A method and system for predicting failure of aerospace payload rotating equipment

Abstract

The present invention provides a method and system for predicting faults of aerospace payload rotating equipment, and relates to the field of space science experimental technology. The method provided by the present invention acquires on-orbit operation data of payload rotating equipment, proposes a rotating equipment fault prediction model based on GPT-2, and redesigns the data embedding and feature mapping layers. Finally, knowledge is transferred to specific layers of the GPT-2 model through transfer learning, and the embedding and feature mapping layers are retrained, so that the model has cross-modal fault prediction capabilities. Compared with the methods for predicting faults of payload rotating equipment in related technologies, the accuracy and timeliness of the prediction results can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of space science experiments, and in particular to a fault prediction method and system for aerospace payload rotating equipment. Background Art

[0002] The space station has entered its application and development phase. As a crucial platform for space science experiments over the next decade, ensuring the long-term safe and stable operation of its space science payloads is a crucial requirement during this phase. Rotating mechanical components in payloads, key measurement components for experimental data, are crucial to the reliability of the entire payload and the smooth conduct of experiments. These components have a limited lifespan and are difficult to replace, making fault prediction crucial.

[0003] In related technologies, fault detection methods for space station scientific experiment payloads primarily rely on setting sensor parameter thresholds based on expert experience. This has certain limitations, making it difficult to achieve early fault prediction. Research on scientific payload fault prediction based on deep learning still faces challenges such as weak early fault signal characteristics, a scarcity of fault samples, and difficulty migrating models across varying operating conditions. This results in low fault prediction accuracy and poor timeliness. Summary of the Invention

[0004] An embodiment of the present invention provides a method and system for predicting faults of aerospace payload rotating equipment. Based on the vibration signal of the payload rotating equipment, a trained neural network model can accurately and timely predict the fault type of the space station payload rotating equipment.

[0005] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions:

[0006] In a first aspect, a fault prediction method for a space payload rotating device is provided, the method comprising: obtaining historical data of the payload rotating device, the historical data being a first parameter corresponding to each of l moments of the payload rotating device obtained by n sensors, the first parameter being acceleration or angular velocity, and l and n being positive integers; determining a plurality of first training samples and a fault category corresponding to each first training sample based on the historical data, wherein each first training sample comprises a first parameter corresponding to each of y moments of the payload rotating device obtained by x sensors, x and y being positive integers, and x being less than or equal to n, and y being less than or equal to l; training a neural network model based on the plurality of first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model; obtaining on-orbit operation data of the payload rotating device, the on-orbit operation data being a first parameter corresponding to each of l moments of the payload rotating device obtained by n sensors, and l and n being positive integers; inputting the on-orbit operation data into the trained neural network model, and outputting a fault prediction result corresponding to the on-orbit operation data, the fault prediction result including the fault category corresponding to the on-orbit operation data.

[0007] In a possible implementation of the first aspect, multiple first training samples and the fault category corresponding to each first training sample are determined based on historical data, including: normalizing and denoising the historical data to eliminate noise interference in the historical data, and ensuring that the value of the first parameter corresponding to each moment included in the historical data is within a preset threshold range; sampling the historical data to obtain multiple first training samples and the fault category corresponding to each first training sample.

[0008] In a possible implementation of the first aspect, training a neural network model based on multiple first training samples and a fault category corresponding to each first training sample to obtain a trained neural network model includes: inputting the multiple first training samples into the neural network model and outputting a predicted fault category corresponding to each first training sample; establishing an objective function based on the predicted fault category and the fault category corresponding to each first training sample; and iteratively training the neural network model based on the objective function to obtain a trained neural network model.

[0009] The objective function L is:

[0010]

[0011] Among them, L represents the cross entropy loss value, n represents the number of fault categories, and y i represents the fault category of the i-th type, Represents the output of the neural network model for the i-th fault category.

[0012] In a possible implementation of the first aspect, the neural network model includes an embedding unit and multiple stacked Transformer units, and the output end of the embedding unit is connected to the input end of the Transformer unit; the embedding unit is used to convert the input first training sample into a feature vector of a preset dimension corresponding to each first training sample; each Transformer unit includes an encoder and a decoder; the output end of the encoder of each Transformer unit is connected to the output end of the decoder of each Transformer unit; each encoder includes an attention layer and a feedforward neural network layer, the attention layer is used to determine the context information included in each feature vector, and the feedforward neural network layer is used to encode each feature vector to obtain a latent vector corresponding to each feature vector; each decoder includes a masked multi-head attention layer, an attention layer and a feedforward neural network layer, the multi-head attention layer is used to associate the input of each encoding unit with the output of each decoding unit; the attention layer is used to determine the context information included in each feature vector, and the feedforward neural network layer is used to decode each latent vector to obtain a feature vector corresponding to each feature vector.

[0013] In a possible implementation of the first aspect, before training the neural network model according to multiple first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model, the above method also includes: constructing a neural network model; training the neural network model to obtain a pre-trained neural network model; and adjusting the model parameters of the pre-trained neural network model based on the dimension of the first training sample to obtain a neural network model.

