Method for predicting residual service life of rotating machine based on GBIT-GAN

Abstract

The invention provides a GBIT-GAN-based method for predicting the remaining service life of a rotating machine. According to the method, a graph neural network GNN and a bidirectional Transform generative adversarial network BIT-GAN are combined, structural information of the rotating machinery can be fully utilized to construct a graph structure, and a GNN layer can accurately capture a topological relation between components. The bidirectional Transform is excellent in performance when the time sequence data is processed, the long-term dependency relationship in the data can be well mined, and the accuracy and reliability of the model are further improved through the adversarial training mechanism of the generator and the discriminator. The method has significant advantages in the aspect of prediction of the residual service life of the rotating machine, can provide a more accurate and reliable decision basis for maintenance and management of the rotating machine in industrial production, greatly reduces the equipment failure risk, and has important significance in improvement of industrial production efficiency and economic benefits.

Description

Technical Field

[0001] The present invention belongs to the technical field of rotating machinery state monitoring and life prediction, and in particular relates to a method for predicting the remaining service life of rotating machinery based on GBIT-GAN. Background Art

[0002] In industrial production, the stable operation of rotating machinery such as bearings and aircraft engines is crucial. Take bearings as an example. In the production line of automobile manufacturing, a large number of bearings are used in various mechanical transmission devices. Once a bearing fails, the mechanical equipment on the production line will not operate smoothly, and the entire production process will be forced to be interrupted. This not only means that the parts being processed may be scrapped, resulting in direct material losses, but also greatly reduces production efficiency, delays product delivery time, and triggers a series of chain reactions, such as economic losses such as order breach compensation. Aircraft engines are the key power source for low-altitude flight operations. Taking low-altitude mapping and geographic exploration as an example, professional mapping aircraft are equipped with high-precision mapping instruments and rely on the stable operation of aircraft engines to collect data over a large area at low altitudes. If the engine fails during flight, not only will the ongoing mapping and exploration tasks be interrupted, resulting in a complete waste of manpower, material resources and time invested in the early stage, but the incomplete data obtained may affect the construction and analysis of subsequent geographic information systems, hindering the smooth progress of projects such as urban planning and resource exploration. In addition, in some scientific research projects, such as long-term low-altitude monitoring of the ecological environment of a specific area, engine failure may cause the loss of data during critical periods, affecting the accuracy and reliability of scientific research results, and thus delaying research progress in related fields.

[0003] The purpose of predicting the remaining service life of rotating machinery is to know the health status of the equipment in advance so as to arrange maintenance and replacement plans reasonably. Its significance lies in that it can effectively avoid production stagnation, safety accidents and economic losses caused by sudden equipment failure, ensure the continuity and stability of industrial production, improve production efficiency, reduce operating costs, ensure personnel safety and sustainable development of enterprises. Through accurate prediction, enterprises can take timely measures before the equipment is about to fail, such as stockpiling parts in advance, arranging professional maintenance personnel, etc., to minimize the impact of equipment failure.

[0004] In the field of remaining useful life prediction of rotating machinery, early deep learning models were relatively simple, such as the multi-layer perceptron (MLP). MLP consists of an input layer, a hidden layer, and an output layer, and processes and transforms the input data through the connection weights between neurons. However, it has obvious defects when processing rotating machinery data. Due to its structural limitations, it is difficult to capture the time series characteristics and spatial structure information in the data. When faced with complex operating state changes of rotating machinery, it is unable to effectively mine potential dependencies from long-term time series data, and the use of equipment structure information is almost zero.

[0005] With the development of technology, although some more complex models have emerged, the existing models are still insufficient in dealing with the prediction problems of rotating machinery. For example, recurrent neural networks (RNNs) and their variants, although they can process time series data to a certain extent, have the problem of gradient disappearance or gradient explosion, which makes the capture of long-term dependencies not ideal. Summary of the invention

[0006] The purpose of the present invention is to solve the problems existing in the prior art, such as insufficient extraction of rotating machinery data features, insufficient model generalization ability, and inability to effectively utilize component topological relationships, so as to achieve more accurate and reliable prediction of the remaining service life of rotating machinery. A method for predicting the remaining service life of rotating machinery based on GBIT-GAN is proposed.

