Method and device for predicting residual life of mechanical equipment, equipment and medium

Abstract

The invention discloses a residual life prediction method and device for mechanical equipment, equipment and a medium, and relates to the field of residual life prediction, and the method comprises the steps: obtaining the equipment data of target mechanical equipment at the current moment; constructing and training a residual life prediction model; the residual life prediction model comprises a smoothing processing unit, a feature extraction unit and a prediction unit; in the training process of the residual life prediction model, a Bayesian optimization algorithm is adopted to optimize hyper-parameters of the residual life prediction model; and inputting the equipment data of the target mechanical equipment at the current moment into the trained residual life prediction model for residual life prediction to obtain the residual life of the target mechanical equipment, thereby improving the accuracy of the residual life prediction result of the mechanical equipment.

Description

Technical Field

[0001] This application relates to the field of remaining life prediction, and particularly to a method, device, equipment and medium for predicting the remaining life of mechanical equipment. Background Art

[0002] Mechanical equipment is currently widely used in various fields such as industry, aerospace, etc. Most mechanical equipment needs to run for a long time, and internal components will inevitably wear and age, performance decline or even fail, which will lead to major accidents and losses. Therefore, it is of great practical significance to timely and accurately predict the remaining service life of mechanical equipment and implement scientific and reasonable maintenance measures according to the remaining life prediction results to prevent serious equipment failures and ensure the safe and stable operation of the equipment.

[0003] Deep learning methods have achieved successful applications in many fields in recent years due to their powerful feature learning and representation capabilities. For example, deep belief networks, convolutional neural networks, long short-term memory networks and Transformer models have been used in the fields of equipment fault diagnosis and condition assessment. However, the hidden layers of the above deep learning models are generally numerous, the model structure is relatively complex, and there are disadvantages such as poor interpretability and cumbersome model training processes.

[0004] The structure of the Generalized regression neural networks (GRNN) model is relatively simple, and the training of the model does not require iteration. A large number of research results show that compared with the BackPropagation (BP) neural network and support vector machine, the GRNN model has a faster training speed and better generalization ability. Therefore, the GRNN model has broad application prospects in the fields of fault diagnosis and state prediction. Considering that there are many hyperparameters in the remaining life prediction model generally based on the GRNN model, if the values of the hyperparameters of the model are set manually and randomly, the optimal result is often not obtained, resulting in a low accuracy of the prediction result. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, equipment and medium for predicting the remaining life of mechanical equipment, which can improve the accuracy of the prediction result of the remaining life of mechanical equipment.

[0006] To achieve the above purpose, this application provides the following solutions: In the first aspect, this application provides a method for predicting the remaining life of mechanical equipment, including: Obtain the equipment data of the target mechanical equipment at the current moment; Build and train a remaining useful life prediction model; the remaining useful life prediction model includes a smoothing processing unit, a feature extraction unit, and a prediction unit; during the training process of the remaining useful life prediction model, the Bayesian optimization algorithm is used to optimize the hyperparameters of the remaining useful life prediction model; Input the equipment data of the target mechanical equipment at the current moment into the trained remaining useful life prediction model for remaining useful life prediction to obtain the remaining useful life of the target mechanical equipment.

[0007] In a second aspect, the present application provides a device for predicting the remaining useful life of a mechanical equipment, including: An acquisition module, configured to acquire the equipment data of the target mechanical equipment at the current moment; A construction module, configured to build and train a remaining useful life prediction model; the remaining useful life prediction model includes a smoothing processing unit, a feature extraction unit, and a prediction unit; during the training process of the remaining useful life prediction model, the Bayesian optimization algorithm is used to optimize the parameters of the remaining useful life prediction model; A prediction module, configured to input the equipment data of the target mechanical equipment at the current moment into the trained remaining useful life prediction model for remaining useful life prediction to obtain the remaining useful life of the target mechanical equipment.

[0008] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the above-mentioned method for predicting the remaining useful life of a mechanical equipment.

[0009] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the above-mentioned method for predicting the remaining useful life of a mechanical equipment.