[0014] In a possible implementation of the first aspect, a neural network model is trained to obtain a pre-trained neural network model, including: performing modal decomposition processing on multiple first training samples to obtain a second training sample corresponding to each first training sample, where the second training sample is a spectrum image including multiple frequency domain features; and training the neural network model according to the second training samples corresponding to the multiple first training samples and the fault category corresponding to each second training sample to obtain a pre-trained neural network model.

[0015] The beneficial effects of the present invention are as follows: the method provided by the present invention obtains historical data of the payload rotating device, determines multiple first training samples based on the historical data of the payload rotating device, and determines second training samples corresponding to the multiple first training samples through modal decomposition processing, and then pre-trains the neural network model based on the multiple second training samples. After the training is completed, the model parameters of the neural network model are adjusted based on the dimension of the first training sample, and some parameters obtained from the previous training are retained. The pre-trained neural network model is trained according to the multiple first training samples to obtain a trained neural network model, and then, based on the trained neural network model, the fault category of the payload rotating device can be accurately and timely predicted according to the on-orbit operation data of the payload rotating device. Compared with the method for predicting faults of payload rotating devices in related technologies, the accuracy and timeliness of the prediction results can be improved. In addition, training time can be saved and training efficiency can be improved.

[0016] In a second aspect, an embodiment of the present invention provides a fault prediction system for aerospace payload rotating equipment, the system comprising: a data acquisition unit for acquiring historical data of the payload rotating equipment, the historical data being a first parameter corresponding to each of l moments of the payload rotating equipment acquired by n sensors, the first parameter being acceleration or angular velocity, and l and n being positive integers; a sample generation unit for determining, based on the historical data, a plurality of first training samples and a fault category corresponding to each first training sample, wherein each first training sample comprises a first parameter corresponding to each of y moments of the payload rotating equipment acquired by x sensors, and x and y being positive integers. and x is less than or equal to n, and y is less than or equal to l; a model training unit is used to train the neural network model according to multiple first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model; the data acquisition unit is further used to obtain on-orbit operation data of the payload rotating device, the on-orbit operation data is the first parameter corresponding to each of l moments of the payload rotating device obtained by n sensors, and l and n are positive integers; the fault prediction unit is used to input the on-orbit operation data into the trained neural network model, and output a fault prediction result corresponding to the on-orbit operation data, and the fault prediction result includes the fault category corresponding to the on-orbit operation data.

[0017] In a possible implementation of the second aspect, the model training unit is further used to: construct a neural network model; train the neural network model to obtain a pre-trained neural network model; and adjust the model parameters of the pre-trained neural network model based on the dimension of the first training sample to obtain a neural network model.

[0018] In a possible implementation of the second aspect, the model training unit is specifically used to: perform modal decomposition processing on multiple first training samples to obtain second training samples corresponding to each first training sample, where the second training sample is a spectrum image including multiple frequency domain features; train the neural network model according to the second training samples corresponding to the multiple first training samples and the fault category corresponding to each second training sample to obtain a pre-trained neural network model.

[0019] In a third aspect, an electronic device is provided, comprising a memory and one or more processors; the memory is coupled to the processor; wherein computer program code is stored in the memory, and the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the electronic device executes a method as in any implementation of the first aspect.

[0020] In a fourth aspect, a computer-readable storage medium is provided, comprising computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the method in any implementation of the first aspect.

[0021] In a fifth aspect, a computer program product is provided. When the computer program product is run on a computer, the computer is caused to execute the method in any implementation of the first aspect.

[0022] It can be understood that the beneficial effects that can be achieved by the system of the second aspect, the electronic device of the third aspect, the computer-readable storage medium of the fourth aspect, and the computer program product of the fifth aspect provided above can be referred to the beneficial effects in the first aspect and any possible design method thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention;

[0024] Figure 2 This is a flow chart of a method for predicting a fault of a space payload rotating device according to an embodiment of the present invention;

[0025] Figure 3 This is a flow chart of a method for predicting a fault of a space payload rotating device according to an embodiment of the present invention;

[0026] Figure 4 This is a flow chart of a method for predicting a fault of a space payload rotating device according to an embodiment of the present invention;

[0027] Figure 5 This is a flow chart of a method for predicting a fault of a space payload rotating device according to an embodiment of the present invention;

[0028] Figure 6A schematic flow chart of a method for predicting a fault of a rotating device of an aerospace payload according to an embodiment of the present invention is shown;

[0029] Figure 7 The figure is a schematic diagram of the hardware structure of a prediction system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention. In the description of the present invention, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship. For example, A / B can represent A or B. The "or" in the present invention is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, in the description of the present invention, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items.

[0031] In addition, to facilitate a clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that the words "first" and "second" do not limit the quantity or execution order, and the words "first" and "second" do not necessarily mean different.

[0032] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner to facilitate understanding.

