Continuous learning performance degradation prediction method and device based on stability-plasticity balance and electronic equipment

Abstract

The invention discloses a continuous learning performance degradation prediction method and device based on stability-plasticity balance and electronic equipment, and the method comprises the steps: obtaining an equipment performance state data set dynamically updated by equipment in different operation task scenes in real time according to the operation task scenes of the equipment; constructing a performance degradation prediction DP-GRUC model based on a convolutional gating network, and training the DP-GRUC model through a continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance state data set to obtain a trained DP-GRUC model; and performing performance degradation prediction on the to-be-tested equipment in the target task scene based on the trained DP-GRUC model.

Description

Technical Field

[0001] The present invention relates to the technical field of performance degradation prediction, and in particular to a method, device and electronic equipment for predicting performance degradation based on continuous learning of stability-plasticity balance. Background Art

[0002] The trend of continuous industrial digitalization has increased the complexity of industrial equipment systems, and also led to high complexity and low predictability of failures. The equipment performance degradation process is jointly affected by three important factors, namely initial degradation, common degradation and differential degradation.

[0003] Common degradation factors make the performance degradation process of the equipment predictable. However, the initial degradation factors determine that different equipment has different degradation starting points. Differential degradation factors determine the differences in degradation characteristics between individual equipment. Therefore, how can the equipment performance degradation prediction model consolidate common degradation characteristics in the context of continuously added prediction tasks to achieve a balance between the model's historical task stability and new task plasticity? Summary of the invention

[0004] The present invention provides a method, device and electronic device for predicting continuous learning performance degradation based on stability-plasticity balance, so as to solve the technical problem of how to consolidate common degradation characteristics in continuously newly added prediction tasks.

[0005] An embodiment of the present invention provides a continuous learning performance degradation prediction method based on stability-plasticity balance, comprising: according to the device operation task scenario, obtaining in real time a device performance status data set that is dynamically updated under different operation task scenarios; constructing a performance degradation prediction DP-GRUC model based on a convolutional gated network, and training the DP-GRUC model through a continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the device performance status data set to obtain a trained DP-GRUC model; and predicting performance degradation of a device to be tested under a target task scenario based on the trained DP-GRUC model.

[0006] Preferably, the DP-GRUC model consists of a history encoder module, a future encoder module and a HI trajectory decoder module.

[0007] Preferably, the equipment operation task scenario includes any of the following: new monitoring data, new operating conditions, new equipment individuals and new equipment models.

[0008] Preferably, the DP-GRUC model is trained by the continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance status data set to obtain the trained DP-GRUC model, including: initializing the DP-GRUC model by randomly initializing the model weights; inputting the equipment performance status data set under any task scenario of the equipment into the initialized DP-GRUC model to fit the historical health indicator HI trajectory and the future health indicator HI trajectory, and obtaining and saving the DP-GRUC model after the first training under the task scenario.

[0009] Preferably, inputting the equipment performance status data set under any task scenario of the equipment into the initialized DP-GRUC model to fit the historical health indicator HI trajectory gradient and the future health indicator HI trajectory gradient includes: dividing the equipment performance status data set under any task scenario of the equipment into a number of time window HI trajectories by sliding window cutting, and setting the first half of the data in the sliding window as the historical HI trajectory, and setting the second half as the corresponding future HI trajectory; calculating the historical HI trajectory gradient and the future HI trajectory gradient based on the historical HI trajectory and the future HI trajectory respectively; based on the historical HI trajectory gradient and the future HI trajectory gradient, inputting the historical HI trajectory gradient into the historical encoder for historical coding update, and outputting the historical HI trajectory coding; at the same time, inputting the future HI trajectory gradient into the future encoder for future coding update, and outputting the future HI trajectory coding; combining the output historical HI trajectory coding and the future HI trajectory coding into a degradation feature association key value.

[0010] Preferably, respectively calculating the historical HI trajectory gradient and the future HI trajectory gradient based on the historical HI trajectory and the future HI trajectory comprises:

[0011]

[0012] in, represents the historical HI trajectory gradient; points represent the future HI trajectory gradient; Indicates the device performance status of device i at time t; Indicates the device performance status of device i at time t-1; Indicates the current moment.

[0013] Preferably, the DP-GRUC model is trained by the continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance status data set to obtain the trained DP-GRUC model, which also includes: when any task scenario triggers the update of the DP-GRUC model, the equipment performance status data set of the newly added task scenario of the task scenario and the DP-GRUC model after the training of the previous task are obtained; by inputting the equipment performance status data set of the newly added task scenario of the task scenario into the DP-GRUC model after the training of the previous task, and calculating the elastic weight consolidation and the training loss function of the current task based on the continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation; the DP-GRUC model after the training of the previous task is trained by minimizing the training loss function by the gradient descent method to obtain the DP-GRUC model after the training of the current task.

[0014] Preferably, the training loss function is minimized as:

[0015] In the formula, represents the training loss function; represents the training loss function of task B, represents the elastic modulus; represents the model parameters, represents the optimal model parameters of model A, represents parameter weight; Represents a model function.

