WO2026012467A1 - 基于多通道域适应网络的化工过程跨装置故障诊断方法及装置 - Google Patents

基于多通道域适应网络的化工过程跨装置故障诊断方法及装置

Info

Publication number
WO2026012467A1
WO2026012467A1 PCT/CN2025/108112 CN2025108112W WO2026012467A1 WO 2026012467 A1 WO2026012467 A1 WO 2026012467A1 CN 2025108112 W CN2025108112 W CN 2025108112W WO 2026012467 A1 WO2026012467 A1 WO 2026012467A1
Authority
WO
WIPO (PCT)
Prior art keywords
domain
target domain
target
features
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2025/108112
Other languages
English (en)
French (fr)
Inventor
赵劲松
秦若时
杨博睿
吕菲亚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tsinghua University
Original Assignee
Tsinghua University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tsinghua University filed Critical Tsinghua University
Publication of WO2026012467A1 publication Critical patent/WO2026012467A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/096—Transfer learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2123/00—Data types
    • G06F2123/02—Data types in the time domain, e.g. time-series data

Definitions

  • This disclosure relates to the field of chemical process control technology, and in particular to a method and apparatus for cross-unit fault diagnosis of chemical processes based on a multi-channel domain adaptive network.
  • fault diagnosis methods in these technologies are mainly based on statistical probability modeling and deep learning, with deep learning-based methods still dominating.
  • this disclosure proposes a cross-unit fault diagnosis method and device for chemical processes based on a multi-channel domain adaptive network, which can realize cross-domain transfer of fault category information, achieve high accuracy and low false alarm rate fault diagnosis on different units in similar process flows, and has effective cross-unit general capability.
  • a method for cross-unit fault diagnosis in chemical processes based on a multi-channel domain adaptation network includes: acquiring a fault diagnosis task for a device to be diagnosed under a target process flow; determining target domain data required to perform the fault diagnosis task based on the fault diagnosis task and the device to be diagnosed, wherein the target domain data includes various operating data of the device to be diagnosed operating under a first target domain, the first target domain being determined according to the target process flow; inputting the target domain data into a trained multi-channel domain adaptation network for calculation to obtain a diagnosis result for the fault diagnosis task; wherein the method further includes a training process for the multi-channel domain adaptation network, the training process including the following steps: acquiring a target domain sample dataset and a source domain sample dataset, wherein the target domain sample dataset includes multiple different sample devices operating under multiple different process flows.
  • the target domain sample data under the second target domain includes source domain sample data of each sample device operating in multiple different source domains.
  • Each target domain sample data and each source domain sample data includes multiple normal operation data and multiple abnormal operation data.
  • Each sample device, each second target domain, and each source domain are determined according to different process flows in the chemical process.
  • Each normal operation data and each abnormal operation data in the source domain sample dataset are labeled to obtain a source domain labeled dataset.
  • a training sample set is constructed based on the source domain labeled dataset and the target domain sample dataset.
  • the initialized multi-channel domain adaptation network is trained based on a preset loss function and the training sample set to obtain a trained multi-channel domain adaptation network.
  • the loss function includes a feature distribution difference function constructed based on the maximum mean difference induced by a multinomial kernel.
  • the multi-channel domain adaptation network includes a feature extraction module and a domain adaptation module.
  • the initialization of the multi-channel domain adaptation network is trained based on a preset loss function and the training sample set to obtain a trained multi-channel domain adaptation network.
  • the feature extraction module includes a source domain branch and a target domain branch; wherein, processing the training sample set using the feature extraction module to obtain processing results, and determining the source domain loss function value and target domain loss function value of the feature extraction module based on the processing results, includes: using the source domain branch to extract features from the data of each source domain in the source domain sample data to obtain source domain features of each source domain, inferring the source domain classification result of the corresponding source domain based on the source domain features of each source domain, and determining the source domain loss function value of the feature extraction module based on the source domain classification result and the true domain label of each source domain; using the target domain branch to extract features from the target domain sample data to obtain target domain features of each second target domain, inferring the target domain classification result of the corresponding second target domain based on the target domain features, and determining the target domain loss function value of the feature extraction module based on the target domain classification result and the true domain label of each second target domain.
