oil pressure of the hydraulic pump.

Advantageously, the digital model includes a three-dimensional physical and simulation model of the hydraulic pump, and determining the second working state parameter set based on the first working state parameter set using the digital model of the hydraulic pump further includes:

The operation process of the hydraulic pump is simulated using the three-dimensional physical and simulation model to determine the second working state parameter set based on the first working state parameter set.

Advantageously, predicting the remaining life of the hydraulic pump based on the real-time data of the working state parameters using a prediction model further comprises:

The prediction model is used to predict the remaining life of the hydraulic pump based on real-time data of the first working state parameter set and the second working state parameter set.

Advantageously, the prediction model is a trained model. During the training phase of the prediction model, a portion of the historical data of the first working state parameter set and the second working state parameter set is used to form a training data set to train the prediction model.

Advantageously, during the training phase of the prediction model, the training data set is used to respectively train different prediction models including a linear regression model, a random forest model and a neural network model.

Advantageously, the prediction model is a verified model, and after the training phase of the prediction model, another part of the historical data of the first working state parameter set and the second working state parameter set is used to form a verification data set to verify the different trained prediction models, and the prediction model with the most accurate predicted remaining life is selected as the final prediction model.

Advantageously, before using the prediction model to predict the remaining life of the hydraulic pump based on the real-time data of the working state parameters, the method further comprises:

Filtering the real-time data of the working state parameter to remove data with null values and/or singular values; and/or

The real-time data of the working status parameters is normalized.

Advantageously, before the training phase of the prediction model, the method further comprises:

Filtering the data of the training data set to remove data with null values and/or singular values; and/or

The data of the training data set is normalized.

Advantageously, the method further comprises:

The prediction model is updated based on a difference between the predicted remaining life and an actual remaining life of the hydraulic pump.

According to another aspect of the present invention, a device for predicting the remaining life of a hydraulic pump is provided, comprising:

Processor; and

A memory, configured to store executable instructions of the processor;

The processor is configured to execute the executable instructions to implement the method for predicting the remaining life of a hydraulic pump according to the present invention.

According to the present invention, when establishing a remaining life prediction model for a hydraulic pump, in addition to parameters such as the speed, torque, inlet flow, outlet flow, inlet pressure, outlet pressure, cumulative working hours and oil temperature of the hydraulic pump, the hydraulic oil cleanliness and fault code information of the hydraulic pump are added as characteristic parameters during modeling, thereby effectively improving the accuracy of the hydraulic pump life prediction. In addition, by establishing a digital model of the hydraulic pump, the return oil flow and return oil pressure of the hydraulic pump are simulated as characteristic parameters input when establishing the prediction model, which further enriches the characteristic parameter data set of the machine learning model and further improves the accuracy of the prediction model, while avoiding the cost increase caused by the later installation of sensors.

BRIEF DESCRIPTION OF THE DRAWINGS

The preferred embodiments of the present invention will be described in more detail below with reference to the schematic drawings. The drawings and corresponding embodiments are for illustrative purposes only and are not intended to limit the present invention. In the drawings:

FIG. 1 schematically shows a flow chart of a method for establishing a prediction model for predicting the remaining life of a hydraulic pump according to an embodiment of the present invention.

FIG. 2 schematically shows a flow chart of a method for predicting the remaining life of a hydraulic pump using a prediction model according to an embodiment of the present invention.

FIG. 3 schematically shows a block diagram of a device for predicting the remaining life of a hydraulic pump according to an embodiment of the present invention.

DETAILED DESCRIPTION

Embodiments of the present invention are described below with reference to the accompanying drawings. In the following description, many specific details are set forth so that those skilled in the art can more fully understand and implement the present invention. However, it is obvious to those skilled in the art that the present invention may be implemented without some of these specific details. In addition, it should be understood that the present invention is not limited to the specific embodiments described. On the contrary, any combination of the features and elements described below may be considered to implement the present invention, regardless of whether they relate to different embodiments. Therefore, the aspects, features, embodiments and advantages described below are for illustrative purposes only and should not be regarded as elements or limitations of the claims unless clearly stated in the claims.

Thanks to the rapid development of industrial big data analysis and machine learning, some methods have been developed to diagnose faults and predict the life of hydraulic pumps based on working state parameters such as pressure, flow, vibration, temperature and even noise, combined with the full life test data of hydraulic pumps. However, due to the diversity and complexity of the working environment of construction machinery, there is a need to more accurately predict its potential failures and remaining life.

FIG. 1 schematically shows a flow chart of a method for establishing a prediction model for predicting the remaining life of a hydraulic pump according to an embodiment of the present invention.

According to the present invention, a remaining life prediction model of a hydraulic pump is established by a machine learning method, and the establishment of the prediction model mainly includes the following steps:

(1) Data acquisition steps:

In this step, a first working state parameter set and a second working state parameter set are obtained as feature input data sets for modeling.