[0007] The present invention is implemented by the following technical solutions. The present invention proposes a method for predicting the remaining service life of rotating machinery based on GBIT-GAN. The method is specifically as follows:

[0008] Data collection and preprocessing: Utilize acceleration, temperature and pressure sensors installed on rotating machinery to collect multi-channel vibration, temperature and pressure data, which covers the entire process from normal to failure of the equipment; remove outliers and noise through filtering, normalize the data to make it in the [0,1] interval, and then segment the data according to specific time windows and mark the remaining service life labels;

[0009] Constructing GBIT-GAN model: The generator is built based on bidirectional Transformer. The encoder and decoder of Transformer are composed of multiple Transformer layers. Each Transformer layer contains a multi-head self-attention mechanism, a feedforward neural network, a residual connection, and layer normalization. The generator can effectively extract data features, input historical data and equipment information, output prediction values, and optimize through adversarial and reconstruction losses. The discriminator uses a structure that processes sequence data to distinguish the authenticity of data. The GNN layer is introduced after the bidirectional Transformer encoder of the generator to capture the topological relationship and information propagation between rotating machinery components. The output of the GNN layer is concatenated or weighted summed with the output of the bidirectional Transformer encoder for information fusion, and then the fused features are input into the decoder of the bidirectional Transformer to generate predicted future sensor data sequences and remaining service life prediction values.

[0010] Model training: divide the training data set and use the training data set to iteratively train the GBIT-GAN model;

[0011] Prediction of the remaining service life of rotating machinery: The newly collected data is preprocessed and input into the trained GBIT-GAN model. The prediction result is compared with the preset threshold. If the predicted remaining service life is lower than the threshold, an early warning signal is issued to prompt maintenance personnel to inspect and maintain the rotating machinery to avoid failures.

[0012] Furthermore, the preprocessed data is segmented according to a certain time window to form multiple data samples; each data sample contains multi-channel sensor data within a period of time and the corresponding remaining service life label; the size of the time window is selected according to the operating characteristics of the rotating machinery and the sampling frequency of the data, and the remaining service life label y i The calculation is based on the actual operating time and failure time of the rotating machinery.

[0013] Furthermore, in the Transformer layer, for the input sequence X = [x1, x2, ..., x n ], where x i It is the i-th element in the sequence, i.e., the preprocessed data sample. The input is mapped into query Q, key K, and value V through linear transformation, i.e., Q = XW Q ,K=XW K ,V=XW V , where W Q ,W K ,W V is a learnable weight matrix; then calculate the attention weight where d kis the dimension of the key, and the softmax function is used to normalize the attention weights to [0,1] so that the sum of the weights is 1; finally, the output of the multi-head self-attention is MultiHead(X)=Concat(head1,head2,…,head h ,)W O , where head i =Attention(QW i Q ,KW i K ,VW i V ), h is the number of heads, W i Q ,W i K ,W i V and W O It is a learnable parameter matrix; the output of the multi-head self-attention is further transformed through a feedforward neural network. The feedforward neural network consists of two fully connected layers with a ReLU activation function in the middle. The formula is FFN(x)=ReLU(xW1+b1)W2+b2, where W1, W2 are weight matrices, and b1, b2 are bias vectors.

[0014] Furthermore, the input of the generator includes historical sensor data sequences and basic information of rotating machinery. These basic information are converted into vector representation through the embedding layer, and then concatenated with the historical sensor data sequence and input into the encoder of the bidirectional Transformer; the output of the generator is the predicted sensor data sequence of n time windows in the future and the corresponding remaining service life prediction value.