[0016] An embodiment of the present invention also provides a continuous learning performance degradation prediction device based on stability-plasticity balance, including: an acquisition module, used to acquire in real time a device performance status data set dynamically updated under different operation task scenarios according to the device operation task scenario; a construction and training module, used to construct a performance degradation prediction DP-GRUC model based on a convolutional gated network, and train the DP-GRUC model through a continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the device performance status data set to obtain a trained DP-GRUC model; a prediction module, used to predict the performance degradation of the device under test in the target task scenario based on the trained DP-GRUC model.

[0017] An embodiment of the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the method for predicting continuous learning performance degradation based on stability-plasticity balance are implemented.

[0018] The beneficial effects of the present invention are as follows: (1) Aiming at the performance degradation prediction problem of complex system equipment, a performance degradation prediction model based on convolutional gated network is proposed. The DP-GRUC model mines performance degradation features through convolutional layers and fits them into degradation feature associated key values ​​through gated neural networks. Based on the mapping relationship between historical HI trajectories and future HI trajectories fitted by the decoder, the model can accurately predict the performance of the equipment at future moments.

[0019] (2) Aiming at the continuous learning needs of equipment performance degradation prediction, a degradation feature memory model based on elastic weight consolidation is designed based on the DP-GRUC model. This model realizes the memory and consolidation of historical performance degradation features by constraining the learning direction of the neural network during the training process, while ensuring the learning ability of new prediction tasks. It achieves a stability-plasticity balance in the performance degradation prediction task during the dynamic update of the model.

[0020] (3) Based on the proposed performance degradation prediction model based on convolutional gated networks and the degradation feature memory model based on elastic weight consolidation, a set of elastic weight consolidation continuous learning processes for performance degradation prediction tasks was designed. This process designed different task addition scenarios, and based on the general classification task continuous learning indicators, designed APRMSE and BTRMSE evaluation indicators for performance degradation prediction tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flow chart of a method for predicting continuous learning performance degradation based on stability-plasticity balance provided by the present invention; Figure 2 It is a flow chart of a method for predicting continuous learning performance degradation based on elastic weight consolidation provided by an embodiment of the present invention; Figure 3 It is a flow chart of elastic weight consolidation continuous learning for performance degradation prediction tasks provided by an embodiment of the present invention; Figure 4 is a schematic diagram of a task accuracy matrix provided by an embodiment of the present invention; FIG5 is a flow chart of the DP-GRUC performance degradation prediction model structure and training method provided in an embodiment of the present invention; Figure 6 is a schematic diagram of elastic weight consolidation training provided by an embodiment of the present invention; FIG. 7 is a schematic diagram of the Laplace approximation probability density provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. In the subsequent description, the use of suffixes such as "module", "component" or "unit" used to represent elements is only to facilitate the description of the present invention and has no specific meaning in itself. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0023] Figure 1 is a flow chart of a method for predicting continuous learning performance degradation based on stability-plasticity balance provided by the present invention, such as Figure 1 As shown, it includes: step S1: according to the equipment operation task scenario, the equipment performance status data set that is dynamically updated in different operation task scenarios is obtained in real time; step S2: a performance degradation prediction DP-GRUC model based on a convolutional gated network is constructed, and the DP-GRUC model is trained by a continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance status data set to obtain a trained DP-GRUC model; step S3: based on the trained DP-GRUC model, the performance degradation of the equipment to be tested in the target task scenario is predicted.

[0024] In the embodiment of the present invention, the DP-GRUC model is composed of a history encoder module, a future encoder module and a HI trajectory decoder module.

[0025] In an embodiment of the present invention, the equipment operation task scenario includes any of the following: newly added monitoring data, newly added operating conditions, newly added equipment individuals and newly added equipment models.

[0026] In an embodiment of the present invention, the DP-GRUC model is trained by the continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance status data set to obtain the trained DP-GRUC model, including: initializing the DP-GRUC model by randomly initializing the model weights; inputting the equipment performance status data set under any task scenario of the equipment into the initialized DP-GRUC model to fit the historical health indicator HI trajectory and the future health indicator HI trajectory, and obtaining and saving the DP-GRUC model after the first training under the task scenario.

[0027] In an embodiment of the present invention, inputting a data set of equipment performance status in any task scenario of the equipment into an initialized DP-GRUC model to fit a historical health indicator HI trajectory gradient and a future health indicator HI trajectory gradient includes: dividing the data set of equipment performance status in any task scenario of the equipment into a plurality of time window HI trajectories by a sliding window cutting method, and setting the first half of the data in the sliding window as the historical HI trajectory, and setting the second half as the corresponding future HI trajectory; calculating the historical HI trajectory gradient and the future HI trajectory gradient based on the historical HI trajectory and the future HI trajectory respectively; based on the historical HI trajectory gradient and the future HI trajectory gradient, inputting the historical HI trajectory gradient into a historical encoder for historical coding update, and outputting the historical HI trajectory coding; at the same time, inputting the future HI trajectory gradient into a future encoder for future coding update, and outputting the future HI trajectory coding; combining the output historical HI trajectory coding and the future HI trajectory coding into a degradation feature association key value.