  • the domain adaptation module processes the source domain features and the target domain features to obtain fault category prediction results for each abnormal operation data in the target domain sample data. Based on each fault category prediction result, the relational loss function value of the domain adaptation module is determined. This includes: using the domain adaptation module to calculate the target domain features and the source domain features to obtain domain-adapted sample features; determining the fault category prediction results for the target domain sample data based on the domain-adapted sample feature degree and a predetermined fault category; and determining the relational loss function value of the domain adaptation module based on the fault category prediction results and the true fault labels of the target domain sample data.
  • the source domain features include source domain-specific features representing information unique to the source domain
  • the target domain features include target domain-specific features representing information unique to the second target domain
  • the domain adaptation module includes a first fully connected layer network pair and a second fully connected layer network pair; wherein, determining the feature distribution difference function value using a polynomial kernel function and the training sample set includes: determining a first feature distribution difference function value based on the source domain sample data according to the definition rules of the polynomial kernel function, determining a second feature distribution difference function value based on the output of the first fully connected layer network pair, and determining a third feature distribution difference function value based on the output of the second fully connected layer network pair; and determining the feature distribution difference function value based on the first feature distribution difference function value, the second feature distribution difference function value, and the third feature distribution difference function value.
  • the target domain data is input into a trained multi-channel domain adaptation network for computation to obtain a diagnostic result for the fault diagnosis task.
  • This includes: extracting sub-domain features from the target domain data to obtain sub-domain specific features representing information unique to the first target domain; and extracting global features from the target domain data to obtain global universal features representing common information shared by the first target domain and each of the source domains.
  • Domain migration features are then determined based on the sub-domain specific features and the global universal features. Fault diagnosis is performed based on the domain migration features to obtain a diagnostic result for the fault diagnosis task.
  • subdomain feature extraction is performed on the target domain data to obtain subdomain-specific features representing information unique to the target domain
  • global feature extraction is performed on the target domain data to obtain global universal features representing common information shared by the target domain and each of the source domains.
  • This includes: performing subdomain feature extraction on the target domain data at a time scale to obtain subdomain temporal features; performing subdomain feature extraction on the subdomain temporal features at a spatial scale to obtain the subdomain-specific features; and performing global feature extraction on the target domain data at a time scale to obtain global temporal features; and performing global feature extraction on the global temporal features at a spatial scale to obtain the global-specific features.
  • a fault diagnosis device for a chemical process across units based on a multi-channel domain adaptation network, comprising: an acquisition module for acquiring a fault diagnosis task for a device to be diagnosed under a target process flow; a determination module for determining target domain data required to perform the fault diagnosis task based on the fault diagnosis task and the device to be diagnosed, the target domain data including various operating data of the device to be diagnosed operating under a first target domain, the first target domain being determined according to the target process flow; and a calculation module for inputting the target domain data into a trained multi-channel domain adaptation network for calculation to obtain a diagnosis result for the fault diagnosis task;
  • the device further comprises a training module, the training module being used to: acquire a target domain sample dataset and a source domain sample dataset, the target domain sample dataset including multiple different sample devices operating under multiple different process flow conditions;
  • the target domain sample data under the same second target domain, the source domain sample dataset includes source domain sample data of each sample device operating under multiple different source domains, wherein each target domain
  • the multi-channel domain adaptation network includes a feature extraction module and a domain adaptation module.
  • the initialization of the multi-channel domain adaptation network is trained based on a preset loss function and the training sample set to obtain a trained multi-channel domain adaptation network.
  • the domain adaptation module processes the source domain features and the target domain features to obtain fault category prediction results for each abnormal operation data in the target domain sample data. Based on each fault category prediction result, the relational loss function value of the domain adaptation module is determined. This includes: using the domain adaptation module to calculate the target domain features and the source domain features to obtain domain-adapted sample features; determining the fault category prediction results for the target domain sample data based on the domain-adapted sample feature degree and a predetermined fault category; and determining the relational loss function value of the domain adaptation module based on the fault category prediction results and the true fault labels of the target domain sample data.
  • the source domain features include source domain-specific features representing information unique to the source domain
  • the target domain features include target domain-specific features representing information unique to the second target domain
  • the domain adaptation module includes a first fully connected layer network pair and a second fully connected layer network pair; wherein, determining the feature distribution difference function value using a polynomial kernel function and the training sample set includes: determining a first feature distribution difference function value based on the source domain sample data according to the definition rules of the polynomial kernel function, determining a second feature distribution difference function value based on the output of the first fully connected layer network pair, and determining a third feature distribution difference function value based on the output of the second fully connected layer network pair; and determining the feature distribution difference function value based on the first feature distribution difference function value, the second feature distribution difference function value, and the third feature distribution difference function value.