[0015] Furthermore, adversarial loss: The goal of the generator is to make the discriminator unable to distinguish between the generated sequence and the real sequence. The adversarial loss of the generator is expressed as where p g is the data distribution generated by the generator, and D(x) is the discriminator's judgment result on the input x;

[0016] Reconstruction loss: Using mean square error MSE as reconstruction loss, then where p data is the real data distribution, x is the real sequence, is the sequence generated by the generator;

[0017] Total loss: The total loss of the generator is the weighted sum of the adversarial loss and the reconstruction loss, i.e. Where α is a weight parameter used to balance the importance of adversarial loss and reconstruction loss.

[0018] Furthermore, the loss function in the discriminator is: The goal of the discriminator is to accurately distinguish between real sequences and generated sequences, and its loss function is expressed as

[0019] Furthermore, the GNN layer adopts the graph convolutional network GCN. For node i, its feature update formula at the l+1th layer is: in is the feature vector of node i in layer l, is the feature vector of node j in layer l, N(i) is the set of neighbor nodes of node i, c ij is the normalization constant, W l is the learnable weight matrix of layer l, b l is the bias vector, σ is the activation function; by stacking multiple GNN layers, the features of the nodes can be continuously updated, thereby fusing the topological information and sensor data information between components.

[0020] Furthermore, in each training iteration, the discriminator parameters are first fixed, and a batch of data is sampled from the training set and input into the generator to generate a batch of predicted future sensor data sequences and remaining service life prediction values; the generated sequences and the real sequences are input into the discriminator, and the loss of the generator and the loss of the discriminator are calculated; the gradients of the parameters of the generator, discriminator and GNN layer are calculated respectively using the back-propagation algorithm, and the model parameters are updated according to the gradients to minimize the loss of the generator and maximize the loss of the discriminator; after each training cycle, the model is evaluated using the validation set, and the loss function value on the validation set and the error index between the predicted remaining service life and the actual remaining service life are calculated; according to the evaluation results of the validation set, the hyperparameters of the model are adjusted, and if the performance on the validation set no longer improves, the training can be stopped early to prevent overfitting.

[0021] The present invention also proposes an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for predicting the remaining useful life of rotating machinery based on GBIT-GAN are implemented.

[0022] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of a method for predicting the remaining useful life of rotating machinery based on GBIT-GAN.

[0023] Beneficial effects of the present invention:

[0024] (1) By combining the bidirectional Transformer and GNN layers, the present invention can fully extract the time series features in the rotating machinery sensor data and the topological relationship features between components, improve the model's data representation and feature extraction capabilities, and thus more accurately predict the remaining service life of the rotating machinery;

[0025] (2) The adversarial training mechanism in the improved BITGAN model, namely the GBIT-GAN model, enables the generator to generate more realistic future sensor data sequences, which helps to capture the potential distribution and change trend of the data, further improving the accuracy and reliability of the remaining useful life prediction;

[0026] (3) The present invention can monitor the operating status of rotating machinery in real time and issue early warnings in a timely manner, providing strong support for equipment maintenance and management, helping to reduce losses caused by equipment failures and improving production efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0028] Figure 1 This is the network architecture diagram of GBIT-GAN.

[0029] Figure 2 Schematic diagram of the GNN graph structure.

[0030] Figure 3 Schematic diagram of the Bi-Transformer structure. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Combination Figure 1-Figure 3 The present invention proposes a method for predicting the remaining service life of rotating machinery based on GBIT-GAN, and the method is specifically as follows:

[0033] Data collection and preprocessing: Use acceleration, temperature and pressure sensors installed on rotating machinery to collect multi-channel vibration, temperature and pressure data. The collected data should include a sufficiently long time series to cover the entire process of rotating machinery from normal operation to failure. Remove outliers and noise through filtering, and then normalize the data to make it in the [0,1] interval. Then, split the data according to a specific time window and mark the remaining service life label.

[0034] Data preprocessing:

[0035] Data cleaning: Remove outliers and noise from the collected data, such as using mean filtering, median filtering and other methods to smooth the vibration signal and remove abnormal data points caused by sensor failure or environmental interference.