[0028] In the embodiment of the present invention, respectively calculating the historical HI trajectory gradient and the future HI trajectory gradient based on the historical HI trajectory and the future HI trajectory includes:

[0029]

[0030] in, represents the historical HI trajectory gradient; points represent the future HI trajectory gradient; Indicates the device performance status of device i at time t; Indicates the device performance status of device i at time t-1; Indicates the current moment.

[0031] In an embodiment of the present invention, the DP-GRUC model is trained by the continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance status data set to obtain the trained DP-GRUC model, which also includes: when any task scenario triggers the update of the DP-GRUC model, the equipment performance status data set of the newly added task scenario of the task scenario and the DP-GRUC model after the training of the previous task are obtained; by inputting the equipment performance status data set of the newly added task scenario of the task scenario into the DP-GRUC model after the training of the previous task, and calculating the training loss function of the elastic weight consolidation and the current task based on the continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation; the DP-GRUC model after the training of the previous task is trained by minimizing the training loss function by the gradient descent method to obtain the DP-GRUC model after the training of the current task.

[0032] In an embodiment of the present invention, the training loss function is minimized as follows:

[0033] In the formula, represents the training loss function; represents the training loss function of task B, represents the elastic modulus; represents the model parameters, represents the optimal model parameters of model A, represents parameter weight; Represents a model function.

[0034] An embodiment of the present invention also provides a continuous learning performance degradation prediction device based on stability-plasticity balance, including: an acquisition module, used to acquire in real time a device performance status data set dynamically updated under different operation task scenarios according to the device operation task scenario; a construction and training module, used to construct a performance degradation prediction DP-GRUC model based on a convolutional gated network, and train the DP-GRUC model through a continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the device performance status data set to obtain a trained DP-GRUC model; a prediction module, used to predict the performance degradation of the device under test in the target task scenario based on the trained DP-GRUC model.

[0035] An embodiment of the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the method for predicting continuous learning performance degradation based on stability-plasticity balance are implemented.

[0036] Before the continuous learning performance degradation prediction method based on stability-plasticity balance, the embodiment of the present invention also includes the steps of a performance status evaluation method based on the spatiotemporal attention mechanism, which specifically includes: using the detection data sliding window reconstruction method to convert the equipment operation monitoring performance degradation data into three-dimensional time series data; according to the relationship between the physical layout of the sensor and the equipment structure, the performance monitoring sensor is graphically expressed as a graph neural network adjacency matrix; constructing a STAGCN model based on spatiotemporal attention graph convolution, and inputting the three-dimensional time series data and the graph neural network adjacency matrix into the STAGCN model for training to obtain a trained STAGCN model; based on the trained STAGCN model, the performance status of the equipment to be evaluated is evaluated.

[0037] In an embodiment of the present invention, the STAGCN model includes a spatiotemporal attention model and an attention graph convolution model; the three-dimensional time series data includes monitoring dimension time series data, time dimension time series data and operation dimension time series data.

[0038] In an embodiment of the present invention, the three-dimensional time series data and the graph neural network adjacency matrix are input into the STAGCN model for training to obtain a trained STAGCN model, including: inputting the three-dimensional time series data into the time attention machine in the spatiotemporal attention model to calculate the time attention matrix; inputting the time attention matrix and the three-dimensional time series data into the space attention machine in the spatiotemporal attention model to calculate the space attention matrix; multiplying the space attention matrix with the graph neural network adjacency matrix to construct an attention graph convolution model, and inputting the three-dimensional time series data into the attention graph convolution model to obtain an evaluation health index of the device; calculating the loss value of the evaluation health index and the evaluation label, and based on the loss value, obtaining a trained STAGCN model.

[0039] In an embodiment of the present invention, the temporal attention matrix includes:

[0040] Where E is the temporal attention matrix, is the first r The input of the spatiotemporal network block, , , , , These are the parameters of the temporal attention matrix to be learned. is the activation function.

[0041] In an embodiment of the present invention, the spatial attention matrix includes:

[0042] in, S is the spatial attention matrix, is the first r The input of the spatiotemporal network block, , , , , These are the parameters of the spatial attention matrix to be learned. is the activation function.

[0043] In an embodiment of the present invention, according to the relationship between the physical layout of the sensor and the device structure, the performance monitoring sensor is graphically expressed as a graph neural network adjacency matrix including:

[0044] in, Indicates The monitoring parameters and The edge weights between monitoring parameters are q is the correlation coefficient of sensors at the same point, and its range is 0< q <1, m and n They represent different collection points respectively.

[0045] In an embodiment of the present invention, the sensors are sensors of various types, and one or more sensors of different types are installed at various positions of the device structure; The number of sensor acquisition channels is:

[0046] in, N Indicates the number of acquisition channels; Indicates m The number of sensors at each collection point; M Indicates the number of sensor locations.

[0047] In an embodiment of the present invention, a detection data sliding window reconstruction method is used to convert equipment operation monitoring performance degradation data into three-dimensional time series data, including: using a sliding time window with a fixed length and a fixed step size to divide the data in each start-stop working cycle in the entire life cycle from operation to failure of the training into small multidimensional time series, and stacking the multidimensional time series into three-dimensional time series data.