[0033] The space station has entered its application and development phase. As a crucial platform for space science experiments over the next decade, ensuring the long-term safe and stable operation of its space science payloads is a crucial requirement during this phase. Rotating mechanical components in payloads, key measurement components for experimental data, are crucial to the reliability of the entire payload and the smooth conduct of experiments. These components have a limited lifespan and are difficult to replace, making fault prediction crucial.

[0034] In related technologies, fault detection methods for space station scientific experiment payloads primarily rely on setting sensor parameter thresholds based on expert experience. This has certain limitations, making it difficult to achieve early fault prediction. Research on scientific payload fault prediction based on deep learning still faces challenges such as weak early fault signal characteristics, a scarcity of fault samples, and difficulty migrating models across varying operating conditions. This results in low fault prediction accuracy and poor timeliness.

[0035] In view of this, an embodiment of the present invention provides a fault prediction method for a space payload rotating device, the method comprising: obtaining historical data of the payload rotating device, the historical data being a first parameter corresponding to each of l moments of the payload rotating device obtained by n sensors, the first parameter being acceleration or angular velocity, and l and n being positive integers; determining a plurality of first training samples and a fault category corresponding to each first training sample based on the historical data, wherein each first training sample comprises a first parameter corresponding to each of y moments of the payload rotating device obtained by x sensors, x and y being positive integers, and x being less than or equal to n, and y being less than or equal to l; training a neural network model based on the plurality of first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model; obtaining on-orbit operation data of the payload rotating device, the on-orbit operation data being a first parameter corresponding to each of l moments of the payload rotating device obtained by n sensors, and l and n being positive integers; inputting the on-orbit operation data into the trained neural network model, and outputting a fault prediction result corresponding to the on-orbit operation data, the fault prediction result including the fault category corresponding to the on-orbit operation data.

[0036] The method provided by the embodiment of the present invention obtains historical data of the payload rotating device, determines multiple first training samples based on the historical data of the payload rotating device, and determines second training samples corresponding to the multiple first training samples through modal decomposition processing, and then pre-trains the neural network model based on the multiple second training samples. After the training is completed, the model parameters of the neural network model are adjusted based on the dimension of the first training sample, and some parameters obtained from the previous training are retained. The pre-trained neural network model is trained according to the multiple first training samples to obtain a trained neural network model. Then, based on the trained neural network model, the fault category of the payload rotating device can be accurately and timely predicted according to the on-orbit operation data of the payload rotating device. Compared with the method for predicting faults of payload rotating devices in related technologies, the accuracy and timeliness of the prediction results can be improved. In addition, training time can be saved and training efficiency can be improved.

[0037] In some embodiments, the fault prediction method for aerospace payload rotating equipment provided by embodiments of the present invention can be performed by a fault prediction system 100 for aerospace payload rotating equipment (hereinafter referred to as prediction system 100). For example, prediction system 100 can be any electronic device 200 with data processing capabilities, such as a general-purpose computer, personal computer, laptop computer, switch, or tablet computer. The specific implementation of procurement list prediction system 100 is not limited herein.

[0038] Figure 1 The electronic device 200 includes a processor 210 , a memory 220 , and a communication interface 230 .

[0039] The processor 210 may include one or more processing cores. The processor 210 uses various interfaces and lines to connect various parts of the electronic device 200, and executes various functions of the electronic device 200 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 220, and calling data stored in the memory 220. Optionally, the processor 210 can be implemented in the form of at least one hardware of a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA).

[0040] The memory 220 may include a random access memory (RAl) or a read-only memory (ROL). Optionally, the memory 220 includes a non-transitory computer-readable storage medium (NMT). The memory 220 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 220 may include a program storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a data acquisition function, a model training function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.

[0041] The communication interface 230 is used to communicate with other devices, equipment or communication networks, such as data storage devices, image processing equipment or Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0042] In physical implementation, the aforementioned components (e.g., processor 210, memory 220, and communication interface 230) may be components within the same device (e.g., a laptop). Alternatively, at least two of the components may be provided within the same device, i.e., as different components within a single device, similar to the deployment of devices or components in a distributed system.

[0043] It should be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 200. In other embodiments of the present invention, the electronic device 200 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0044] The following describes a method for predicting a fault of a space payload rotating device according to an embodiment of the present invention in conjunction with the accompanying drawings.

[0045] Figure 2 The present invention provides a flowchart of a method for predicting a fault of a space payload rotating device. Figure 1 The electronic device 200 shown is executed, that is, executed by the prediction system 100. The method may include the following steps:

[0046] S1. Obtain historical data of payload rotation equipment.

[0047] Specifically, historical data is the first parameter of the payload rotating device at each of l moments, acquired by n sensors. The first parameter is acceleration or angular velocity, and l and n are positive integers. Alternatively, historical data can be understood as the vibration signal of the payload rotating device acquired by n sensors during the time period corresponding to l moments.

[0048] Specifically, the number of sensors is n, and each sensor acquires a one-dimensional time series data segment of length l, that is, including the first parameter corresponding to each of the l moments. The historical data is an input sequence set of size [l,n].

