Knowledge and data co-driven gear deterioration state prediction method and device
Through the knowledge and data collaboratively driven method, combined with neural network and loss function training, the accurate prediction of gear degradation state is achieved, the problem of insufficient reliability and interpretability of a single data-driven model is solved, and the accuracy and adaptability of prediction are improved.
Patent Information
- Application Number
- CN202510345442.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-24
- Publication Date
- 2025-07-11
AI Technical Summary
In the prior art, the gear degradation state prediction model based on a single data drive has shortcomings in terms of reliability and interpretability, making it difficult to accurately evaluate the health status of the gear.
Using a method of collaborative driving of knowledge and data, by obtaining the vibration data and acquisition time of the gear, combining the first neural network and the second neural network, predicting the deterioration state and dynamic function of the gear, embedding the loss function for training, and achieving accurate prediction of the deterioration state of the gear.
It improves the accuracy and robustness of gear degradation state prediction, can maintain high accuracy in complex environments, and has knowledge-driven interpretability and data-driven adaptability.
Smart Images
Figure CN120296898A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of mechanical equipment degradation state prediction, and particularly to a method and device for predicting gear degradation state driven by the collaboration of knowledge and data. Background Art
[0002] Gear transmission is widely used in fields such as automobiles, rail transit, ships, and aircraft. As a key component, the performance of gears directly affects the overall operating efficiency and safety of equipment. Therefore, in order to effectively evaluate the health state of gears and prevent potential catastrophic losses, it is of important practical application value to establish a model that can accurately predict the health state of gears.
[0003] However, due to the degradation process of gears being affected by various complex factors, the gear degradation state prediction model constructed based on single data-driven is a black-box model with relatively low reliability and interpretability. To address this problem, a gear degradation state prediction model driven by the collaboration of knowledge and data is proposed. Summary of the Invention
[0004] Based on this, it is necessary to provide a method and device for predicting gear degradation state driven by the collaboration of knowledge and data to more accurately predict the gear degradation state for the above technical problems.
[0005] In a first aspect, this application provides a method for predicting gear degradation state driven by the collaboration of knowledge and data. The method includes:
[0006] Obtain the vibration data of the gear and the acquisition time of the vibration data;
[0007] Input the vibration data and the acquisition time into the middle layer of the first neural network to obtain the solution function of the degradation state, and predict the gear degradation state according to the solution function; based on the gear degradation state, use the middle layer of the second neural network to obtain the degradation dynamics function of the gear, and obtain the predicted degradation speed according to the degradation dynamics function;
[0008] Embed the predicted degradation speed into the loss function, train the prediction model including the middle layer of the first neural network and the middle layer of the second neural network, and predict the gear degradation state based on the trained prediction model.
[0009] In one embodiment, after obtaining the vibration data, the method further includes:
[0010] Perform maximum-minimum normalization processing on the vibration data.
[0011] In one embodiment, predicting the gear degradation state according to the solution function includes:
[0012] Obtain the degradation data of different fault states according to the solution function, and take the derivative of the degradation data to obtain the true degradation speed; the gear degradation state is represented by the degradation data and the true degradation speed.
[0013] In one embodiment, based on the gear degradation state, use the middle layer of the second neural network to obtain the degradation kinetic function of the gear, and obtaining the predicted degradation speed according to the degradation kinetic function includes:
[0014] Input the degradation data, the true degradation speed, and the acquisition time into the middle layer of the second neural network to obtain the degradation kinetic function; solve the first-order partial differential equation for the degradation kinetic function to obtain the predicted degradation speed.
[0015] In one embodiment, the loss function includes a data item loss and a PDE loss; the method further includes:
[0016] Use the data item loss to update the parameters of the middle layer of the first neural network, use the PDE loss to update the parameters of the middle layer of the second neural network, and use the sum of the data item loss and the PDE loss to update the parameters of the prediction model.
[0017] In one embodiment, the middle layer of the first neural network includes a six-layer structure. The first layer is Linear(200)-ReLu, and the output dimension is 60; the second layer is Linear(60)-ReLu-Drouput(0.2), and the output dimension is 60; the third layer is Linear(60), and the output dimension is 10; the fourth layer is Linear(110)-ReLu, and the output dimension is 60; the fifth layer is Linear(60)-ReLu-Drouput(0.2), and the output dimension is 60; the sixth layer is Linear(60), and the output dimension is 1;
[0018] The middle layer of the second neural network includes a three-layer structure. The first layer is Linear(201)-ReLu, and the output dimension is 60; the second layer is Linear(60)-ReLu-Drouput(0.2), and the output dimension is 60; the third layer is Linear(1), and the output dimension is 1.