  • the target domain data is input into a trained multi-channel domain adaptation network for computation to obtain a diagnostic result for the fault diagnosis task.
  • This includes: extracting sub-domain features from the target domain data to obtain sub-domain specific features representing information unique to the first target domain; and extracting global features from the target domain data to obtain global universal features representing common information shared by the first target domain and each of the source domains.
  • Domain migration features are then determined based on the sub-domain specific features and the global universal features. Fault diagnosis is performed based on the domain migration features to obtain a diagnostic result for the fault diagnosis task.
  • subdomain feature extraction is performed on the target domain data to obtain subdomain-specific features representing information unique to the target domain
  • global feature extraction is performed on the target domain data to obtain global universal features representing common information shared by the target domain and each of the source domains.
  • This includes: performing subdomain feature extraction on the target domain data at a time scale to obtain subdomain temporal features; performing subdomain feature extraction on the subdomain temporal features at a spatial scale to obtain the subdomain-specific features; and performing global feature extraction on the target domain data at a time scale to obtain global temporal features; and performing global feature extraction on the global temporal features at a spatial scale to obtain the global-specific features.
  • an electronic device comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the above-described method when executing instructions stored in the memory.
  • a non-volatile computer-readable storage medium that stores computer program instructions thereon, wherein the computer program instructions, when executed by a processor, implement the above-described method.
  • a computer program product including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device performs the above-described method.
  • Figures 1 and 2 show schematic diagrams of a cross-unit fault diagnosis method for chemical processes based on a multi-channel domain adaptive network according to embodiments of the present disclosure.
  • Figure 3 shows a schematic diagram of a multi-channel domain adaptation network provided according to an embodiment of the present disclosure.
  • Figure 4 shows a schematic diagram of a feature extraction module provided according to an embodiment of the present disclosure.
  • Figure 5 shows a schematic diagram of a multi-head attention mechanism provided according to an embodiment of the present disclosure.
  • Figure 6 shows a schematic diagram of a converter model provided according to an embodiment of the present disclosure.
  • Figure 7 shows a schematic diagram illustrating the variation trend of the maximum mean difference induced by the Gaussian kernel under different bandwidth parameters.
  • Figure 8 shows a schematic diagram of the process flow of the Tennessee-Eastman process.
  • Figure 9 shows a comparative schematic diagram of the operation of the Tennessee-Eastman process provided according to an embodiment of the present disclosure under normal and fault conditions.
  • Figure 10 shows a schematic diagram of a cross-condition fault diagnosis confusion matrix provided according to an embodiment of the present disclosure.
  • Figure 11 shows a radar diagram illustrating the comparison of fault diagnosis time in the Tennessee-Eastman process using different deep transfer learning methods provided according to embodiments of the present disclosure.
  • Figures 12 and 13 show block diagrams of a chemical process cross-unit fault diagnosis device based on a multi-channel domain adaptive network according to embodiments of the present disclosure.
  • this disclosure provides a cross-unit fault diagnosis method for chemical processes based on a Multi-Channel Domain Adaptive Network (MSDAN).
  • the method includes: acquiring a fault diagnosis task for the equipment to be diagnosed under a target process flow; determining target domain data required to perform the fault diagnosis task based on the fault diagnosis task and the equipment to be diagnosed, wherein the target domain data includes various operating data of the equipment to be diagnosed operating under a first target domain, which is determined according to the target process flow; inputting the target domain data into a trained multi-channel domain adaptive network for calculation to obtain a diagnosis result for the fault diagnosis task; wherein the method further includes a training process for the multi-channel domain adaptive network, the training process including the following steps: acquiring a target domain sample dataset and a source domain sample dataset, wherein the target domain sample dataset includes multiple different sample devices operating under a target process flow.
  • the system comprises target domain sample data under multiple different second target domains, and source domain sample datasets including source domain sample data of various sample devices operating under multiple different source domains.
  • Each target domain sample dataset and each source domain sample dataset includes multiple normal operation data and multiple abnormal operation data.
  • Each sample device, each second target domain, and each source domain is determined based on different process flows in the chemical process.
  • Each normal operation data and each abnormal operation data in the source domain sample dataset is labeled to obtain a source domain labeled dataset.
  • a training sample set is constructed based on the source domain labeled dataset and the target domain sample dataset.