During the use of the construction machinery, its operating data, including the operating data of the hydraulic pump, is sent to the supplier of the construction machinery at regular intervals (eg, every day, every two days or every week) and stored in a background database as historical data.

The first working state parameter set is extracted from the engineering machinery operation data with a complete hydraulic pump life cycle obtained from the background database, including parameters such as the speed, torque, inlet flow, outlet flow, inlet pressure, outlet pressure, cumulative working time and oil temperature of the hydraulic pump throughout the life cycle.

In addition, according to the present invention, the first working state parameter set also includes hydraulic oil cleanliness and hydraulic pump fault code. The hydraulic pump fault code includes information such as when and what faults the hydraulic pump has experienced.

Based on the analysis of the actual application of hydraulic pumps, it is found that many hydraulic pump failures are caused by the high content of impurities in the hydraulic oil, which aggravates the wear and causes the failure of the hydraulic pump. The cleanliness of the hydraulic oil will affect the working life of the hydraulic pump. Therefore, a hydraulic oil cleanliness sensor is added to the hydraulic pump to monitor the cleanliness of the hydraulic oil, and the characteristics of the hydraulic oil cleanliness are added to the input data of the prediction model as one of the first working state parameters.

In addition, because the fault code reflects possible operating abnormalities of the hydraulic pump to a certain extent, the characteristics of the fault code information are also added to the input data as one of the first working state parameters, thereby effectively improving the accuracy of the hydraulic pump life prediction.

For example, the operating data of hydraulic pumps that failed in the past five years may be acquired from the background database, and the first working state parameter set may be extracted therefrom.

The second working state parameter set includes the return oil flow and return oil pressure of the hydraulic pump. The return oil flow and return oil pressure can be obtained by additionally installing a flow sensor and a pressure sensor. Advantageously, in order to avoid the cost increase caused by the later installation of sensors, the return oil flow and return oil pressure can be calculated by a digital model of the hydraulic pump based on the first working state parameter set. The digital model is used to simulate and emulate the operation of the hydraulic pump, which is, for example, a digital twin model, or any other appropriate simulation model.

The digital twin model includes a three-dimensional physical and simulation model of the hydraulic pump. The input parameters of the three-dimensional physical and simulation model include the speed, torque, inlet flow, outlet flow, inlet pressure, outlet pressure, cumulative working time, oil temperature and hydraulic oil cleanliness of the hydraulic pump. After running the three-dimensional physical and simulation model, the return oil flow and return oil pressure of the hydraulic pump are output.

By using the digital model of the hydraulic pump, the two characteristics of the hydraulic pump, namely the return oil flow and the return oil pressure, are simulated as the second working state parameters in the input data of the prediction model, so as to further enrich the characteristic data dimension in the input data.

(2) Data processing steps:

In this step, the acquired data is processed, including filtering the acquired data to remove data with null values and/or singular values to ensure data integrity. In addition, the data is normalized to avoid affecting the accuracy of the overall prediction result due to differences in data dimensions.

(3) Model training steps:

In this step, a portion of the processed historical data of the first working state parameter set and the second working state parameter set is used to form a training data set to train the prediction model. For example, 80% of the historical data can be used as the training data set, or other amounts (such as 90%) of the historical data can be used as the training data set.

Different types of prediction models can be used as candidate prediction models. These candidate prediction models can include at least one of a linear regression model, a random forest model, and a neural network model. The prediction model can also include other known machine learning models.

The training data sets are used to train different candidate prediction models including linear regression model, random forest model and neural network model. Through training and learning, the model parameters are optimized so that the output results of the candidate prediction models gradually become more accurate.

(4) Model verification steps:

In this step, another part of the processed historical data of the first working state parameter set and the second working state parameter set (i.e., the remaining historical data different from the training data set) is used to form a verification data set to verify the trained different candidate prediction models. For example, another 20% of the historical data is used as a verification data set, or another 10% of the historical data is used as a verification data set.

Different trained candidate prediction models are used to predict the remaining life of a hydraulic pump based on a validation data set, the results output by each candidate prediction model are compared with the actual life of the verified hydraulic pump, and the candidate prediction model with the most accurate predicted remaining life is selected as the final prediction model.

For example, in one example, the accuracy of different models can be judged by calculating the average absolute error of different trained models, and the model with the highest accuracy is selected as the prediction model for predicting the remaining life of the hydraulic pump. In another example, the accuracy of different models can be judged by judging whether the remaining life predicted by different trained models falls within a predetermined error range, and the model with the largest number of prediction results falling within the predetermined error range is used as the prediction model for predicting the remaining life of the hydraulic pump. It is understandable that other appropriate judgment criteria can also be used to select the final prediction model.