[0019] In a second aspect, the present application also provides a gear degradation state prediction device driven by knowledge and data collaboration. The device includes:
[0020] An acquisition module, configured to obtain the vibration data of the gear and the acquisition time of the vibration data;
[0021] A knowledge extraction module is used to input vibration data and acquisition time into the middle layer of the first neural network, obtain a solution function for the deterioration state, and predict the gear deterioration state according to the solution function; based on the gear deterioration state, use the middle layer of the second neural network to obtain the deterioration dynamics function of the gear, and obtain the predicted deterioration speed according to the deterioration dynamics function.
[0022] A prediction model construction module is used to embed the predicted deterioration speed into the loss function, train the prediction model including the middle layer of the first neural network and the middle layer of the second neural network, and predict the gear deterioration state based on the trained prediction model.
[0023] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps in the above-mentioned knowledge and data co-driven gear deterioration state prediction method are implemented.
[0024] In a fourth aspect, the present application also provides a computer-readable storage medium. On the computer-readable storage medium, a computer program is stored, and when the computer program is executed by the processor, the steps in the above-mentioned knowledge and data co-driven gear deterioration state prediction method are implemented.
[0025] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by the processor, the steps in the above-mentioned knowledge and data co-driven gear deterioration state prediction method are implemented.
[0026] The above-mentioned knowledge and data co-driven gear deterioration state prediction method and device include: obtaining the vibration data of the gear and the acquisition time of the vibration data; inputting the vibration data and the acquisition time into the middle layer of the first neural network, obtaining a solution function for the deterioration state, and predicting the gear deterioration state according to the solution function; based on the gear deterioration state, using the middle layer of the second neural network to obtain the deterioration dynamics function of the gear, and obtaining the predicted deterioration speed according to the deterioration dynamics function; embedding the predicted deterioration speed into the loss function, training the prediction model including the middle layer of the first neural network and the middle layer of the second neural network, and predicting the gear deterioration state based on the trained prediction model. By predicting the deterioration speed and embedding it as knowledge into the data-driven model, the prediction model not only has the reliability and interpretability of the knowledge-driven model, but also has the advantages of strong adaptability and high-precision prediction of the data-driven end-to-end model, improving the robustness and accuracy of the prediction model. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 It is a flowchart of the knowledge and data co-driven gear deterioration state prediction method in an embodiment.
[0028] Figure 2 It is a training flow chart of a prediction model for an embodiment. Detailed implementation manners
[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0030] The embodiment of the present application provides a method for predicting the deterioration state of gears driven by knowledge and data collaboration, as Figure 1 shown, including the following steps:
[0031] Step 102, obtain the vibration data of the gear and the acquisition time of the vibration data.
[0032] Collect the vibration data and acquisition time of the gear under normal conditions. The vibration data can be collected by using an acceleration sensor. The acceleration sensor can be installed in the horizontal, vertical and axial directions of the bearing seat to comprehensively measure the vibration of the gear; the acceleration sensor can also be installed on the gearbox housing.
[0033] According to the rotational speed and vibration frequency range of the gear, select an appropriate sampling frequency. Generally, the sampling frequency should be at least twice the highest frequency of the signal to avoid signal aliasing. For example, if the highest vibration frequency of the gear is 10 kHz, the sampling frequency should be at least 20 kHz. The number of sampling points determines the length of the collected data. The more sampling points, the more complete the collected data, but at the same time, it will also increase the burden of data storage and processing. Usually, the number of sampling points is determined according to the required data acquisition duration and sampling frequency.
[0034] It should be noted that before collecting the vibration data of the gear, the gear system needs to reach a steady-state operation state. This is because during the start-up and shutdown processes, the vibration of the gear will be affected by various factors, such as inertial force, friction force, etc., and cannot reflect the normal operation state of the gear. Generally, a sound gear system runs for a period of time until its rotational speed, load and other parameters are stable and reach the normal state, and then the data collection starts.