[0049] S2. Determine a plurality of first training samples and a fault category corresponding to each first training sample based on historical data.

[0050] Each first training sample includes a first parameter corresponding to each of y moments of the payload rotation device obtained by x sensors, where x and y are positive integers, and x is less than or equal to n, and y is less than or equal to 1;

[0051] In some embodiments, see Figure 3 The above S2 specifically includes the following steps:

[0052] S21 . Perform normalization and denoising processing on the historical data to eliminate noise interference in the historical data and ensure that the value of the first parameter corresponding to each moment included in the historical data is within a preset threshold range.

[0053] S22: Perform a sampling operation on the historical data to obtain a plurality of first training samples and a fault category corresponding to each first training sample.

[0054] Specifically, in actual applications, the length of historical data l is often as high as hundreds of millions of words. If all of this historical data is input into a neural network model for training at once, the computing device will overflow its memory, making effective training impossible. Therefore, the method provided by the present invention performs a sampling operation on historical data. In one example, first, a sliding sampling window is set. The width of this sliding window always remains consistent with the number of channels v in the feature map after data fusion. The length of the sliding window, W, is the length of the first training sample to be generated. Second, the sliding window slides forward at a certain step length B. After each step, the original data points with a length of W and a width of v channels contained in the sliding window are the newly generated feature map of the first training sample.

[0055] Optionally, the calculation formula for the number L of generated first training samples is:

[0056]

[0057] Where l represents the number of data points corresponding to each sensor in the historical data, W represents the length of the sliding window, that is, the length of the first training sample, B is the step size of the sliding window, λ represents the sampling overlap rate, and L is the number of newly generated training samples.

[0058] The method provided in the embodiments of the present invention flexibly controls the number of first training samples generated by adjusting the sampling overlap ratio λ. When λ>0, incremental overlapping sampling is used for data expansion; when λ=0, non-overlapping sampling is used for equal truncation; and when λ<0, sparse interval sampling is used. Furthermore, the width W of the sliding sampling window can be set based on the fault frequency, sampling period, and operating speed of the rotating machinery. According to Shannon's sampling theorem, the recommended setting for W is to be at least greater than or equal to two complete fault waveform cycles. The embodiments of the present invention do not impose any particular restrictions on the specific implementation of the sampling overlap ratio λ and the sampling window width W.

[0059] S3. Train the neural network model according to the multiple first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model.

[0060] In some embodiments, the neural network model includes an embedding unit and multiple stacked Transformer units, and the output end of the embedding unit is connected to the input end of the Transformer unit; the embedding unit is used to convert the input first training sample into a feature vector of a preset dimension corresponding to each first training sample; each Transformer unit includes an encoder and a decoder; the output end of the encoder of each Transformer unit is connected to the output end of the decoder of each Transformer unit; each encoder includes an attention layer and a feedforward neural network layer, the attention layer is used to determine the context information included in each feature vector, and the feedforward neural network layer is used to encode each feature vector to obtain a latent vector corresponding to each feature vector; each decoder includes a masked multi-head attention layer, an attention layer and a feedforward neural network layer, the multi-head attention layer is used to associate the input of each encoding unit with the output of each decoding unit; the attention layer is used to determine the context information included in each feature vector, and the feedforward neural network layer is used to decode each latent vector to obtain a feature vector corresponding to each feature vector.

[0061] Alternatively, the neural network model provided by the embodiments of the present invention features a neural network architecture based on stacked Transformer units. The Transformer units in this architecture consist of two parts: an encoder and a decoder. Within the Transformer unit, the encoder is responsible for converting the input sequence data into a high-dimensional representation for subsequent processing. The encoder is composed of multiple identical stacked layers, each of which contains two main sublayers: multi-head attention and a feedforward neural network. Multi-head attention establishes an attentional relationship between the glyph at each position and the glyphs at all other positions, thereby capturing global contextual information; while the feedforward neural network maps the vector at each position into a higher-dimensional space, helping the model capture more complex semantic information. Each sublayer is followed by accumulation and layer normalization to stabilize training and accelerate convergence. The stacking of multiple encoder layers enables the model to extract and fuse features from the input sequence layer by layer. The decoder differs from the encoder in that it incorporates masked multi-head attention, which correlates the input sequence with the output of the current decoding position to generate a meaningful output sequence. This structure more effectively captures semantic information and maintains consistency when generating sequences. The Transformer-based network achieves global information modeling and more efficient feature extraction through the self-attention mechanism, and alleviates the problems of gradient explosion and gradient vanishing during training, which greatly expands the number of parameters in the language model.