[0036] Data normalization: Normalize the data collected by different sensors so that their value range is between [0,1] to facilitate model training and processing. Common normalization methods include minimum-maximum normalization, and the formula is: norm =(xx min ) / (x max -x min ), where x is the original data, x min and x max are the minimum and maximum values ​​in the data sequence, respectively, norm is the normalized data.

[0037] Data segmentation: The preprocessed data is segmented according to a certain time window to form multiple data samples; each data sample contains multi-channel sensor data within a period of time and the corresponding remaining service life label; the size of the time window is selected according to the operating characteristics of the rotating machinery and the sampling frequency of the data. For example, the window size can be selected as W and the step size can be selected as S, then the i-th data sample can be expressed as X i =[x i,1 ,x i,2 ,…,x i,W ], where X i Indicates the xth i,j The sensor data vector of the i-th time step in samples, j = 1, 2, ..., W. The remaining useful life label y i The calculation is based on the actual operating time and failure time of the rotating machinery. For example, if the rotating machinery fails after the operating time T, and the time range corresponding to the current data sample is from t1 to t2, then the remaining service life label y of the sample i =T-(t2-t1).

[0038] Constructing GBIT-GAN model: The generator is constructed based on the bidirectional Transformer. The encoder and decoder of the Transformer are composed of multiple Transformer layers. Each Transformer layer contains a multi-head self-attention mechanism, a feed-forward neural network, a residual connection, and layer normalization. The generator can effectively extract data features, input historical data and equipment information, output prediction values, and optimize through adversarial and reconstruction losses. The discriminator uses a structure that processes sequence data to distinguish the authenticity of data. The GNN layer is introduced after the bidirectional Transformer encoder of the generator to capture the topological relationship and information propagation between rotating machinery components. The output of the GNN layer is concatenated or weighted summed with the output of the bidirectional Transformer encoder to perform information fusion, and then the fused features are input into the decoder of the bidirectional Transformer to generate predicted future sensor data sequences and remaining service life prediction values.

[0039] In the Transformer layer, for the input sequence X = [x1, x2, ..., x n ], where x i It is the i-th element in the sequence, i.e., the preprocessed data sample. The input is mapped into query Q, key K, and value V through linear transformation, i.e., Q = XW Q ,K=XW K ,V=XW V , where W Q ,W K ,W V is a learnable weight matrix; then calculate the attention weight where d k is the dimension of the key, and the softmax function is used to normalize the attention weights to [0,1] so that the sum of the weights is 1; finally, the output of the multi-head self-attention is MultiHead(X)=Concat(head1,head2,…,head h ,)W O , where head i =Attention(QW i Q ,KW i K ,VW i V ), h is the number of heads, W iQ ,W i K ,W i V and W O is a learnable parameter matrix; the output of the multi-head self-attention is further transformed by the feedforward neural network, which consists of two fully connected layers, with the ReLU activation function in the middle, and the formula is FFN(x)=ReLU(xW1+b1)W2+b2, where W1, W2 are weight matrices, and b1, b2 are bias vectors. In order to avoid the problem of gradient disappearance and explosion, residual connection and layer normalization are used in each Transformer layer, namely LayerNorm(x+Sublayer(x)), where Sublayer(x) represents the output of the multi-head self-attention or feedforward neural network, and LayerNorm represents the layer normalization operation. The input of the generator includes the historical sensor data sequence (such as the data of the past time windows) and the basic information of the rotating machinery (such as model, speed, load, etc.), which is converted into vector representation through the embedding layer, and then spliced ​​with the historical sensor data sequence and input into the encoder of the bidirectional Transformer; the output of the generator is the predicted sensor data sequence of the next n time windows and the corresponding remaining service life prediction value.

[0040] Adversarial Loss: The goal of the generator is to make the discriminator unable to distinguish between the generated sequence and the real sequence. The adversarial loss of the generator is expressed as where p g is the data distribution generated by the generator, and D(x) is the discriminator's judgment result on the input x (the probability of being true);

[0041] Reconstruction Loss: In order to make the generated sequence closer to the real sequence in some features, reconstruction loss can also be added. Using mean square error MSE as reconstruction loss, then where p data is the real data distribution, x is the real sequence, is the sequence generated by the generator;

[0042] Total loss: The total loss of the generator is the weighted sum of the adversarial loss and the reconstruction loss, i.e. Where α is a weight parameter used to balance the importance of adversarial loss and reconstruction loss.