[0035] Step 104, input the vibration data and the acquisition time into the middle layer of the first neural network to obtain the solution function of the deterioration state, and predict the gear deterioration state according to the solution function; based on the gear deterioration state, use the middle layer of the second neural network to obtain the deterioration dynamics function of the gear, and obtain the predicted deterioration speed according to the deterioration dynamics function.
[0036] Both the first neural network intermediate layer and the second neural network intermediate layer are parts of the prediction model. The initial learning rate of the model is set to 0.001. The training data uses a sliding window and non-overlapping sampling, with each sample having a length of 100. The vibration data and acquisition time collected in step 102 are divided into a training set, a validation set, and a test set at a ratio of 6:2:2, and the prediction model is trained.
[0037] In the training phase, Adam is selected as the optimizer, and the mean squared error loss function is used to measure the difference between the predicted value and the true value. 50 samples are trained in each batch, and a total of 1000 training epochs are iterated.
[0038] The first neural network intermediate layer is the solution function F(·) for predicting the deterioration state, which is used to map the data-driven relationship between the gear health state and the fault state, and realize the prediction of the gear deterioration state. The second neural network intermediate layer is a non-linear function for learning the deterioration evolution dynamic behavior from the gear health state to the fault state, that is, the deterioration dynamics function g(·), and the deterioration speed is determined by the deterioration dynamics function.
[0039] In step 106, the predicted deterioration speed is embedded into the loss function, and the prediction model including the first neural network intermediate layer and the second neural network intermediate layer is trained, and the gear deterioration state is predicted based on the trained prediction model.
[0040] The deterioration speed can intuitively reflect the dynamic trend of the deterioration state evolving over time. When predicting the operating state of mechanical equipment, by monitoring the change speed of the equipment vibration amplitude, etc., it is possible to accurately judge whether the equipment is in different stages such as stable operation, performance decline, or about to fail.
[0041] When training the prediction model, integrating the information of the deterioration speed into the loss function can be used to adjust the parameters of the prediction model, guide the prediction model to better learn the pattern of deterioration state changes, realize the collaborative driving of knowledge and data, and the embedding of deterioration knowledge improves the robustness of the model, enabling it to maintain a high prediction accuracy under complex working environments and changing working conditions. The modeling process of this model can be applied to other research objects, providing a guiding method for the modeling of such models driven by knowledge and data collaboration.
[0042] In one embodiment, after acquiring the vibration data, the method further includes: performing maximum-minimum normalization processing on the vibration data.
[0043] To reduce the impact of data differences on model training, maximum-minimum normalization processing is performed on the training data. The maximum-minimum normalization formula is as follows:
[0044]
[0045] where x is the original vibration data value, xmin is the minimum value of the vibration data, x max is the maximum value of the vibration data, y i is the vibration data after normalization.
[0046] Input the vibration data after normalization and the acquisition time into the prediction model together.
[0047] In one embodiment, the solving process of predicting the deterioration rate includes: inputting the vibration data and the acquisition time into the first neural network intermediate layer to obtain a solution function, obtaining the deterioration data of different fault states according to the solution function, and deriving the deterioration data to obtain the true deterioration rate; the gear deterioration state is represented by the deterioration data and the true deterioration rate. Input the deterioration data, the true deterioration rate, and the acquisition time into the second neural network intermediate layer to obtain the deterioration kinetic function; solve the first-order partial differential equation for the deterioration kinetic function to obtain the predicted deterioration rate.
[0048] It should be noted that the true deterioration rate described in this embodiment is not the true speed data in the absolute sense, but a relative concept relative to the predicted deterioration rate. This data is still essentially the speed data predicted by the first neural network intermediate layer.
[0049] The input data first passes through the first neural network intermediate layer F(·) of the model to predict the deterioration data u of different fault states, and derive u with respect to t to obtain the true deterioration rate u t , take the deterioration data u, the deterioration rate u t and the time t as the input of the second layer g(·) of the model, and obtain the predicted deterioration rate by solving the first-order partial differential equation g(t, u, u t , θ) and embed it into the loss function of the neural network intermediate layer to achieve knowledge and data collaborative driving. Among them, θ represents the learnable parameters in the neural network.
[0050] In one embodiment, the loss function includes a data item loss and a PDE loss; the method further includes: updating the parameters of the first neural network intermediate layer using the data item loss, updating the parameters of the second neural network intermediate layer using the PDE loss, and updating the parameters of the prediction model using the sum of the data item loss and the PDE loss.