[0048] Aiming at the actual needs in industrial scenarios and the continuous learning goal of equipment performance degradation prediction tasks, this paper proposes a continuous learning of state prediction based on elastic weight consolidation (CLSP-EWC) method inspired by the synaptic plasticity mechanism. The method architecture is as follows: Figure 2 As shown in the figure. The method consists of a performance degradation prediction model based on a convolutional gating network and a degradation feature memory model based on elastic weight consolidation. The performance degradation prediction model fits the mapping relationship between historical and future HIs through a two-stage encoder structure. During the training and updating process, the degradation feature memory model realizes the memory and consolidation of historical task information by constraining the model learning direction, achieving a balance between the model's historical task stability and new task plasticity.

[0049] like Figure 2As shown in the figure, the performance degradation prediction model in the CLSP-EWC method is composed of two encoders, one for history and one for the future, and one feature decoder. The encoder takes the historical and future HI data of the device as input, mines the degradation features through neural network learning, and combines them to generate the key values ​​of the degradation features. The encoder takes the key values ​​of the degradation features as input, and decodes to fit the mapping relationship between the historical and future degradation features. During the retraining process of the task update model, the degradation feature memory model in the CLSP-EWC method flexibly limits the iteration intensity of each neuron by identifying the contribution of each neuron in the model to the historical tasks. The gradient fitting direction of the model is converged in the superposition space of the historical tasks and the newly added tasks. Through the combination of the performance degradation prediction model and the degradation feature memory model, continuous learning performance degradation prediction in the scenarios of newly added tasks for different data sets is realized.

[0050] 1.1 Continuous learning performance degradation prediction process based on elastic weight consolidation Based on the CLSP-EWC method designed by the present invention, combined with the characteristics of equipment performance degradation, such as Figure 3 As shown, the present invention specifically designs an elastic weight consolidation continuous learning process for performance degradation prediction tasks. A performance degradation prediction task trigger mechanism is designed for four scenarios: new monitoring data, new operating conditions, new equipment individuals, and new equipment models in actual industrial equipment. At the same time, in view of the evolution characteristics of equipment performance degradation, a performance degradation prediction model based on a convolutional gated network (Degradation Prediction based on GRU withConvolutional, DP-GRUC) is specifically designed. Based on the DP-GRUC model structure, a dynamic update method for the elastic weight consolidation degradation feature memory model is designed. Finally, based on the general evaluation index of continuous learning for classification tasks, the present invention combines the characteristics of performance degradation trend prediction tasks to specifically design a continuous learning performance degradation prediction evaluation index to evaluate the ability of the CLSP-EWC method designed by the present invention to overcome catastrophic forgetting, that is, the continuous learning level.

[0051] (11) Classification of task scenario attributes In the process of the equipment being put into actual use, performance degradation prediction is usually a non-real-time task in the health management link. That is, it is usually triggered under fixed requirements such as abnormal monitoring data and regular maintenance. Therefore, the present invention is oriented to the equipment operation scenarios in actual industrial applications, and designs a corresponding prediction task update trigger mechanism. At the same time, differentiated elasticity coefficients are set according to the differences in performance degradation characteristics in different scenarios to adapt to the task differences between different task updates.

[0052] 111) Time series expansion task In the industrial field, the use time of equipment is usually long. Most industrial equipment has been in use for several years or decades. During the operation of the equipment, the performance status HI data continues to grow. During the use of the equipment after it is put into operation, due to the wear of components and other conditions, a certain subsystem of the equipment has a specific failure mode, and the health status of the equipment may transition to a certain type of abnormal state. Therefore, the present invention is designed to set a quantitative performance degradation prediction threshold based on the performance status HI data. When the equipment HI is lower than a certain threshold, a prediction model update is triggered.

[0053] 112) Tasks for capacity expansion in the working condition area During the actual operation of the equipment, the operating conditions of the equipment will change due to the influence of the environment and usage scenarios. Since different operating conditions have very different damage to the equipment subsystems, the operating conditions will greatly affect the performance degradation characteristics of the equipment. Based on this scenario, the equipment operating conditions are identified and judged by monitoring the equipment operating environment and operating condition parameters. When the equipment enters a new operating condition, a prediction model update is triggered.

[0054] 113) Unit quantity expansion task Due to individual differences such as factory manufacturing errors, the equipment is affected by differential degradation factors during the performance degradation process, and different equipment units have different individual performance degradation characteristics. Therefore, in the group equipment operation scenario, when a new unit appears in the group and is put into operation and generates certain performance status HI data, a prediction model update is triggered.

[0055] 114) Degenerate feature expansion task In the industrial field, the same type of equipment is usually designed, developed and produced in a certain cycle. In most industries, it is common for new and old models of equipment to be in service at the same time. Due to differences in the structure, formula and other design of the equipment, the performance degradation characteristics of the equipment will also be different. Therefore, when a new model of equipment is put into operation in a group equipment service scenario, after the new model of equipment is running and generates certain performance status HI data, a prediction model update is triggered.