[0062] In one example, the first training example is a two-dimensional tensor with a shape of (batch_size, sequence_length), where batch_size is the batch size and sequence_length is the sequence length. First, the input data is embedded in an embedding layer, converting it into a format that the neural network model can process. Assuming the embedding dimension is embed_dim, the data shape becomes (batch_size, sequence_length, embed_dim). Next, the data is fed into a Transformer unit. A series of self-attention and feedforward network operations are performed on the input data. Assuming that n stacked Transformer units are retained, the data shape after passing through the Transformer unit remains (batch_size, sequence_length, embed_dim). The data is then transformed through a Linear layer. If the task is to predict k time points in the future, the output dimension of the Linear layer should be set to k. Therefore, after passing through the Linear layer, the data shape becomes (batch_size, sequence_length, k). Finally, the data is processed through a Regression layer. The normalization layer is usually used to normalize or otherwise transform the last dimension of the data to make it consistent with our prediction goal. For example, if our goal is to predict the value of k time points in the future, the normalization layer normalizes the last dimension of the data so that its value is between 0 and 1. Therefore, after the data passes through the normalization layer, its shape is still (batch_size, sequence_length, k), but its values ​​have been appropriately transformed.

[0063] In one possible implementation, see Figure 4 The above S3 specifically includes the following steps:

[0064] S31. Input a plurality of first training samples into a neural network model, and output a predicted fault category corresponding to each first training sample.

[0065] S32: Establish an objective function according to the predicted fault category and the fault category corresponding to each first training sample.

[0066] S33. Iteratively train the neural network model according to the objective function to obtain a trained neural network model.

[0067] Among them, the objective function L is:

[0068]

[0069] Among them, L represents the cross entropy loss value, n represents the number of fault categories, and y irepresents the fault category of the i-th type, Represents the output of the neural network model for the i-th fault category.

[0070] S4. Obtain on-orbit operation data of the payload rotating device. The on-orbit operation data is a first parameter corresponding to each of l moments of the payload rotating device obtained by n sensors, where l and n are positive integers.

[0071] S5. Input the on-orbit operation data into the trained neural network model, and output a fault prediction result corresponding to the on-orbit operation data. The fault prediction result includes a fault category corresponding to the on-orbit operation data.

[0072] As can be seen from S1-S5 above, the method provided by this embodiment of the present invention obtains historical data of the payload rotating device and trains a neural network model based on this data to obtain a trained neural network model. This trained neural network model can then be used to accurately and timely predict the type of faults in the payload rotating device based on the payload rotating device's on-orbit operation data. Compared to related methods for predicting faults in payload rotating devices, this method can improve the accuracy and timeliness of prediction results.

[0073] In some embodiments, see Figure 5 Before the prediction system executes S3 above, the method provided by the embodiment of the present invention further includes the following steps:

[0074] S61. Construct a neural network model;

[0075] Among them, the neural network model is the GPT-2 model.

[0076] S62, training the neural network model to obtain a pre-trained neural network model;

[0077] S63. Based on the dimension of the first training sample, adjust the model parameters of the pre-trained neural network model to obtain a neural network model.

[0078] In a possible implementation, the above S62 specifically includes the following steps:

[0079] Modal decomposition processing is performed on multiple first training samples to obtain second training samples corresponding to each first training sample, where the second training samples are spectrum images including multiple frequency domain features; a neural network model is trained according to the second training samples corresponding to the multiple first training samples and the fault category corresponding to each second training sample to obtain a pre-trained neural network model.

[0080] Specifically, Empirical Mode Decomposition (EMD) is an adaptive signal processing method particularly suitable for analyzing nonlinear and nonstationary signals. The EMD method does not require pre-defined basis functions. Instead, it decomposes the vibration signal included in the first training sample based on the time-scale characteristics of the data itself. The vibration signal included in the first training sample is decomposed into a finite number of intrinsic mode functions (IMFs). Each IMF contains local features of the original signal at different time scales. In other words, it forms a spectrum image containing multiple frequency-domain features.

[0081] The method provided in an embodiment of the present invention trains the neural network model through the second training sample to obtain a pre-trained neural network model, thereby realizing cross-modal migration of the architecture of the neural network model, that is, the self-attention layer and feedforward neural network of the pre-trained neural network model contain most of the knowledge learned during the pre-training process, and then the model parameters of the position embedding and layer normalization layer of the pre-trained neural network model are fine-tuned for cross-modal migration based on the dimension of the first training sample. The original input embedding layer is for the second training sample, so the input and output layers are redesigned here according to the dimension of the first training sample so that the first training sample is mapped to the dimension required by the specific pre-training model.

[0082] Furthermore, the architecture of the neural network model retains the multi-head attention and feedforward neural network in the pre-trained model. Since the multi-head attention and feedforward neural network contain most of the knowledge from the pre-trained neural network model, they are chosen to be retained during fine-tuning.

[0083] In one example, during the training of a neural network model, the neural network model learns the potential representation of sequence data through unsupervised learning. For a large language model, a potential representation of language is constructed by learning from a large text corpus, so that the model learns the statistical laws and semantic information of the language. Given a sequence data S = {s1, s2, s3, ..., s n}, the model task goal is based on the previous text s1,s2,s3,...,s i-1 , predict the target text s by autoregression i The objective function L pre (s) is expressed as the maximum likelihood function, where

[0084] Where n is the number of shape symbols in the sequence data, and P(·) is the likelihood function.