[0043] Discriminator: The discriminator can use a convolutional neural network (CNN) or other structures suitable for processing sequence data. It receives an input sequence (real or generated) and outputs a discriminant score, which represents the probability that the input sequence is real. The network structure of the discriminator can include convolutional layers, pooling layers, fully connected layers, etc. The specific number of layers and parameters can be adjusted according to actual conditions.

[0044] The loss function in the discriminator is: The goal of the discriminator is to accurately distinguish between real sequences and generated sequences, and its loss function is expressed as

[0045] Introducing the GNN layer:

[0046] Graph construction: Build a graph based on the physical structure of the rotating machinery and the connection relationship between its components. The nodes in the constructed graph represent the various components of the rotating machinery (such as bearings, gears, shafts, etc.). The characteristics of the nodes may include information such as the type, size, material, and the corresponding sensor data of the component (such as vibration signals and temperature signals collected by sensors installed near the component). Edges represent the connection relationship between components, and the weights of the edges can be set based on factors such as the physical distance between components and the strength of the connection. For example, an adjacency matrix can be used to represent the structure of a graph, where A ij Indicates whether there is an edge connection between node i and node j. If there is an edge connection, then A ij =1, otherwise A ij =0.

[0047] GNN layer: The GNN layer is introduced after the bidirectional Transformer encoder of the generator to capture the topological relationship and information propagation between rotating mechanical parts. The GNN layer can use a graph convolutional network (GCN) or other types of GNN models. Taking GCN as an example, for node i, its feature update formula at the l+1 layer is: in is the feature vector of node i in layer l, is the feature vector of node j in layer l, N(i) is the set of neighbor nodes of node i, c ij is a normalization constant (e.g. where d i and d j are the node and the degree of the node respectively), W l is the learnable weight matrix of layer l, b l is the bias vector, σ is the activation function (such as ReLU); by stacking multiple GNN layers, the features of the nodes can be continuously updated, thereby fusing the topological information and sensor data information between components.

[0048] Information fusion: The output of the GNN layer is fused with the output of the bidirectional Transformer encoder by concatenating or weighted summing the information, and then the fused features are input into the decoder of the bidirectional Transformer to generate the predicted future sensor data sequence and the remaining service life prediction value.

[0049] Model training: training data set division, using the training data set to iteratively train the GBIT-GAN model; specifically including:

[0050] Training data set division: The preprocessed data samples are divided into training set, validation set and test set according to a certain ratio. For example, 70% of the data can be used as training set, 15% of the data as validation set, and 15% of the data as test set.

[0051] Initialize model parameters: Randomly initialize the parameters of the generator, discriminator, and GNN layers.

[0052] Iterative training: In each training iteration, first fix the discriminator parameters, sample a batch of data from the training set and input them into the generator to generate a batch of predicted future sensor data sequences and remaining service life prediction values; input the generated sequences and the real sequences into the discriminator, and calculate the generator loss and the discriminator loss; use the back-propagation algorithm to calculate the gradients of the generator, discriminator and GNN layer parameters respectively, and update the model parameters according to the gradients to minimize the generator loss and maximize the discriminator loss; after each training cycle, use the validation set to evaluate the model, calculate the loss function value on the validation set (such as the total loss of the generator, the loss of the discriminator, etc.) and the error index between the predicted remaining service life and the actual remaining service life (such as the root mean square error RMSE, the mean absolute error MAE, etc.); according to the evaluation results of the validation set, adjust the model's hyperparameters (such as the learning rate, the weight parameter α of the generator and discriminator losses, the number of layers and parameters of the GNN layer, etc.), and if the performance on the validation set no longer improves, the training can be stopped early to prevent overfitting.