[0056] (12) Prediction model construction and degradation feature memory According to the actual equipment operation scenario conditions, the performance degradation prediction task update trigger mechanism mentioned above is used to build the equipment performance degradation prediction model based on the DP-GRUC model structure, and the elastic weight consolidation feature memory method for the performance degradation prediction task is used to train and update the model parameters. The specific training process is shown in Table 1. The CLSP-EWC method is used to iterate the DP-GRUC model in the time series dimension, update the model weights, and output the corresponding prediction model at different times. PT .

[0057] Table 1

[0058] (13) Continuous learning evaluation indicators for performance degradation prediction tasks Since the widespread and successful application of continuous learning methods is mainly concentrated in classification tasks, in order to evaluate the ability of the CLSP-EWC method proposed in this invention to overcome catastrophic forgetting of tasks, this invention refers to the evaluation indicators that are widely used in the field of continuous learning, and improves them according to the characteristics of performance degradation prediction tasks, and designs evaluation indicators for continuous learning methods for performance degradation prediction tasks. In the process of continuous learning evaluation for classification tasks, the indicator calculation is mainly based on the task accuracy matrix, whose structure is as follows: Figure 4 As shown. According to the order in which the tasks appear, the accuracy of the model for each task after each task training is arranged in order to form the task accuracy matrix. Indicates i After the task data is trained, the model j The accuracy in each task.

[0059] 1.2 Performance Degradation Prediction Model Based on Convolutional Gated Network Equipment performance degradation is a continuous dynamic time series process, which starts from the time of commissioning until the failure occurs and reaches the end of life. The HI trajectory during this period represents the entire process of equipment performance change, and the length of the HI trajectory represents the length of the equipment's operating life. During the entire life cycle of equipment operation, the performance degradation process has the following two characteristics: (21) Continuity of degradation process: The performance change caused by a certain start-stop cycle of the equipment is based on the performance state after the previous working cycle. That is, the performance degradation process is a process of progressive evolution in time. The change of equipment performance state is not only related to the equipment operating conditions and individual equipment conditions, but also to the operating cycle time of the equipment.

[0060] (22) Differences in degradation characteristics: For equipment of the same model and batch, the degradation characteristics of the equipment have certain differences due to differences in initial manufacturing and assembly errors and differences in operating environment, working conditions and other conditions. That is, in the same equipment performance degradation feature space, different individuals still have personalized differences. Therefore, equipment performance degradation prediction needs to mine common degradation characteristics based on historical data, and output prediction results in combination with personalized degradation characteristics of the equipment to be predicted.

[0061] Predicting equipment performance degradation can determine the performance status of the equipment in the future working process in advance, providing strong support for operation decision-making. Based on dynamically updated equipment performance status data set , Aiming at the two characteristics of the equipment performance degradation evolution process, the DP-GRUC model consists of a history encoder module, a future encoder module and a HI trajectory decoder module. The model architecture is as follows Figure 5 shown.

[0062] Based on the continuity of the equipment degradation process, the present invention designs an HI trajectory encoder based on convolutional neural network and gated neural network, and extracts equipment degradation features by fitting the HI trajectory gradient. and Data, define the HI trajectory gradient as follows: (1.0)

[0063] (1.1)

[0064] and The HI trajectory gradients of equipment performance degradation in the past and future are characterized respectively, which characterize the relative performance degradation change of the equipment before and after a start-stop cycle. and , the calculation process of historical degradation feature coding and future degradation feature coding is as follows: (1.2) (1.3) In the formula, and Represents the historical and future degradation feature encoders respectively and Learnable parameters of the GRU layer and the Conv1d layer of the 1D convolutional network.

[0065] Based on the encoding results, the historical and future degradation characteristics at a certain moment are is defined as a pair of degradation feature associated key values. With historical degradation gradient is fed into the encoder to generate future HI trajectories The performance degradation prediction model is trained through the historical data of different equipment operations, the key-value mapping relationship of degradation features is learned based on the encoder model, and the future degradation gradient is generated based on the decoder's comprehensive HI trajectory information of the device to be predicted. The performance state value of the device at the future moment is deduced from the current performance state to achieve device performance degradation prediction.

[0066] 1.3 Degraded feature memory model based on elastic weight consolidation The DP-GRUC model can be used to predict device performance degradation. However, the fitting results of the model in a single training process converge to the training data set D M With the continuous operation of equipment and the update of industrial needs, a new dataset D M+1 With the increase of , there is a task conflict between the consolidation of historical capabilities learned in the model and the update of the newly added data set. This problem is called the "stability-plasticity" balance in biological neuroscience. In response to repeated external stimulation, the connection morphology between neuronal synapses will change, and the reconnection process aims at the optimal learning cost. The task architecture of continuous learning is that after a fixed number of trainings on each task, no further training is allowed on the data set of the task. Therefore, to achieve continuous learning, it is necessary to limit the direction of the iterative gradient descent of the model weights to ensure the model's ability to complete the previous task A. Based on this goal, inspired by the biological synaptic plasticity mechanism, the present invention constructs an elastic weight consolidation feature memory model for the performance degradation prediction task. The neurons of the DP-GRUC artificial neural network influence each other through the connection weights. The core of the elastic weight consolidation is to regard the weight protection applied to the neuronal synaptic connection as a spring link, and its stiffness is proportional to the importance of the neuronal connection of the previous task. The present invention uses the complex equipment performance degradation prediction task based on the DP-GRUC model as a continuous learning task to carry out the design and research of the elastic weight consolidation method.