[0010] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application: The present application provides a method, device, equipment, and medium for predicting the remaining useful life of a mechanical equipment. By acquiring the equipment data of the target mechanical equipment at the current moment and inputting the equipment data of the target mechanical equipment at the current moment into the trained remaining useful life prediction model for remaining useful life prediction, the trained remaining useful life prediction model is set with optimal hyperparameters, and the optimal hyperparameters are obtained by optimizing through the Bayesian optimization algorithm. Compared with setting hyperparameters manually, the parameter values obtained by optimizing through the Bayesian optimization algorithm are better. Based on this, the remaining useful life of the mechanical equipment is predicted, and the obtained prediction result has higher accuracy. Description of the Drawings

[0011] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0012] Figure 1 It is an application environment diagram of a method for predicting the remaining life of a mechanical device in an embodiment of the present application; Figure 2 It is a schematic flowchart of a method for predicting the remaining life of a mechanical device provided in an embodiment of the present application; Figure 3 It is a schematic flowchart of another method for predicting the remaining life of a mechanical device provided in an embodiment of the present application; Figure 4 It is a structural diagram of a GRNN model provided in another embodiment of the present application; Figure 5 It is a schematic diagram of the functional modules of a device for predicting the remaining life of a mechanical device provided in an embodiment of the present application; Figure 6 It is a schematic structural diagram of a computer device provided in an embodiment of the present application. Detailed implementation manners

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0014] To make the purpose, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0015] The method for predicting the remaining life of a mechanical device provided in the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set separately, integrated on the server 104, placed on the cloud or other servers. The terminal 102 can send the device data of the target mechanical equipment at the current moment to the server 104. After receiving the device data of the target mechanical equipment at the current moment, for the device data of the target mechanical equipment at the current moment, the server 104 constructs and trains a remaining life prediction model; the remaining life prediction model includes a smoothing processing unit, a feature extraction unit, and a prediction unit; during the training process of the remaining life prediction model, the Bayesian optimization algorithm is used to optimize the hyperparameters of the remaining life prediction model; the device data of the target mechanical equipment at the current moment is input into the trained remaining life prediction model for remaining life prediction, and the remaining life of the target mechanical equipment is obtained. The server 104 can feedback the obtained remaining life of the target mechanical equipment to the terminal 102. In addition, in some embodiments, the mechanical equipment remaining life prediction method can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly perform remaining life prediction processing on the device data of the target mechanical equipment at the current moment, or the server 104 can obtain the device data of the target mechanical equipment at the current moment from the data storage system and perform remaining life prediction processing on the device data of the target mechanical equipment at the current moment.

[0016] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0017] In an exemplary embodiment, such as Figure 2 and Figure 3 shown, a method for predicting the remaining life of mechanical equipment is provided. This method is executed by a computer device, and specifically can be executed independently by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the server 104 in as an example for illustration, it includes the following steps 201 to step 203. Among them:

[0018] Step 201, obtain the device data of the target mechanical equipment at the current moment.Step 202, construct and train a remaining useful life prediction model; the remaining useful life prediction model includes a smoothing processing unit, a feature extraction unit, and a prediction unit; during the training process of the remaining useful life prediction model, the Bayesian optimization algorithm is used to optimize the hyperparameters of the remaining useful life prediction model.

[0019] Step 203, input the equipment data of the target mechanical equipment at the current moment into the trained remaining useful life prediction model for remaining useful life prediction, and obtain the remaining useful life of the target mechanical equipment.

[0020] Executing the method of steps 201 - 203 can improve the accuracy of the remaining useful life prediction result of the mechanical equipment.

[0021] In an exemplary embodiment, step 203 specifically includes steps 301 - 303: Step 301, input the equipment data of the target mechanical equipment at the current moment into the smoothing processing unit for smoothing filtering processing, and obtain the equipment data after smoothing filtering.

[0022] Specifically, the smoothing processing unit uses the mean filtering method to perform smoothing filtering processing on the equipment data of the target mechanical equipment at the current moment.