[0053] Model optimization: Some optimization techniques can be used to improve the training efficiency and performance of the model, such as using learning rate decay strategy (such as gradually reducing the learning rate as training progresses), gradient clipping (to prevent gradient explosion), batch normalization (to accelerate model convergence), etc.

[0054] Prediction of the remaining service life of rotating machinery: The newly collected data is preprocessed and input into the trained GBIT-GAN model. The prediction result is compared with the preset threshold. If the predicted remaining service life is lower than the threshold, an early warning signal is issued to prompt maintenance personnel to inspect and maintain the rotating machinery to avoid failures.

[0055] Online prediction: When the trained model is deployed to the actual rotating machinery monitoring system, the newly collected real-time sensor data is first cleaned, normalized, and windowed according to the data preprocessing steps to obtain the input data samples at the current moment.

[0056] Model reasoning: The input data samples at the current moment are input into the trained model, and after being processed by the generator’s bidirectional Transformer and GNN layers, the predicted future sensor data sequence and remaining service life prediction value are obtained.

[0057] Result output and early warning: The predicted value of the remaining service life is compared with the preset threshold. If the predicted remaining service life is lower than the threshold, an early warning signal is issued to prompt maintenance personnel to inspect and maintain the rotating machinery to avoid failures.

[0058] The GBIT-GAN-based rotating machinery remaining service life prediction method proposed in the present invention effectively overcomes the problems in the prior art. By combining the graph neural network (GNN) with the bidirectional Transformer generative adversarial network (BIT-GAN), the structural information of the rotating machinery can be fully utilized to construct the graph structure, and the GNN layer can accurately capture the topological relationship between the components. The bidirectional Transformer performs well in processing time series data and can well mine the long-term dependencies in the data. The adversarial training mechanism of the generator and the discriminator further improves the accuracy and reliability of the model. This innovative fusion architecture makes the method described in the present invention have significant advantages in the prediction of the remaining service life of rotating machinery, and can provide more accurate and reliable decision-making basis for the maintenance and management of rotating machinery in industrial production, greatly reduce the risk of equipment failure, and ensure the safe and stable operation of production, which is of great significance to improving industrial production efficiency and economic benefits.

[0059] Example: Prediction of remaining bearing service life

[0060] In the monitoring of bearings of large rotating equipment in a factory, vibration, temperature and pressure sensors were installed at key parts of the bearings, and data was collected for 4 months. After screening and sorting, 1200 groups of valid samples were obtained. In the data preprocessing stage, the noise was removed by median filtering, and the data was mapped to the interval [0,1] according to the minimum-maximum normalization method. The time window was set to 30 minutes and the step length was 15 minutes for segmentation, and the remaining service life label was calculated according to the equipment operation and failure time. The improved BITGAN model was constructed. The bidirectional Transformer encoder and decoder of the generator were set to 3 layers each, the number of heads of the multi-head self-attention mechanism was 4, and the feedforward neural network was set according to a specific structure. The input was the data of the past 12 hours and the information such as the equipment speed, and the output was the data of the next 24 hours and the predicted value of the remaining service life. Its loss function was calculated according to the given formula and the appropriate weight was determined. The discriminator adopted a simple multi-layer perceptron structure, which contained 2 hidden layers and was trained according to its own loss function. When the GNN layer was introduced, a graph was constructed according to the bearing structure. The nodes covered the various components of the bearing and the related sensor data, and the edges reflected the connection relationship of the components and set the weights reasonably. Connect 3 layers of GCN layers after the Transformer encoder of the generator, update the node features according to the formula, and then weightedly fuse with the Transformer output (weight is set to 0.5) and input into the decoder. In model training, the training, validation and test sets are divided into 70%, 15%, and 15%. The Adam optimizer is used with an initial learning rate of 0.002. During training, the discriminator is fixed to train the generator, and then the parameters are updated by back propagation. The hyperparameters are adjusted according to the performance of the validation set. If there is no improvement for 8 consecutive cycles, the training is stopped. At the same time, the learning rate decay and gradient clipping optimization are used. During online prediction, the newly collected data is preprocessed and input into the trained model to obtain the prediction result. If the predicted remaining service life is less than 400 hours, an early warning is triggered to notify the maintenance personnel to check the bearing lubrication, wear and other conditions to ensure the normal operation of the equipment.