[0067] (131) Design of elastic weight consolidation method for DP-GRUC model The DP-GRUC model neural network consists of multiple layers of linear mapping layers and multiple types of nonlinear mapping layers. Fitting learning is a process of continuously adjusting the model weight set based on the linear mapping deviation to optimize the model prediction performance. θ represents the artificial neural network layer parameters, θ Indicates the optimal parameter configuration for the task. θ During the configuration process, the same performance effect can match multiple configuration combinations. This theory is the basis for the consolidation of elastic weights. The present invention develops a method design based on this. Due to over-parameterization, the solution configuration of the subsequent task B There is a high probability that the solution configuration is the same as the previous task A Therefore, if Figure 7 As shown in Figure 2, when learning the subsequent task B, EWC constrains the parameters to The performance of task A is protected by keeping the task in the low error region of task A centered on . This constraint is implemented by the quadratic penalty method, so the reset of neuron weights can be defined as the process of a rigid spring anchoring the weight parameters to the configuration region of the previous task. The spring stiffness varies between parameters. For parameters that are important to the performance in the previous task A, the stiffness is greater, and vice versa.

[0068] Different retraining model parameter change paths are as follows Figure 6 As shown, after the model learns the previous task A, the parameters are located in the space , if the model training gradient is adjusted only according to the effect of task B, the parameter path will be as shown by the red line. The model maximizes the learning ability of task B, but destroys the knowledge learned in task A, causing knowledge forgetting. If the model iteration process is constrained by task A, as shown by the green line in the figure, due to the overly strict restrictions, the model's ability to learn task B is seriously insufficient. Therefore, by calculating the importance of different model weights to task A, determining the direction of the parameter gradient change path, and finding the gradient path for task B in the low-loss space of parameter A, it is possible to achieve effective learning of task B while retaining the ability of task A.

[0069] In order to demonstrate the rationality of the retraining constraints of the deep neural network model and determine the importance of different neuron weights to the task, the model training process is optimized by probability, that is, for a given data set Determine the optimal importance under the condition of Calculating conditional probabilities , based on Bayes' rule: (1.4) Since the objective function to be maximized is the same as the logarithm, the calculation The logarithmic process is as follows: (1.5) In the formula, Given a data set The probability logarithm of . During the network model training process, is the objective function to be optimized on the log-likelihood function: (1.6) Assume that the dataset corresponding to the task is divided into two independent parts, and task A and task B are defined as and , so rearrange the formula to: (1.7) In the formula, the left side of the equation still describes the given data set The parameter posterior probability of the equation only depends on the loss function of the subsequent task B. Therefore, the posterior distribution on the right side of the equation is It must contain the knowledge information of the previous task A. This knowledge information includes the importance of model parameters to task A, which is the key attribute to realize EWC.

[0070] (132) Approximate solution of the posterior distribution of the previous task In formula (1.7), is the posterior probability distribution of the previous task A, which contains the parameter information of the network model fitting task A. However, since it cannot be expressed in an interpretable display form, it is very difficult to calculate the posterior probability that fully conforms to the actual data. Therefore, consider calculating its approximate value through the Karplus method.

[0071] First, exist Secondary Taylor expansion (1.8)

[0072] because is the peak value, the tangent slope , formula (1.8) can be written as: (1.9) Based on formula (1.6), formula (1.9) can be written as: (2.0) in, .Will Written as , formula (2.0) can be expressed as the standard expression of normal distribution: (2.1)

[0073] Thus, the posterior probability distribution of the previous task A can be obtained as: (2.2) That is, Figure 7 As shown, the normal distribution approximation of the continuous probability density distribution is found based on the Laplace approximation method. Assume is a smooth probability distribution, and the peak is located at the maximum point ( ), the average value can be used With variance Normal distribution fitting of .

[0074] (133) Fisher information matrix parameter importance calculation like Figure 7As shown, the Laplace approximation method can be used to The approximate fit is a normal distribution, and the mean of the normal distribution is , the variance of the normal distribution is Since the Fisher information matrix can be calculated by the first-order derivative. This property can be used to avoid calculating the Hessian matrix in formula (1.9).

[0075] (2.3)

[0076] Substituting formula (2.0) into formula (1.7), we have: (2.4)

[0077] In the formula, represents all constant terms, It is a hyperparameter introduced to weigh the ability of the network model to learn task B and remember the previous task A.

[0078] Substituting formula (2.3) into the equation, we have: (2.5) Therefore, the network model elastic weight consolidation training can be expressed as formula (2.5). Where the Fisher information matrix It contains the importance information of model parameters to task A. There are three key properties: Equivalent to the second-order derivative when the loss is close to the minimum; It can be calculated only from the first-order derivative, so the calculation process is relatively simple; is a positive semidefinite matrix.