[0023] In industrial automation and control systems, the mean filtering method is widely used to remove noise from the data collected by sensors, improving the stability and reliability of the system. Therefore, in this embodiment, the mean filtering method is used to denoise the data collected by the sensors. Denote the original collected data as and then calculate the arithmetic mean of the data collected by each sensor within the window width parameter . Then the calculation formula of the mean filtering method is: (1); where, is the equipment data after smoothing filtering processing, , m is the data dimension, , is the operating time of the mechanical equipment, is the window width parameter, and c is a constant.

[0024] Step 302, input the equipment data after smoothing filtering into the feature extraction unit for feature extraction, and obtain the degradation features of the target mechanical equipment. Specifically, the feature extraction unit uses the principal component analysis method to perform feature extraction on the equipment data after smoothing filtering, and obtain the degradation features of the target mechanical equipment.

[0025] Although the data quality after smoothing filtering is improved compared with the original data, due to the large number of general sensors, there are some useless data or data redundancy. As the data dimension increases, the number of samples required for algorithm learning increases exponentially. Directly using the device data after smoothing filtering is not conducive to the training and use of the remaining useful life prediction model. Therefore, in this embodiment, the Kernel Principal Component Analysis (KPCA) method is used to extract features from the device data after smoothing filtering.

[0026] KPCA is a non-linear data processing method. Its core idea is to project the data in the original space into a high-dimensional feature space through a non-linear mapping, and then perform data processing based on principal component analysis in the high-dimensional feature space. The algorithm steps for feature extraction based on KPCA are as follows: 1. Select the Gaussian radial basis function as the kernel function: (2); Among them, is the kernel parameter.

[0027] 2. Calculate the kernel matrix , The element in the p-th row and q-th column of satisfies: , , where is the vector of the p-th column of , is the device data after smoothing filtering.

[0028] 3. Calculate the centered kernel matrix , and the calculation formula is: (3); Among them, is an n-dimensional matrix with all elements being 1.

[0029] 4. Perform eigenvalue decomposition on the centered kernel matrix , , after sorting the eigenvalues by size, the eigenvalues are , and the corresponding eigenvectors are .

[0030] 5. Take the first principal component as the degradation feature of the mechanical equipment, where is the transpose of the vector.

[0031] Step 303: Input the degradation features into the prediction unit for remaining useful life prediction to obtain the remaining useful life of the target mechanical equipment.

[0032] Specifically, the prediction unit uses the GRNN model to predict the remaining useful life of the target mechanical equipment to obtain the remaining useful life of the target mechanical equipment.

[0033] Using the result obtained in step 302 as the input of the prediction unit, and using the actual life of the mechanical equipment as the output to conduct learning and training on the GRNN model.

[0034] The GRNN model belongs to a variant form of the radial basis neural network. The theoretical basis of the GRNN model is non-linear kernel regression analysis. The regression analysis of non-independent variables relative to independent variables is actually to calculate the one with the maximum probability value . Let the random variables and have a joint probability density function of . Given the actual observed value as , that is, the collected original data, is all the data collected by the sensor when the mechanical equipment runs to a certain moment, including the engine low-pressure turbine outlet temperature, fan inlet pressure, uncorrected core engine speed, core engine corrected speed, bypass ratio, total pressure of the outer bypass duct, engine pressure ratio, static pressure at the outlet of the high-pressure compressor, and fan corrected speed.

[0035] The training samples are composed of degradation features and the actual values of the corresponding remaining useful life. Then relative to the regression, that is, the conditional mean is: (4); For the unknown probability density function , is the degradation feature the actual value of the corresponding remaining useful life.

[0036] (5); Where: and are the degradation feature corresponding to the i-th training sample and the actual value of the remaining useful life corresponding to the i-th training sample, is the smoothing factor, is the number of training samples. Using to replace in formula (4), the calculation gives: (6); Denote: (7); Among them, measures the similarity between the input vector and the degradation feature to complete the non-linear mapping from the input space to the high-dimensional feature space.