  • the initialized multi-channel domain adaptation network is trained based on a preset loss function and the training sample set to obtain the trained multi-channel domain adaptation network.
  • the loss function includes a feature distribution difference function constructed based on the maximum mean difference induced by a multinomial kernel. This enables cross-domain transfer of fault category information, achieving high-accuracy, low-false-report fault diagnosis on different devices in similar process flows, and possesses effective cross-device generalization capabilities.
  • Figures 1 and 2 are schematic diagrams of a cross-unit fault diagnosis method for chemical processes based on a multi-channel domain adaptation network according to an embodiment of the present disclosure.
  • Figure 3 is a schematic diagram of a multi-channel domain adaptation network according to an embodiment of the present disclosure.
  • Figure 4 is a schematic diagram of a feature extraction module according to an embodiment of the present disclosure.
  • Figure 5 is a schematic diagram of a multi-head attention mechanism according to an embodiment of the present disclosure.
  • Figure 6 is a schematic diagram of a converter model according to an embodiment of the present disclosure.
  • Figure 7 is a schematic diagram of the variation trend of the maximum mean difference induced by Gaussian kernels under different bandwidth parameters.
  • Figure 8 is a schematic diagram of the process flow of the Tennessee-Eastman process.
  • Figure 9 is a schematic diagram comparing the operation of the Tennessee-Eastman process under normal and fault conditions according to an embodiment of the present disclosure.
  • Figure 10 is a schematic diagram of a cross-condition fault diagnosis confusion matrix according to an embodiment of the present disclosure.
  • Figure 11 is a radar schematic diagram showing the comparison results of fault diagnosis time of different deep transfer learning methods according to an embodiment of the present disclosure in the Tennessee-Eastman process.
  • the cross-unit fault diagnosis method for chemical processes (hereinafter referred to as the diagnosis method) provided in this disclosure is illustrated below with reference to Figures 1 to 11.
  • This diagnosis method includes not only the actual fault diagnosis method based on a multi-channel domain adaptation network, but also the training method for the multi-channel domain adaptation network.
  • the multi-channel domain adaptation network i.e., the fault diagnosis model, includes a feature extraction module and a domain adaptation module.
  • the number of feature extraction modules can be set to one or more according to actual needs.
  • the cross-unit fault diagnosis method for chemical processes provided in this embodiment may include the following steps S101 to S103 in the online diagnosis stage for a fault diagnosis model. Steps S101 to S103 enable cross-domain transfer of fault category information, achieving high-accuracy and low-false-alarm-rate fault diagnosis for the equipment to be diagnosed.
  • Step S101 Obtain the fault diagnosis task for the equipment to be diagnosed under the target process flow.
  • the target process flow can be determined based on the process flow of interest in the actual chemical process.
  • the equipment to be diagnosed can also be determined based on the process flow of interest in the actual chemical process, and the number can be one or multiple.
  • Step S102 Determine the target domain data required to perform the fault diagnosis task based on the fault diagnosis task and the device to be diagnosed.
  • the target domain data includes various operating data of the device to be diagnosed operating under the first target domain.
  • the specific operating data can be determined according to the actual process flow and the actual device to be diagnosed in the chemical process. This disclosure does not limit this.
  • the first target domain is also determined based on the target process flow.
  • the first target domain used in practical applications and the second target domain involved in training are essentially both target domains, meaning new datasets from which knowledge learned from the source domain needs to be applied.
  • the data distribution of the target domain differs from that of the source domain, and it may have little or no labeled data.
  • the source domain in transfer learning, refers to the dataset with labeled data, usually used to train the model to learn useful features and knowledge.
  • target domain data refers to the dataset from which prediction or classification needs to be performed.
  • multi-channel domain adaptation networks i.e., fault diagnosis models, need to apply knowledge learned from the source domain to infer target domain data and target sample data.
  • Multi-source domain data also known as the source domain sample dataset (hereinafter referred to as the source domain sample dataset), refers to datasets from multiple different source domains. Multi-source domain data can provide more diversity and richer information, helping to improve the learning effect of the target domain.
  • Step S103 Input the target domain data into the trained multi-channel domain adaptation network for calculation to obtain the diagnostic results for the fault diagnosis task.
  • step S103 may include: extracting subdomain features from the target domain data to obtain subdomain-specific features representing information unique to the first target domain; and extracting global features from the target domain data to obtain global universal features representing common information shared by the first target domain and various source domains.