[0079] The Laplace calculation is similar to the expectation propagation process, where each subtask is regarded as a posterior factor, so the loss function minimized by EWC is: (2.6) In the formula, is the training loss function for task B, The elasticity coefficient is configured with the relative importance of task B and the previous task A, and Relative importance marking is performed on each parameter, thereby realizing EWC model training.

[0080] When the model performs the third task C, EWC uses the sum of the two penalty terms of task A and task B as the secondary penalty term to bring the network parameters close to the common parameter area. Similarly, for future prediction tasks, the historical task penalty term is used to maintain the model's ability to remember historical tasks, thereby achieving continuous learning of the DP-GRUC model.

[0081] Specifically, the present invention includes a method for quantitatively characterizing the HI (Health Index) of a performance status evaluation method before the continuous learning performance degradation prediction method based on the stability-plasticity balance. In this context, the system is located in a complex equipment system state monitoring network. G In total N Monitoring points, the monitoring point records are ; Record at each work start-stop cycle monitoring point of the equipment L measurements, .by Indicated in t Moment, n Among the status monitoring points, l Condition monitoring measurement value. Indicated in t Moment, n All status monitoring measurements of nodes; express t All status monitoring measurements at all times; express All state monitoring measurement values ​​in the time series. Based on the above assumptions, the objective function of equipment state monitoring is ,in, ,by Characterization t Quantitative value of the device performance status at a moment.

[0082] In view of the above problem description and model fitting goals, combined with the engineering characteristics of equipment operation and data collection in the performance status evaluation process, the present invention proposes a performance status evaluation method based on Spatial-TemporalAttention based on Graph Convolutional Networks (STAGCN). Firstly, in the data preprocessing process, a three-dimensional sliding window reconstruction method of monitoring data is designed according to the characteristics of the differences in the duration of a single start-stop cycle of the equipment, and the equipment operation monitoring data is converted into training and test data for the performance status evaluation model; secondly, a graphical expression method of performance monitoring sensors is designed according to the relationship between the physical layout of equipment sensors and the equipment structure, and the physical structure design information of the equipment is input into the STAGCN model through the graph neural network adjacency matrix; on this basis, the STAGCN model is trained based on the input data and the adjacency matrix to output the performance status evaluation results.

[0083] In the process of engineering application, due to the differences in frequency, physical dimensions, sampling quality, etc. between different sensors, equipment operation monitoring data cannot usually be directly used for data-driven performance status evaluation. Therefore, it is necessary to preprocess the data first, and the processed data is used as the input of the performance status evaluation model.

[0084] Since most equipment has different start-up and shutdown time, t Monitoring data collected at all times X t The corresponding length L In order to solve this problem, the present invention designs a sliding window reconstruction method for monitoring data based on the two conventional preprocessing methods of resampling and normalization, aiming at the characteristics of equipment performance status evaluation. Win , a sliding time window with a step size of 1, splits the data of each startup and shutdown cycle in the training life cycle from operation to failure into small multidimensional time series, and stacks them into three-dimensional time series data to ensure that the data contained in each sliding window is dimensionally regular input data, that is, X t Convert to In addition, the corresponding health status of each sliding window data is used as the evaluation label. The original working cycle data of different lengths are converted into a regular three-dimensional data structure through the data sliding window reconstruction method, which provides standardized data input for the performance status evaluation model.

[0085] The operation monitoring sensors of complex system equipment are installed in different positions of the equipment structure. Some positions may be equipped with one or more sensors of different types. GIn the example, the number of sensor locations is M ,but:

[0086] in, M m For the m The number of sensors at each collection point, N is the number of acquisition channels. The sensors are numbered according to the physical layout. The data collected at the same sampling point have a certain correlation. Therefore, the performance monitoring sensor is graphically expressed as an adjacency matrix as shown in the formula:

[0087] in, w i,j Indicates i The monitoring parameters and j The edge weights between monitoring parameters are q is the correlation coefficient of sensors at the same point, and its range is 0< q <1, m and n They represent different collection points respectively.

[0088] The spatiotemporal attention graph convolution model is the core of the equipment performance status evaluation method proposed in this invention. It identifies the performance degradation information of the time dimension and space dimension in the equipment status monitoring data step by step through the stacked model structure, and fits the equipment performance status degradation characteristics through the graph neural network. The degradation characteristics are fit into a one-dimensional vector based on the feature decoder, and finally realizes the conversion of a large amount of performance status information covered in the monitoring data into a quantitative health indicator HI.