[0085] By training the neural network model with multiple second training samples, the neural network model learns a large amount of prior knowledge based on the corpus data. In order to enable the large prediction model to have the ability to reason about time series fault data with similar modalities, it is necessary to conduct cross-modal transfer learning on the model. That is, supervised learning is carried out on the mechanical fault diagnosis task to fine-tune and optimize the model parameters. For the supervised diagnosis task, given the state monitoring sequence data X of the mechanical equipment = {x1, x2, ..., x n} and its corresponding fault label set Y = (y1, y2, ...y n}, the fine-tuning target of the fault diagnosis model is based on any sample x in the given sequence data i Determine the corresponding fault type l i , the objective function L(x) of the process.

[0086]

[0087] The neural network model provided by the embodiments of the present invention uses the GPT-2 model as its core component and fine-tunes and configures the model parameters accordingly based on different task requirements (the dimensionality of the training samples). During the initialization phase, the neural network model sets various properties such as sequence length, prediction length, patch size, and step size based on the configuration parameters and calculates the required number of patches. In addition, the model initializes the DataEmbedding layer, which is responsible for converting the input data into a format suitable for model processing (that is, converting the first training sample into a format suitable for model processing). At the same time, the model loads a pretrained GPT-2 model (pretrained neural network model) and selects the number of layers to retain based on the configuration. To adapt to specific tasks, the model uses different linear and normalization layers before the output. For example, in a classification task, the model uses a linear layer to convert the GPT-2 output into an output representing the number of categories, and applies an activation function and normalization. These task-specific layers enable the model to better adapt to different application scenarios. During the fine-tuning process, the model specifically retains some parameters of the GPT-2 model, allowing only the parameters of some layers to be updated during training. The purpose of doing this is to retain the advantages of the pre-trained model while preventing overfitting during fine-tuning and speeding up the training process. If the configuration specifies the use of a GPU, the model will also transfer the GPT-2 components to the corresponding GPU device to take advantage of the GPU's computing power. In general, the present invention demonstrates how to fine-tune and adapt the pre-trained GPT-2 model according to different task requirements (a first training sample of type time series data and a second training sample of type spectral image). By retaining some parameters and introducing task-specific layers, the model can adapt to specific application scenarios while maintaining the advantages of pre-training, thereby achieving effective performance in a variety of tasks.

[0088] For example, to facilitate understanding of this solution, see Figure 6 , Figure 6 The present invention provides a flow chart of a method for predicting a fault of a space payload rotating device. The prediction system 100 first obtains historical data of the payload rotating device. The prediction system 100 then determines a plurality of first training samples and a fault category corresponding to each first training sample based on the historical data. The prediction system 100 then determines a second training sample corresponding to each first training sample based on the plurality of first training samples. The prediction system 100 then trains a neural network model based on the second training samples to obtain a pre-trained neural network model. It should be understood that the first training sample is a vibration signal of a first parameter (acceleration or angular velocity) corresponding to each of a plurality of moments acquired by a plurality of sensors. The second training sample is a spectrum image including a plurality of frequency domain features corresponding to each first training sample. The first training sample and the second training sample have different modes.

[0089] The prediction system 100 adjusts the parameters of the pre-trained neural network model based on the first training sample (freezes the multi-head attention and feedforward neural network of the pre-trained neural network model, adjusts the embedding layer and feature processing layer of the pre-trained neural network model, so that the pre-trained neural network model can take multiple first training samples as input for further training), and obtains the adjusted neural network model. The prediction system 100 then trains the adjusted neural network model based on multiple first training samples to obtain a trained neural network model. Finally, the prediction system 100 obtains the on-orbit operation data of the payload rotating equipment; inputs the on-orbit operation data into the trained neural network model, and outputs the fault prediction result corresponding to the on-orbit operation data, and the fault prediction result includes the fault category corresponding to the on-orbit operation data. Among them, the on-orbit operation data includes the vibration signal of the first parameter (acceleration or angular velocity) corresponding to each of multiple moments acquired by multiple sensors.

[0090] The above mainly introduces the solution of the embodiment of the present invention from the perspective of the method. It can be understood that in order to realize the above functions, the prediction system includes at least one of the hardware structure and software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiment of the present invention.

[0091] In embodiments of the present invention, the prediction system can be divided into functional units based on the above-described method examples. For example, the prediction system can be divided into functional units corresponding to different functions, or two or more functions can be integrated into a single processing unit. These integrated units can be implemented as either hardware or software functional units. It should be noted that the division of units in the embodiments of the present invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be employed.