[0051] The training of the prediction model is iterative training. In each round of iterative update process, the parameters of the first neural network intermediate layer, the second neural network intermediate layer, and the prediction model are updated. Among them, the update of the first neural network intermediate layer is based on the data item loss L data , and the update of the second neural network intermediate layer is based on the PDE (Partial Differential Equation) loss LPDE , the update of the prediction model is based on the loss function L, which is the sum of the data item loss L data and the PDE loss L PDE .
[0052] L data is expressed by the formula as follows:
[0053]
[0054] where i represents the i-th sample, N represents the total number of samples, u i represents the true degradation data under different fault states, represents the model-predicted degradation data.
[0055] L PDE is expressed by the formula as follows:
[0056]
[0057] where u t i represents the true degradation rate, represents the model-predicted degradation rate.
[0058] The formula for the loss function L of the entire prediction model is expressed as:
[0059] L = L data + L PDE .
[0060] As Figure 2 shown, it is the overall flowchart for the training of the prediction model. First, the intermediate layer of the first neural network is iteratively trained and its parameters are updated using the training data until the data item loss is no greater than the first preset value. Then, the true degradation rate is calculated using the degradation data output by the intermediate layer of the first neural network. The true degradation rate, the degradation data, and the sampling time are used as the training data to be input into the intermediate layer of the second neural network for iterative training and parameter update until the PDE loss is no greater than the second preset value. Finally, the data item loss and the PDE loss are added together to calculate the overall loss of the prediction model. If the overall loss is no greater than the third preset value, the training of the prediction model is completed; otherwise, return to the update step of the intermediate layer of the first neural network.
[0061] In one embodiment, the first intermediate neural network layer includes a six-layer structure. The first layer is Linear(200)-ReLu with an output dimension of 60; the second layer is Linear(60)-ReLu-Drouput(0.2) with an output dimension of 60; the third layer is Linear(60) with an output dimension of 10; the fourth layer is Linear(110)-ReLu with an output dimension of 60; the fifth layer is Linear(60)-ReLu-Drouput(0.2) with an output dimension of 60; the sixth layer is Linear(60) with an output dimension of 1. The second intermediate neural network layer includes a three-layer structure. The first layer is Linear(201)-ReLu with an output dimension of 60; the second layer is Linear(60)-ReLu-Drouput(0.2) with an output dimension of 60; the third layer is Linear(1) with an output dimension of 1.
[0062] It is represented in tabular form as follows:
[0063] Table 1 Deterioration state prediction model structure
[0064]
[0065] In Table 1, Linear() represents a linear layer, and the number in the parentheses represents the input dimension of the linear layer; ReLu represents an activation function; Drouput(0.2) represents a Drouput layer with a dropout probability of 0.2; in the output size, Nc represents a variable in the batch dimension, and the data after Nc represents the output dimension.
[0066] The present invention solves the deterioration rate and embeds the gear deterioration rate into the data-driven model, which not only has the reliability and interpretability of the knowledge-driven model but also has the strong adaptability and high-precision prediction advantages of the data-driven end-to-end model, improving the robustness and accuracy of model prediction. In addition, due to the embedding of deterioration knowledge, the gear deterioration state prediction model driven by knowledge and data collaboration can maintain a high prediction accuracy under complex working environments and variable working conditions. Finally, the basic framework of the gear deterioration state model driven by knowledge and data collaboration can be extended to the deterioration prediction of other mechanical components (such as bearings and turbines, etc.), with technical generality and scalability.
[0067] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown in the direction of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.
[0068] Based on the same inventive concept, an embodiment of the present application further provides a knowledge and data collaborative driven gear degradation state prediction device for implementing the knowledge and data collaborative driven gear degradation state prediction method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the knowledge and data collaborative driven gear degradation state prediction device provided below can refer to the limitations on the knowledge and data collaborative driven gear degradation state prediction method in the above text, and will not be repeated here.
[0069] In one embodiment, a knowledge and data collaborative driven gear degradation state prediction device is provided, including:
[0070] An acquisition module, configured to acquire vibration data of the gear and the acquisition time of the vibration data;
[0071] A knowledge extraction module, configured to input the vibration data and the acquisition time into the intermediate layer of the first neural network to obtain a solution function of the degradation state, and predict the gear degradation state according to the solution function; based on the gear degradation state, use the intermediate layer of the second neural network to obtain the degradation dynamics function of the gear, and obtain the predicted degradation speed according to the degradation dynamics function;
[0072] A prediction model construction module, configured to embed the predicted degradation speed into a loss function, train a prediction model including the intermediate layer of the first neural network and the intermediate layer of the second neural network, and perform gear degradation state prediction based on the trained prediction model.