  • subdomain-specific features and global universal features can be determined by a feature extraction module.
  • Domain migration features are then determined based on the subdomain-specific features and global universal features.
  • Fault diagnosis is performed based on the domain migration features to obtain a diagnostic result for the fault diagnosis task.
  • the total features determined by the subdomain-specific features and global universal features can be processed based on a domain adaptation module to obtain the final diagnostic result.
  • Subdomain-specific features cover unique information specific to the first target domain
  • global universal features cover common information between the target domain and multiple source domains. This fusion of dual features can more accurately identify fault modes in the first target domain, thereby improving the accuracy of fault diagnosis.
  • step S103 which involves extracting sub-domain features from the target domain data to obtain sub-domain-specific features representing information unique to the target domain, and extracting global features from the target domain data to obtain global universal features representing common information shared by the target domain and all source domains, may include: extracting sub-domain features at a time scale from the target domain data to obtain sub-domain temporal features; extracting sub-domain features at a spatial scale from the sub-domain temporal features to obtain sub-domain-specific features; and extracting global features at a time scale from the target domain data to obtain global temporal features, and extracting global features at a spatial scale from the global temporal features to obtain global-specific features.
  • the process of extracting sub-domain features at a time scale can be implemented based on a Transformer model, and the process of extracting global features at a spatial scale can be implemented based on a Multi-Scale Convolutional Neural Network (MSCNN), as detailed below.
  • MSCNN Multi-Scale Convolutional Neural Network
  • Feature extraction at the time scale helps to understand the changing trends and periodicity of data over time, while feature extraction at the spatial scale can reveal the patterns and differences in the spatial distribution of data.
  • This multi-dimensional feature extraction method significantly enhances the diagnostic model's ability to capture both target domain-specific and common information, thereby improving the accuracy of fault diagnosis.
  • the cross-unit fault diagnosis method for chemical processes provided in this embodiment of the present disclosure further includes a training process for a multi-channel domain adaptation network.
  • the training process includes the following steps S201 to S203 in the offline modeling stage for the fault diagnosis model.
  • steps S201 to S203 key features can be effectively extracted from the data in the source domain and the second target domain, and the domain adaptation mechanism can be used to reduce the differences between domains, thereby improving the fault diagnosis capability of the multi-channel domain adaptation network in the target domain.
  • This cross-domain adaptation capability enables the multi-channel domain adaptation network to maintain high diagnostic accuracy in different target domains.
  • the use of a multinomial kernel function to calculate the feature distribution difference function value helps to quantify the difference between the feature distributions of the source domain and the target domain, thereby guiding the multi-channel domain adaptation network to gradually reduce this difference during the training process. This allows the multi-channel domain adaptation network to not only perform well on the training set, but also maintain high generalization performance on unseen test sets.
  • Step S201 Obtain the target domain sample dataset and the source domain sample dataset.
  • the target domain sample dataset includes target domain sample data from multiple different sample devices operating in multiple different second target domains. These multiple different sample devices and multiple different second target domains can be determined based on similar or different process flows in chemical engineering. Taking sample device A as an example, target domain sample data for sample device A under each second target domain can be obtained. This data may include one or more types of operational data.
  • the source domain sample dataset includes source domain sample data for each sample device operating in multiple different source domains. These multiple different sample devices and multiple different source domains can be determined based on similar or different process flows in chemical engineering. Taking sample device B as an example, source domain sample data for sample device B in various source domains can be obtained. This data may include one or more types of operational data.
  • Each target domain sample data and each source domain sample data includes multiple normal operation data and multiple abnormal operation data, so that the multi-channel domain adaptation network can perform transfer learning based on these normal operation data and abnormal operation data.
  • the number and type of sample devices, the number of second target domains, the number of source domains, and the type and quantity of running data can all be flexibly set according to actual needs.
  • Step S202 Label each normal operation data and each abnormal operation data in the source domain sample dataset to obtain the source domain labeled dataset. Construct a training sample set based on the source domain labeled dataset and the target domain sample dataset.
  • Step S203 Train the initialized multi-channel domain adaptation network based on the preset loss function and training sample set to obtain the trained multi-channel domain adaptation network.
  • the loss of a multi-channel domain adaptation network can include three parts: domain class loss (source domain loss and target domain loss), relation loss, and feature distribution difference loss.