[0089] The specific structure of the STAGCN model consists of two parts: the spatiotemporal attention model and the attention graph convolution model. The spatiotemporal attention model takes the multi-dimensional monitoring parameters of the equipment as input, outputs the temporal attention matrix through the temporal attention machine, and passes the degradation feature density information of the time dimension to the spatial attention machine. The high-dimensional input data is transformed into a multi-dimensional matrix through the spatial attention machine, and the spatial attention matrix is ​​output to characterize the difference in degradation information density between different monitoring parameters. The attention graph convolution model converts the physical position of the sensor of the device to be evaluated into a graph convolution network adjacency matrix through graphical expression, introduces the layout information of the device status monitoring sensor through the adjacency matrix in the graph neural network, and combines the adjacency matrix with the spatial attention matrix to mine the degradation characteristics of the device performance status through graph convolution coding. Finally, based on the performance status degradation characteristics, the degradation characteristics are fitted into the health index HI through a linear decoder. In order to achieve quantitative characterization of the performance status of the equipment.

[0090] The equipment performance degradation assessment model is constructed based on the model structure, and the model is trained using training data. The algorithm process is shown in Table 2.

[0091] Table 2

[0092]

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be used to modify the technical solutions or to perform equivalent replacements on some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting continuous learning performance degradation based on stability-plasticity balance, characterized in that: include: According to the equipment operation task scenarios, the equipment performance status data set dynamically updated in different operation task scenarios is obtained in real time; Constructing a performance degradation prediction DP-GRUC model based on a convolutional gated network, and training the DP-GRUC model through a continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance status data set to obtain a trained DP-GRUC model; Based on the trained DP-GRUC model, performance degradation prediction is performed on the device under test in the target task scenario.

2. The method according to claim 1, characterized in that The DP-GRUC model consists of a history encoder module, a future encoder module and a HI trajectory decoder module.

3. The method according to claim 1 or 2, characterized in that: The equipment operation task scenario includes any of the following: new monitoring data, new operating conditions, new equipment individuals and new equipment models.

4. The method according to claim 3, characterized in that The DP-GRUC model is trained by using the CLSP-EWC method for continuous learning performance degradation prediction based on elastic weight consolidation and the equipment performance status data set, and the trained DP-GRUC model includes: Initialize the DP-GRUC model by randomly initializing the model weights; The equipment performance status data set under any task scenario of the equipment is input into the initialized DP-GRUC model to fit the historical health index HI trajectory and the future health index HI trajectory, and the DP-GRUC model after the first training under the task scenario is obtained and saved.

5. The method according to claim 4, characterized in that Input the equipment performance status data set under any task scenario of the equipment into the initialized DP-GRUC model to fit the historical health index HI trajectory gradient and the future health index HI trajectory gradient, including: The equipment performance status data set in any task scenario of the equipment is divided into several time window HI trajectories by sliding window cutting method, and the first half of the data in the sliding window is set as the historical HI trajectory, and the second half is set as its corresponding future HI trajectory; Calculate the historical HI trajectory gradient and the future HI trajectory gradient respectively based on the historical HI trajectory and the future HI trajectory; Based on the historical HI trajectory gradient and the future HI trajectory gradient, the historical HI trajectory gradient is input into the historical encoder for historical coding update, and the historical HI trajectory code is output; at the same time, the future HI trajectory gradient is input into the future encoder for future coding update, and the future HI trajectory code is output; The output historical HI trajectory encoding and future HI trajectory encoding are combined into a degradation feature association key value.

6. The method according to claim 5, characterized in that Calculating the historical HI trajectory gradient and the future HI trajectory gradient based on the historical HI trajectory and the future HI trajectory respectively includes: ； ； in, represents the historical HI trajectory gradient; points represent the future HI trajectory gradient; Indicates the device performance status of device i at time t; Indicates the device performance status of device i at time t-1; Indicates the current moment.

7. The method according to claim 5, characterized in that The DP-GRUC model is trained by the continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance status data set, and the trained DP-GRUC model also includes: When any task scenario triggers the DP-GRUC model update, the equipment performance status data set of the newly added task scenario and the DP-GRUC model trained by the previous task are obtained; By inputting the equipment performance status data set of the newly added task scenario of the task scenario into the DP-GRUC model after the previous task training, and calculating the training loss function of the elastic weight consolidation and the current task based on the continuous learning performance degradation prediction CLSP-EWC method of elastic weight consolidation; The DP-GRUC model trained for the previous task is trained by minimizing the training loss function through the gradient descent method to obtain the DP-GRUC model trained for the current task.

8. The method according to claim 7, characterized in that The training loss function is minimized as: ； In the formula, represents the training loss function; represents the training loss function of task B, represents the elastic modulus; represents the model parameters, represents the optimal model parameters of model A, represents parameter weight; Represents a model function.

9. A continuous learning performance degradation prediction device based on stability-plasticity balance, characterized in that: include: An acquisition module is used to acquire, in real time, a dynamically updated device performance status data set of the device under different operation task scenarios according to the device operation task scenarios; A construction and training module is used to construct a performance degradation prediction DP-GRUC model based on a convolutional gated network, and train the DP-GRUC model through a continuous learning performance degradation prediction CLSP-EWC method based on elastic weight consolidation and the equipment performance status data set to obtain a trained DP-GRUC model; The prediction module is used to predict the performance degradation of the device under test in the target task scenario based on the trained DP-GRUC model.

10. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the method for predicting continuous learning performance degradation based on stability-plasticity balance described in any one of claims 1 to 8 are implemented.

Images