[0092] For example, Figure 7 The hardware structure diagram of a prediction system provided by an embodiment of the present invention is shown. The prediction system 100 includes: a data acquisition unit 110, for acquiring historical data of the payload rotating device, the historical data being the first parameter corresponding to each of l moments of the payload rotating device acquired by n sensors, the first parameter being acceleration or angular velocity, l and n being positive integers; a sample generation unit 120, for determining a plurality of first training samples and a fault category corresponding to each first training sample based on the historical data, wherein each first training sample includes the first parameter corresponding to each of y moments of the payload rotating device acquired by x sensors, x and y being positive integers, and x being less than or equal to n, and y being less than or equal to l; a model The training unit 130 is used to train the neural network model based on multiple first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model; the data acquisition unit 110 is also used to obtain on-orbit operation data of the payload rotating equipment, where the on-orbit operation data is the first parameter corresponding to each of l moments of the payload rotating equipment obtained by n sensors, where l and n are positive integers; the fault prediction unit 140 is used to input the on-orbit operation data into the trained neural network model and output a fault prediction result corresponding to the on-orbit operation data, where the fault prediction result includes the fault category corresponding to the on-orbit operation data.

[0093] Optionally, the model training unit 130 is further used to: construct a neural network model; train the neural network model to obtain a pre-trained neural network model; and adjust the model parameters of the pre-trained neural network model based on the dimension of the first training sample to obtain a neural network model.

[0094] Optionally, the model training unit 130 is specifically used to: perform modal decomposition processing on multiple first training samples to obtain a second training sample corresponding to each first training sample, where the second training sample is a spectrum image including multiple frequency domain features; train the neural network model according to the second training samples corresponding to the multiple first training samples and the fault category corresponding to each second training sample to obtain a pre-trained neural network model.

[0095] Optionally, the sample generation unit 120 is specifically used to: normalize and denoise the historical data to eliminate noise interference in the historical data, and ensure that the value of the first parameter corresponding to each moment included in the historical data is within a preset threshold range; perform sampling operations on the historical data to obtain multiple first training samples and the fault category corresponding to each first training sample.

[0096] Optionally, the model training unit 130 is specifically configured to: input a plurality of first training samples into the neural network model, output a predicted fault category corresponding to each first training sample; establish an objective function based on the predicted fault category and the fault category corresponding to each first training sample; and iteratively train the neural network model based on the objective function to obtain a trained neural network model;

[0097] The objective function L is:

[0098]

[0099] Among them, L represents the cross entropy loss value, n represents the number of fault categories, and y i represents the fault category of the i-th type, Represents the output of the neural network model for the i-th fault category.

[0100] It should be understood that the specific description of the above optional methods can refer to the above method embodiments, which will not be repeated here. In addition, the explanation of any of the prediction systems 100 provided above and the description of the beneficial effects can refer to the above corresponding method embodiments, which will not be repeated here.

[0101] An embodiment of the present invention further provides a computer-readable storage medium storing at least one computer instruction, which is loaded and executed by a processor to implement the methods of each of the above embodiments. For explanations of the relevant contents and descriptions of the beneficial effects of any of the above-mentioned computer-readable storage media, reference can be made to the corresponding embodiments described above and will not be repeated here.

[0102] The embodiment of the present invention further provides a chip. The chip integrates a control circuit and one or more ports for implementing the functions of the above-mentioned prediction system 100. Optionally, the functions supported by the chip can be referred to above and will not be repeated here.

[0103] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned embodiments can be implemented by a program to instruct the relevant hardware to complete the program, which can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a random access memory, etc. The above-mentioned processing unit or processor can be a central processing unit, a general-purpose processor, a specific circuit structure (application specific integrated circuit, ASIC), a microprocessor (digital signal processor, DSP), a field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.

[0104] An embodiment of the present invention further provides a computer program product comprising instructions that, when executed on a computer, cause the computer to perform any of the methods described in the above embodiments. The computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of the present invention are fully or partially generated. 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. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium accessible by a computer or a data storage device such as a server or data center that includes one or more available media. Available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives).

[0105] It should be noted that the above-mentioned devices for storing computer instructions or computer programs provided in the embodiments of the present invention, such as but not limited to the above-mentioned memories, computer-readable storage media and communication chips, etc., all have non-transitory properties. Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present invention can be implemented using hardware, software, firmware or any combination thereof. When implemented using software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that facilitates the transmission of a computer program from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0106] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A method for predicting failures of aerospace payload rotating equipment, characterized in that: The method comprises: Acquire historical data of a payload rotating device, where the historical data is a first parameter corresponding to each of l moments of the payload rotating device acquired by n sensors, where the first parameter is acceleration or angular velocity, and l and n are positive integers; Determining, based on the historical data, a plurality of first training samples and a fault category corresponding to each first training sample, wherein each first training sample includes a first parameter corresponding to each of y moments of the payload rotating device acquired by x sensors, where x and y are positive integers, and x is less than or equal to n, and y is less than or equal to 1; Training the neural network model according to the multiple first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model; Acquire on-orbit operation data of the payload rotating device, where the on-orbit operation data is a first parameter corresponding to each of l moments of the payload rotating device acquired by n sensors, where l and n are positive integers; Inputting the on-orbit operation data into the trained neural network model, and outputting a fault prediction result corresponding to the on-orbit operation data, wherein the fault prediction result includes a fault category corresponding to the on-orbit operation data; Before training the neural network model according to the plurality of first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model, the method further includes: Build a neural network model; Train the neural network model to obtain a pre-trained neural network model; Adjusting model parameters of the pre-trained neural network model based on the dimension of the first training sample to obtain a neural network model; The training of the neural network model to obtain a pre-trained neural network model includes: Performing modal decomposition processing on the plurality of first training samples to obtain a second training sample corresponding to each first training sample, where the second training sample is a spectrum image including a plurality of frequency domain features; The neural network model is trained according to the second training samples corresponding to the multiple first training samples and the fault category corresponding to each second training sample to obtain a pre-trained neural network model.