After obtaining the final prediction model, the remaining life of the hydraulic pump in use can be predicted.

FIG. 2 schematically shows a flow chart of a method for predicting the remaining life of a hydraulic pump using the prediction model obtained by the machine learning method as described above.

When predicting the remaining life of a hydraulic pump, first, in the data acquisition step, real-time data of the working status parameters of the hydraulic pump are acquired in real time or in batches from a background database or from sensors of the hydraulic pump, including the speed, torque, inlet flow, outlet flow, inlet pressure, outlet pressure, accumulated working hours, oil temperature, hydraulic oil cleanliness and hydraulic pump fault code of the hydraulic pump included in a first working status parameter set.

Then, the speed, torque, inlet flow, outlet flow, inlet pressure, outlet pressure, cumulative working time, oil temperature and hydraulic oil cleanliness of the hydraulic pump are input as input parameters into the three-dimensional physical and simulation model of the hydraulic pump, and the return oil flow and return oil pressure of the hydraulic pump are obtained through calculation, that is, the data in the second working state parameter set.

Then, the data processing step is entered. In this step, the acquired real-time data of the working state parameters are filtered to remove data with null values and/or singular values, and the real-time data of the working state parameters are normalized.

Then, the data prediction step is entered. In this step, the final prediction model obtained in the model establishment and training process shown in FIG1 is used to predict the remaining life of the hydraulic pump based on the real-time data of the working state parameters (including the first working state parameter set and the second working state parameter set).

Then, the predicted remaining life of the hydraulic pump is output and the prediction result can be stored in a database.

The prediction results can be pushed to the dealer or user of the hydraulic pump. For example, the relevant information of the hydraulic pump predicted to fail in the future (for example, within 3 months) can be pushed to the corresponding dealer or user. In this way, the dealer can make reasonable arrangements for after-sales service personnel and repair or replace the hydraulic pump in time, ultimately achieving the optimization of human resources and the increase of after-sales business volume.

Advantageously, in the process of using the prediction model, the prediction model is updated based on the difference between the predicted remaining life and the actual remaining life of the hydraulic pump. Specifically, after the prediction results are pushed to the agent's service personnel, the field service engineer will track and monitor the status of the hydraulic pump and the actual failure time based on the pushed results, and feed back the results of the field verification to the OEM. If the predicted remaining life is consistent with the actual remaining life, it means that the prediction result of the prediction model is accurate. Otherwise, the prediction model can be retrained based on the difference between the actual remaining life and the predicted remaining life of the hydraulic pump, so as to update and optimize the parameters of the prediction model and further improve the accuracy of the model prediction.

According to the present invention, when establishing a remaining life prediction model for a hydraulic pump, in addition to parameters such as the speed, torque, inlet flow, outlet flow, inlet pressure, outlet pressure, cumulative working hours and oil temperature of the hydraulic pump, the hydraulic oil cleanliness and fault code information of the hydraulic pump are added as characteristic parameters during modeling, thereby effectively improving the accuracy of the hydraulic pump life prediction. In addition, by establishing a digital model of the hydraulic pump, the return oil flow and return oil pressure of the hydraulic pump are simulated as characteristic parameters input when establishing the prediction model, which further enriches the characteristic parameter data set of the machine learning model and further improves the accuracy of the prediction model, while avoiding the cost increase caused by the later installation of sensors.

In an exemplary embodiment of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, the program including executable instructions, which can implement the steps of the method for predicting the remaining life of a hydraulic pump described in any of the above embodiments when executed by, for example, a processor. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps of various exemplary embodiments of the present invention described in the method for predicting the remaining life of a hydraulic pump in this specification.

The program product for implementing the above method according to an embodiment of the present invention can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

In addition, the present invention also proposes a device for predicting the remaining life of a hydraulic pump, which may include a processor and a memory for storing executable instructions of the processor. The processor is configured to execute the steps of the method for predicting the remaining life of a hydraulic pump in any of the above embodiments by executing the executable instructions.

It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

The device 100 according to this embodiment of the present invention is described below with reference to Figure 3. The device 100 shown in Figure 3 is only an example and should not bring any limitation to the function and scope of use of the embodiment of the present invention.

As shown in Fig. 3, the device 100 is in the form of a general-purpose computing device. The components of the device 100 may include, but are not limited to: at least one processing unit 110, at least one storage unit 120, a bus 130 connecting different system components (including the storage unit 120 and the processing unit 110), a display unit 140, etc.

The storage unit stores a program code, which can be executed by the processing unit 110, so that the processing unit 110 performs the steps of various exemplary embodiments of the present invention described in the method for predicting the remaining life of a hydraulic pump in this specification. For example, the processing unit 110 can perform the steps shown in Figures 1 and 2.