[0037] (8); (9); Among them, the summation layer has a total of neurons, including neurons and one neuron. is the th neuron of the summation layer, is the actual value of the remaining life corresponding to the degradation feature , and the sum of the weighted outputs of all neurons in the pattern layer .

[0038] (10); Among them, is the sum of the outputs of all neurons in the pattern layer.

[0039] Then formula (6) can be simplified and expressed as: (11); Formulas (4)-(11) can be described by the GRNN four-layer network structure model, and the network structure of GRNN is as Figure 4 shown.

[0040] The original data collected is subjected to smoothing filtering and KPCA feature extraction processing in steps 301 and 302 to obtain the degradation features of the mechanical equipment, that is, the input vector . After the degradation features are input into the GRNN network, the output results are obtained after passing through the input layer, pattern layer, summation layer, and output layer in sequence. Among them, the number of neurons in the input layer is equal to the vector dimension in the learning sample; the number of neurons in the pattern layer is equal to the number of learning samples.

[0041] The input layer receives the input vector and directly transfers it to the pattern layer. There is no actual calculation operation in this layer, only data transmission.

[0042] The pattern layer has neurons, and each neuron corresponds to a training sample. For the th neuron, its input is , the output is . The pattern layer calculates the similarity between the input vector and each training sample vector through the Gaussian function, completing the non-linear mapping from the input space to the high-dimensional feature space.

[0043] Let the connection coefficient between the pattern layer and the neurons in the summation layer be 1, and the connection coefficient with the remaining neurons in the summation layer be . The final output is obtained through formulas (8) - (11).

[0044] In an exemplary embodiment, the remaining useful life prediction model includes multiple hyperparameters, and the hyperparameters include the window width parameter , the kernel parameter and the smoothing factor . The window width parameter , the kernel parameter and the smoothing factor constitute a hyperparameter combination. In step 202, the Bayesian Optimization (BO) algorithm is used to optimize the hyperparameters of the remaining useful life prediction model, specifically including steps 401 - 407: Step 401, define the hyperparameter combination space, and randomly select multiple groups of hyperparameter combinations from the hyperparameter combination space as the initial hyperparameter combinations; the hyperparameter combination space includes multiple groups of hyperparameter combinations.

[0045] Step 402, construct an objective function with the goal of minimizing the mean absolute error between the predicted remaining useful life output by the remaining useful life prediction model and the actual remaining useful life during the training process, and calculate the objective function value of each group of initial hyperparameter combinations through the objective function.

[0046] Specifically, the data sampled by the sensor is divided into a training set , a validation set and a test set . Find a group of hyperparameter combinations within the hyperparameter combination space such that the mean absolute error of the remaining useful life prediction results of the validation set is minimized: (12); where is the objective function, and is the mean absolute error of the remaining useful life prediction results of the validation set.

[0047] Step 403, construct an initial data set, the initial data set includes multiple initial data points, and the initial data points include the initial hyperparameter combinations and the corresponding objective function values.

[0048] Specifically, randomly sample the initial hyperparameter combinations: randomly select init groups of hyperparameter combinations within the hyperparameter combination space to form an initial dataset by running the objective function for each initial hyperparameter combination to obtain the corresponding objective function values ; where is the i th group of initial hyperparameter combinations, and is the objective function value of the i th group of initial hyperparameter combinations

[0049] Step 404, construct a Gaussian surrogate model based on the initial dataset; the Gaussian surrogate model is used to estimate the distribution of the objective function over the entire hyperparameter space according to the initial data points

[0050] For the init initial hyperparameter combinations , their corresponding objective function values are respectively . Assume that follows a Gaussian distribution, that is: .