2. The method according to claim 1, characterized in that The determining, based on the historical data, a plurality of first training samples and a fault category corresponding to each first training sample includes: Performing normalization and denoising on the historical data to eliminate noise interference in the historical data and ensure that the value of the first parameter corresponding to each moment included in the historical data is within a preset threshold range; A sampling operation is performed on the historical data to obtain a plurality of first training samples and a fault category corresponding to each first training sample.

3. The method according to claim 2, characterized in that The step of training the neural network model according to the plurality of first training samples and the fault category corresponding to each first training sample to obtain a trained neural network model includes: Inputting the plurality of first training samples into a neural network model, and outputting a predicted fault category corresponding to each first training sample; Establishing an objective function based on the predicted fault category and the fault category corresponding to each first training sample; Iteratively train the neural network model according to the objective function to obtain a trained neural network model; The objective function L is: Among them, L represents the cross entropy loss value, n represents the number of fault categories, and y i represents the fault category of the i-th type, Represents the output of the neural network model for the i-th fault category.

4. The method according to claim 3, characterized in that The neural network model includes an embedding unit and multiple stacked Transformer units, wherein the output end of the embedding unit is connected to the input end of the Transformer unit; the embedding unit is used to convert the input first training sample into a feature vector of a preset dimension corresponding to each first training sample; each Transformer unit includes an encoder and a decoder; the output end of the encoder of each Transformer unit is connected to the output end of the decoder of each Transformer unit; each encoder includes an attention layer and a feedforward neural network layer, the attention layer is used to determine the context information included in each feature vector, and the feedforward neural network layer is used to encode each feature vector to obtain a latent vector corresponding to each feature vector; each decoder includes a masked multi-head attention layer, an attention layer and a feedforward neural network layer, and the multi-head attention layer is used to associate the input of each encoding unit with the output of each decoding unit; The attention layer is used to determine the context information included in each feature vector, and the feedforward neural network layer is used to decode each latent vector to obtain the feature vector corresponding to each feature vector.

5. A fault prediction system for aerospace payload rotating equipment, characterized in that: The system comprises: a data acquisition unit, configured to acquire historical data of the payload rotating device, wherein the historical data is a first parameter corresponding to each of l moments of the payload rotating device acquired by n sensors, wherein the first parameter is acceleration or angular velocity, and l and n are positive integers; a sample generating unit, configured to determine, based on the historical data, a plurality of first training samples and a fault category corresponding to each first training sample, wherein each first training sample includes a first parameter corresponding to each of y moments of the payload rotating device acquired by x sensors, where x and y are positive integers, and x is less than or equal to n, and y is less than or equal to 1; A model training unit, configured to train a neural network model according to the plurality of first training samples and the fault category corresponding to each first training sample, to obtain a trained neural network model; The data acquisition unit is further configured to acquire on-orbit operation data of the payload rotating device, wherein the on-orbit operation data is a first parameter corresponding to each of l moments of the payload rotating device acquired by n sensors, where l and n are positive integers; a fault prediction unit, configured to input the on-orbit operation data into the trained neural network model and output a fault prediction result corresponding to the on-orbit operation data, wherein the fault prediction result includes a fault category corresponding to the on-orbit operation data; The model training unit is further used to: Build a neural network model; Train the neural network model to obtain a pre-trained neural network model; Adjusting model parameters of the pre-trained neural network model based on the dimension of the first training sample to obtain a neural network model; The training of the neural network model to obtain a pre-trained neural network model includes: Performing modal decomposition processing on the plurality of first training samples to obtain a second training sample corresponding to each first training sample, where the second training sample is a spectrum image including a plurality of frequency domain features; The neural network model is trained according to the second training samples corresponding to the multiple first training samples and the fault category corresponding to each second training sample to obtain a pre-trained neural network model.

6. The system according to claim 5, characterized in that The model training unit is further used to: Build a neural network model; Train the neural network model to obtain a pre-trained neural network model; Based on the dimension of the first training sample, the model parameters of the pre-trained neural network model are adjusted to obtain a neural network model.

7. The system according to claim 6, characterized in that The model training unit is specifically used to: Performing modal decomposition processing on the plurality of first training samples to obtain a second training sample corresponding to each first training sample, where the second training sample is a spectrum image including a plurality of frequency domain features; The neural network model is trained according to the second training samples corresponding to the multiple first training samples and the fault category corresponding to each second training sample to obtain a pre-trained neural network model.

8. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the fault prediction method for aerospace payload rotating equipment according to any one of claims 1 to 4.

Images