The storage unit 120 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 1201 and/or a cache memory unit 1202 , and may further include a read-only memory unit (ROM) 1203 .

The storage unit 120 may also include a program/utility 1204 having a set (at least one) of program modules 1205, such program modules 1205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

Bus 130 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The device 100 may also communicate with one or more external devices 200 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the device 100, and/or any device that enables the device 100 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input/output (I/O) interface 150. Furthermore, the device 100 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) via a network adapter 160. The network adapter 160 may communicate with other modules of the device 100 via the bus 130. It should be understood that, although not shown in the figure, other hardware and/or software modules may be used in conjunction with the device 100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the method for predicting the remaining life of a hydraulic pump according to the embodiment of the present invention.

It should be noted that although several modules or units of the device for predicting the remaining life of a hydraulic pump are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of a module or unit described above can be further divided into multiple modules or units for concretization. The components displayed as modules or 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 technical solution of the present invention. Those of ordinary skill in the art can understand and implement it without paying creative labor.

The method and apparatus for predicting the remaining life of a hydraulic pump of the present invention are described above with the aid of specific embodiments. It is obvious to those skilled in the art that various modifications and variations may be made to the embodiments disclosed above without departing from the scope or spirit of the present invention. For example, the implementation of the present invention may not include some of the specific features described, and the present invention is not limited to the specific embodiments described, but rather any combination of the described features and elements may be envisioned. Other embodiments will be apparent to those skilled in the art from consideration of the specification and practice of the disclosed methods and apparatus. The specification and examples are to be regarded as exemplary only, with the true scope being represented by the appended claims and their equivalents.

Claims (12)

1. A method for predicting the remaining life of a hydraulic pump, comprising the steps of:

Acquiring real-time data of working state parameters of the hydraulic pump, wherein the working state parameters at least comprise the hydraulic oil cleanliness and/or fault codes of the hydraulic pump;

predicting a remaining life of the hydraulic pump based on the real-time data of the operating state parameter using a prediction model.

2. The method of claim 1, wherein the operating state parameters comprise a first operating state parameter set comprising at least one of a rotational speed, a torque, an inlet flow, an outlet flow, an inlet pressure, an outlet pressure, a cumulative operating duration, and an oil temperature of the hydraulic pump, and a hydraulic oil cleanliness and/or a fault code of the hydraulic pump.

3. The method according to claim 2, wherein the method further comprises: a second set of operating state parameters is determined based on the first set of operating state parameters using a digital model of the hydraulic pump, the second set of operating state parameters including at least one of a return oil flow rate and a return oil pressure of the hydraulic pump.

4. A method according to claim 3, characterized in that the digital model is preferably a digital twin model, the digital model comprising a three-dimensional physical and simulation model of the hydraulic pump, determining a second set of operating state parameters based on the first set of operating state parameters using the digital model of the hydraulic pump further comprises:

Simulating an operating process of the hydraulic pump using the three-dimensional physical and simulation model to determine the second set of operating state parameters based on the first set of operating state parameters.

5. The method of claim 4, wherein predicting a remaining life of the hydraulic pump based on real-time data of the operating state parameter using a prediction model further comprises:

Predicting a remaining life of the hydraulic pump based on real-time data of the first and second operating state parameter sets using the prediction model.

6. A method according to any of claims 3-5, characterized in that the predictive model is a trained model, and that a training data set is formed using a part of the historical data of the first and second operating state parameter sets during a training phase of the predictive model to train the predictive model.

7. The method of claim 6, wherein during a training phase of the predictive model, different predictive models having a linear regression model, a random forest model, and a neural network model are trained using the training data set, respectively.

8. The method of claim 7, wherein the predictive model is a validated model, wherein after a training phase of the predictive model, a validation data set is constructed using another portion of the historical data of the first and second operating state parameter sets to validate the trained different predictive models, and wherein the predictive model with the most accurate predicted remaining life is selected as the final predictive model.

9. The method of any one of claims 1 to 5, wherein prior to predicting a remaining life of the hydraulic pump based on real-time data of the operating state parameters using a predictive model, the method further comprises:

Filtering the real-time data of the operating state parameters to remove data having null and/or singular values; and/or

And carrying out normalization processing on the real-time data of the working state parameters.

10. The method of claim 4, wherein prior to the training phase of the predictive model, the method further comprises:

Filtering data of the training dataset to remove data having null and/or singular values; and/or

And carrying out normalization processing on the data of the training data set.

11. The method according to claim 1, wherein the method further comprises:

The prediction model is updated based on a difference between the predicted remaining life and the actual remaining life of the hydraulic pump.

12. An apparatus for predicting a remaining life of a hydraulic pump, comprising:

a processor; and

A memory for storing executable instructions of the processor;

Wherein the processor is configured to execute the executable instructions to implement the method according to any one of claims 1 to 11.