[0051] Where: is the mean vector predicted by the Gaussian process, is the calculation function of the mean. Let be initialized as a zero vector

[0052] Covariance matrix: (13); The covariance function is used to measure the similarity between the th group of initial hyperparameter combinations and the th group of hyperparameter combinations

[0053] Step 405, use the gradient ascent algorithm to find the hyperparameter combination that maximizes the value of the expected improvement function in the entire hyperparameter combination space as the new hyperparameter combination, and evaluate the new hyperparameter combination using the objective function to obtain the objective function value of the new hyperparameter combination; the expected improvement function is composed of the minimum value of the objective function values in the initial dataset and the variance of the Gaussian surrogate model

[0054] Specifically, select the next evaluation point based on the expected improvement function: For the Gaussian process, the predicted posterior distribution of a new hyperparameter combination also follows a Gaussian distribution. For a certain new hyperparameter combination , the predicted corresponding objective function value is .

[0055] ​According to the conditional probability property of the Gaussian process, the mean of the posterior distribution and the covariance matrix are respectively: (14); (15); The formula for calculating the variance of the posterior distribution is: (16); Denote the current optimal value of the objective function among the init initial hyperparameter combinations , ,…, as: (17); Using the Expected Improvement (EI) function as the acquisition function, for the new hyperparameter combination point , its expected improvement function is: (18); (19); Where: is the expectation; and are respectively the cumulative distribution function (CDF) and the probability density function (PDF) of the standard normal distribution.

[0056] Based on the above principle, find the point that maximizes the value of the expected improvement function through the gradient ascent algorithm

[0057] as the next evaluation point, that is, the new hyperparameter combination. Evaluate the objective function at the selected new hyperparameter combination .

[0058] Step 406, add the new hyperparameter combination and the objective function value of the new hyperparameter combination as new data points to the initial data set, and iteratively update the mean and variance of the Gaussian surrogate model until the set maximum number of iterations is reached.

[0059] Specifically, add the new hyperparameter combination to the initial data set: ; where is the updated data set.

[0060] Step 407, select the hyperparameter combination with the minimum objective function value from all the evaluated hyperparameter combinations as the optimal hyperparameter combination.

[0061] Finally, through the test set Verify the remaining life prediction performance of the constructed remaining life prediction model.

[0062] Based on the same inventive concept, an embodiment of the present application further provides a remaining life prediction device for a mechanical device for implementing the above-mentioned remaining life prediction method for a mechanical device. 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 remaining life prediction device for a mechanical device provided below can refer to the limitations on the remaining life prediction method for a mechanical device in the above text, and will not be repeated here.

[0063] In an exemplary embodiment, as Figure 5 shown, a remaining life prediction device for a mechanical device is provided, including: An acquisition module 51, configured to acquire device data of a target mechanical device at the current moment.

[0064] A construction module 52, configured to construct and train a remaining life prediction model; the remaining life prediction model includes a smoothing processing unit, a feature extraction unit, and a prediction unit; during the training process of the remaining life prediction model, a Bayesian optimization algorithm is used to optimize the parameters of the remaining life prediction model.

[0065] A prediction module 53, configured to input the device data of the target mechanical device at the current moment into the trained remaining life prediction model for remaining life prediction, and obtain the remaining life of the target mechanical device.

[0066] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the device data of the target mechanical device at the current moment. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements the remaining life prediction method for a mechanical device.

[0067] Those skilled in the art can understand,Figure 6 The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component arrangement.

[0068] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0069] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0070] 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 relevant regulations.

[0071] 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 the present 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 memory (RAM) 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.

[0072] The databases involved in the embodiments provided in the present 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 the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0073] 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.

[0074] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for predicting the remaining life of mechanical equipment, characterized in that: include: Obtain the equipment data of the target mechanical equipment at the current moment; Constructing and training a remaining life prediction model; the remaining life prediction model includes a smoothing processing unit, a feature extraction unit and a prediction unit; during the training process of the remaining life prediction model, a Bayesian optimization algorithm is used to optimize the hyperparameters of the remaining life prediction model; The equipment data of the target mechanical equipment at the current moment is input into the trained remaining life prediction model to perform remaining life prediction to obtain the remaining life of the target mechanical equipment.