[0061] The present invention relates to the technical field of state monitoring and life prediction of rotating machinery, and specifically to a method for predicting the remaining service life of rotating machinery by using a fusion technology (GBIT-GAN) of a graph neural network (GNN) and a bidirectional Transformer generative adversarial network (BIT-GAN). The GBIT-GAN-based rotating machinery remaining service life prediction method of the present invention first performs data acquisition and preprocessing, and uses sensors such as acceleration, temperature, and pressure installed on the rotating machinery to collect multi-channel vibration, temperature, pressure, and other data, covering the entire process from normal to faulty equipment. Abnormal values ​​and noise are removed by filtering, and then the data is normalized to be in the [0,1] interval, and then the data is segmented according to a specific time window and the remaining service life label is marked. In terms of model construction, the generator is constructed based on a bidirectional Transformer, and its unique structure can effectively extract data features, input historical data and equipment information, output predicted values, and optimize through adversarial and reconstruction losses. The discriminator uses a suitable structure to distinguish the authenticity of data. At the same time, a GNN layer is introduced, a graph is constructed according to the mechanical structure and component connection, and the component and sensor data are integrated into the node, and the GNN layer is connected to the generator to fuse topological information. During model training, the data set is divided, training is iterated, and hyperparameters are adjusted based on the validation set. Techniques such as learning rate decay are used to improve performance. In actual applications, newly collected data is preprocessed and input into the model. The prediction results are compared with the threshold. If the result is lower than the threshold, an early warning is issued to ensure the stable operation of the rotating machinery and effectively improve the accuracy and reliability of the prediction.

[0062] The present invention also proposes an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for predicting the remaining useful life of rotating machinery based on GBIT-GAN are implemented.

[0063] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of a method for predicting the remaining useful life of rotating machinery based on GBIT-GAN.

[0064] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DRRAM). It should be noted that the memory of the method described in the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0065] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disc (SSD)).

[0066] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in a processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0067] It should be noted that the processor in the embodiment of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor can be combined and performed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0068] The above is a detailed introduction to the remaining service life prediction method of rotating machinery based on GBIT-GAN proposed in the present invention. This article uses specific examples to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for predicting the remaining useful life of rotating machinery based on GBIT-GAN, characterized in that: The method is specifically as follows: Data acquisition and preprocessing: Utilize acceleration, temperature and pressure sensors installed on rotating machinery to collect multi-channel vibration, temperature and pressure data, which covers the entire process from normal operation to failure of the equipment; Remove outliers and noise through filtering, normalize the data to the interval [0,1], and then segment the data into specific time windows and label the remaining useful life. Building the GBIT-GAN model: The generator is built on a bidirectional Transformer. The encoder and decoder of the Transformer are composed of multiple Transformer layers. Each Transformer layer contains a multi-head self-attention mechanism, a feedforward neural network, a residual connection, and layer normalization. The generator can effectively extract data features, input historical data and device information, output predicted values, and optimize through adversarial and reconstruction losses. The discriminator uses a structure that processes sequence data to distinguish the authenticity of data. A GNN layer is introduced after the bidirectional Transformer encoder of the generator to capture the topological relationship and information propagation between rotating machinery components; the output of the GNN layer is concatenated or weighted summed with the output of the bidirectional Transformer encoder for information fusion, and then the fused features are input into the decoder of the bidirectional Transformer to generate the predicted future sensor data sequence and the remaining service life prediction value; Model training: divide the training data set and use the training data set to iteratively train the GBIT-GAN model; Prediction of the remaining service life of rotating machinery: The newly collected data is preprocessed and input into the trained GBIT-GAN model. The prediction result is compared with the preset threshold. If the predicted remaining service life is lower than the threshold, an early warning signal is issued to prompt maintenance personnel to inspect and maintain the rotating machinery to avoid failures.