[0073] Each module in the above knowledge and data collaborative driven gear degradation state prediction device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules.
[0074] In one embodiment, a computer device is provided, which includes a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in all the above method embodiments are implemented.
[0075] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in all the above method embodiments are implemented.
[0076] In one embodiment, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, the steps in all the above method embodiments are implemented.
[0077] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. And the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.
[0078] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random-access memories (ReRAMs), magnetoresistive random-access memories (MRAMs), ferroelectric random-access memories (FRAMs), phase change memories (PCMs), graphene memories, etc. Volatile memories can include random access memories (RAMs) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.
[0079] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.
[0080] The above-described embodiments merely represent several implementation manners of this application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.
Claims
1. A method for predicting the deterioration state of gears driven by knowledge and data collaboration, characterized in that The method includes: Obtaining the vibration data of the gear and the acquisition time of the vibration data; Inputting the vibration data and the acquisition time into the middle layer of the first neural network to obtain the solution function of the degradation state, and predicting the gear degradation state according to the solution function; Based on the gear degradation state, using the middle layer of the second neural network to obtain the degradation dynamics function of the gear, and obtaining the predicted degradation speed according to the degradation dynamics function; Embedding the predicted degradation speed into the loss function, training the prediction model including the middle layer of the first neural network and the middle layer of the second neural network, and predicting the gear degradation state based on the trained prediction model.
2. The method according to claim 1, wherein After obtaining the vibration data, the method further includes: Performing max-min normalization processing on the vibration data.
3. The method according to claim 1, wherein The predicting the gear degradation state according to the solution function includes: Obtaining the degradation data of different fault states according to the solution function, and taking the derivative of the degradation data to obtain the true degradation speed; The gear degradation state is represented by the degradation data and the true degradation speed.
4. The method according to claim 3, characterized in that, The obtaining the degradation dynamics function of the gear by using the middle layer of the second neural network based on the gear degradation state and obtaining the predicted degradation speed according to the degradation dynamics function includes: Inputting the degradation data, the true degradation speed, and the acquisition time into the middle layer of the second neural network to obtain the degradation dynamics function; Solving the first-order partial differential equation of the degradation dynamics function to obtain the predicted degradation speed.
5. The method according to claim 1, characterized in that, The loss function includes a data term loss and a PDE loss; The method further includes: Updating the parameters of the middle layer of the first neural network by using the data term loss, updating the parameters of the middle layer of the second neural network by using the PDE loss, and updating the parameters of the prediction model by using the sum of the data term loss and the PDE loss.
6. The method according to claim 1, characterized in that, The middle layer of the first neural network includes a six-layer structure. The first layer is Linear(200)-ReLu with an output dimension of 60; the second layer is Linear(60)-ReLu-Drouput(0.2) with an output dimension of 60; the third layer is Linear(60) with an output dimension of 10; the fourth layer is Linear(110)-ReLu with an output dimension of 60; the fifth layer is Linear(60)-ReLu-Drouput(0.2) with an output dimension of 60; the sixth layer is Linear(60) with an output dimension of 1; The middle layer of the second neural network includes a three-layer structure. The first layer is Linear(201)-ReLu with an output dimension of 60; the second layer is Linear(60)-ReLu-Drouput(0.2) with an output dimension of 60; the third layer is Linear(1) with an output dimension of 1.
7. A gear deterioration state prediction device driven by knowledge and data collaboration, characterized in that The device includes: An acquisition module for obtaining the vibration data of the gear and the acquisition time of the vibration data; A knowledge extraction module, which is used to input the vibration data and the acquisition time into the intermediate layer of the first neural network, obtain a solution function for the deterioration state, and predict the gear deterioration state according to the solution function; based on the gear deterioration state, use the intermediate layer of the second neural network to obtain a gear deterioration dynamics function, and obtain a predicted deterioration speed according to the deterioration dynamics function. A prediction model construction module, which is used to embed the predicted deterioration speed into a loss function, train a prediction model including the intermediate layer of the first neural network and the intermediate layer of the second neural network, and predict the gear deterioration state based on the trained prediction model.
8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.