2. The method for predicting the remaining service life of mechanical equipment according to claim 1, characterized in that: Inputting the equipment data of the target mechanical equipment at the current moment into the trained remaining life prediction model to perform remaining life prediction, and obtaining the remaining life of the target mechanical equipment, including: Inputting the equipment data of the target mechanical equipment at the current moment into the smoothing processing unit for smoothing filtering to obtain the equipment data after smoothing filtering; The smoothed and filtered equipment data is input into a feature extraction unit for feature extraction to obtain degradation features of the target mechanical equipment; The degradation characteristics are input into the prediction unit to perform remaining life prediction to obtain the remaining life of the target mechanical equipment.

3. The method for predicting the remaining service life of mechanical equipment according to claim 2, characterized in that: The smoothing processing unit uses a mean filtering method to perform smoothing filtering on the equipment data of the target mechanical equipment at the current moment.

4. The method for predicting the remaining service life of mechanical equipment according to claim 3, characterized in that: The calculation formula of the mean filtering method is: ； in, To smooth the device data after filtering, , m is the data dimension, , is the operating time of the mechanical equipment, is the window width parameter and c is a constant.

5. The method for predicting the remaining service life of mechanical equipment according to claim 2, characterized in that: The feature extraction unit uses principal component analysis to extract features from the smoothed and filtered equipment data to obtain degradation features of the target mechanical equipment.

6. The method for predicting the remaining service life of mechanical equipment according to claim 2, characterized in that: The prediction unit uses the GRNN model to predict the remaining life of the target mechanical equipment to obtain the remaining life of the target mechanical equipment.

7. The method for predicting the remaining service life of mechanical equipment according to claim 1, characterized in that: The remaining life prediction model includes multiple hyperparameters, and the multiple hyperparameters constitute a hyperparameter combination; Among them, the Bayesian optimization algorithm is used to optimize the hyperparameters of the remaining life prediction model, including: Defining a hyperparameter combination space, and randomly selecting multiple sets of hyperparameter combinations from the hyperparameter combination space as initial hyperparameter combinations; the hyperparameter combination space includes multiple sets of hyperparameter combinations; An objective function is constructed with the goal of minimizing the mean absolute error between the predicted remaining life output by the remaining life prediction model and the actual remaining life during the training process, and the objective function value of each set of initial hyperparameter combinations is calculated through the objective function; Construct an initial data set, which includes multiple initial data points. The initial data points include initial hyperparameter combinations and corresponding objective function values. Constructing a Gaussian surrogate model based on the initial data set; the Gaussian surrogate model is used to estimate the distribution of the objective function in the entire hyperparameter combination space according to the initial data points; Using a gradient ascent algorithm, a hyperparameter combination that maximizes the expected boost function value is searched in the entire hyperparameter combination space as a new hyperparameter combination, and the new hyperparameter combination is evaluated using an objective function to obtain an objective function value of the new hyperparameter combination; the expected boost function is composed of the minimum value of the objective function value in the initial data set and the variance of the Gaussian surrogate model; The new hyperparameter combination and the objective function value of the new hyperparameter combination are added as new data points to the initial data set, and the mean and variance of the Gaussian surrogate model are iteratively updated until the set maximum number of iterations is reached; The hyperparameter combination with the smallest objective function value is selected from all evaluated hyperparameter combinations as the optimal hyperparameter combination.

8. A device for predicting the remaining life of mechanical equipment, characterized in that: include: An acquisition module is used to acquire the equipment data of the target mechanical equipment at the current moment; A construction module is used to construct and train a remaining life prediction model; the remaining life prediction model includes a smoothing processing unit, a feature extraction unit and a prediction unit; during the training process of the remaining life prediction model, a Bayesian optimization algorithm is used to optimize the parameters of the remaining life prediction model; The prediction module is used to input the equipment data of the target mechanical equipment at the current moment into the trained remaining life prediction model to perform remaining life prediction and obtain the remaining life of the target mechanical equipment.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for predicting the remaining life of mechanical equipment according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting the remaining life of mechanical equipment described in any one of claims 1 to 7 is implemented.

Images