2. The method according to claim 1, characterized in that: The preprocessed data is divided into several data samples according to a certain time window. Each data sample contains multi-channel sensor data within a period of time and the corresponding remaining service life label. The size of the time window is selected according to the operating characteristics of the rotating machinery and the sampling frequency of the data. The remaining service life label y i The calculation is based on the actual operating time and failure time of the rotating machinery.

3. The method according to claim 1, characterized in that In the Transformer layer, for the input sequence X = [x1, x2, ..., x n ], where x i It is the i-th element in the sequence, i.e., the preprocessed data sample. The input is mapped into query Q, key K, and value V through linear transformation, i.e., Q = XW Q ,K=XW K ,V=XW V , where W Q ,W K ,W V is a learnable weight matrix; then calculate the attention weight where d k is the dimension of the key, and the softmax function is used to normalize the attention weights to [0,1] so that the sum of the weights is 1; finally, the output of the multi-head self-attention is MultiHead(X)=Concat(head1,head2,…,head h ,)W O , where head i =Attention(QW i Q ,KW i K ,VW i V ), h is the number of heads, W i Q ,W i K ,W i V and W O It is a learnable parameter matrix; the output of the multi-head self-attention is further transformed through a feedforward neural network. The feedforward neural network consists of two fully connected layers with a ReLU activation function in the middle. The formula is FFN(x)=ReLU(xW1+b1)W2+b2, where W1, W2 are weight matrices, and b1, b2 are bias vectors.

4. The method according to claim 3, characterized in that The input of the generator includes historical sensor data sequences and basic information of rotating machinery. This basic information is converted into vector representation through the embedding layer, and then concatenated with the historical sensor data sequence and input into the encoder of the bidirectional Transformer. The output of the generator is the predicted sensor data sequence of the next n time windows and the corresponding remaining service life prediction value.

5. The method according to claim 1, characterized in that Adversarial loss: The goal of the generator is to make the discriminator unable to distinguish between the generated sequence and the real sequence. The adversarial loss of the generator is expressed as where p g is the data distribution generated by the generator, and D(x) is the discriminator's judgment result on the input x; Reconstruction loss: Using mean square error MSE as reconstruction loss, then where p data is the real data distribution, x is the real sequence, is the sequence generated by the generator; Total loss: The total loss of the generator is the weighted sum of the adversarial loss and the reconstruction loss, i.e. Where α is a weight parameter used to balance the importance of adversarial loss and reconstruction loss.

6. The method according to claim 5, characterized in that The loss function in the discriminator is: The goal of the discriminator is to accurately distinguish between real sequences and generated sequences, and its loss function is expressed as 7. The method according to claim 1, characterized in that The GNN layer uses the graph convolutional network GCN. For node i, its feature update formula at the l+1 layer is: in is the feature vector of node i in layer l, is the feature vector of node j in layer l, N(i) is the set of neighbor nodes of node i, c ij is the normalization constant, W l is the learnable weight matrix of layer l, b l is the bias vector, σ is the activation function; By stacking multiple GNN layers, the features of the nodes can be continuously updated, thereby fusing the topological information and sensor data information between components.

8. The method according to claim 1, characterized in that In each training iteration, the discriminator parameters are first fixed, and a batch of data is sampled from the training set and input into the generator to generate a batch of predicted future sensor data sequences and remaining service life prediction values; the generated sequences and the real sequences are input into the discriminator, and the loss of the generator and the loss of the discriminator are calculated; the gradients of the parameters of the generator, discriminator and GNN layer are calculated respectively using the back-propagation algorithm, and the model parameters are updated according to the gradients to minimize the loss of the generator and maximize the loss of the discriminator; after each training cycle, the model is evaluated using the validation set, and the loss function value on the validation set and the error index between the predicted remaining service life and the actual remaining service life are calculated; according to the evaluation results of the validation set, the hyperparameters of the model are adjusted. If the performance on the validation set no longer improves, the training can be stopped early to prevent overfitting.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium for storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images