  • the loss function can include the source domain loss function and target domain loss function of the feature extraction module, the relation loss function of the domain adaptation module, and the feature distribution difference function constructed based on polynomial kernel-induced maximum mean difference (PK-MMD).
  • the parameters of the multi-channel domain adaptation network can be initialized according to actual needs, and this embodiment of the disclosure does not limit this.
  • the parameters of the current multi-channel domain adaptation network can be updated based on the specific value corresponding to the loss function.
  • the multi-channel domain adaptation network can comprehensively evaluate the performance of the fault diagnosis model during training and update the parameters based on these evaluation results.
  • This multi-level evaluation mechanism helps to improve the reliability and accuracy of the diagnostic results.
  • the multi-channel domain adaptation network structure includes two main modules: a feature extraction module and a domain adaptation module.
  • This diagnostic method incorporates a novel feature extraction module, Transformer-MSCNN, within a multi-channel domain adaptation network.
  • This module is formed by concatenating a Transformer model with a multi-scale convolutional neural network. For example, as shown in Figure 4, normal operation data (or normal samples) and abnormal operation data (or fault samples with labels) from the source domain sample data are input into the feature extraction module via different channels.
  • the temporal features determined by the Transformer are processed by a global general feature extraction channel and a sub-domain specific feature extraction channel to form a feature map containing key information about the source domain. This provides strong source domain knowledge support for subsequent sample classification tasks.
  • the global general feature extraction channel aims to summarize common features between domains through domain adaptation, while the sub-domain specific feature extraction channel extracts domain-specific discriminative features to facilitate fault classification and domain label classification.
  • Transformer and MSCNN focus on the sample data at both temporal and spatial scales, respectively, to capture richer feature information across different dimensions.
  • the Transformer primarily focuses on the global relationships between different variables, which helps extract cross-domain shared information in transfer tasks.
  • MSCNN focuses on local features of data, complementing the ability of multi-channel domain adaptive networks to learn data features at different scales.
  • an attention mechanism is also introduced to enhance the multi-channel adaptive network's understanding of data features.
  • the multi-head attention mechanism used is another variation of the self-attention mechanism.
  • the multi-head attention mechanism executes multiple self-attention unit operations in parallel on the input data. Each self-attention operation can be considered a new subspace. Its workflow is shown in Figure 5, consisting of three steps: input data segmentation, attention weight calculation, and feature fusion and output.
  • the initial calculation of the multi-head attention mechanism is similar to the original self-attention mechanism.
  • the query, key, and value vectors (referred to as Q, K, and V vectors) obtained after linear transformation of the original data sequence are linearly transformed by their respective transformation matrices and then input into the scaled dot-product attention module.
  • the mechanism calculates the attention scores between vectors and performs a weighted summation of the values. Then, it concatenates all the scaled dot-product results and outputs them after a linear transformation to obtain the feature results enhanced by the multi-head attention mechanism.
  • This mechanism endows multi-channel adaptive networks with the ability to learn their correlation information within different representation subspaces, and is also key to the Transformer model's ability to capture complex variable relationships. For example, the calculation of scaled dot product attention is as follows:
  • q represents the Query vector, which is used to match the key in the attention mechanism to calculate the attention weights;
  • k represents the Key vector, which is matched with q to calculate the attention weights;
  • v represents the Value vector, which is the vector of the final weighted sum to obtain the output result.
  • the main structure of the Transformer model consists of an encoder and a decoder.
  • the encoder processes the input sequence, and the decoder generates the output sequence (emphasizing temporal features). Both are formed by stacking feedforward neural networks (FFNs) using a multi-head attention mechanism.
  • FNNs feedforward neural networks
  • the self-attention layer enhances the model's representational ability by learning information from different positions in the sequence in parallel. Residual connections are added at the output of each sub-layer of the Transformer model to avoid the gradient vanishing problem during training.
  • the decoder outputs the probability distribution of each output element, thereby analyzing the positional information and importance of each element in the input sequence.
  • the number of attention heads in both the encoder and decoder of the Transformer can be set to 3.
  • the convolutional kernels of MSCNN can be set according to actual needs. Fully connected layers are connected before and after to integrate the features extracted from each unit. The learning rate is 0.001 by default, and the network parameters are updated through backpropagation.
  • L′ represents the loss function of the feature extractor module, where n is the total number of samples, x represents the dimension of the variable, and y is the true label of the sample. Assign classification labels to the samples.
  • the feature extraction module can arrange an equal number of branch channels according to the total number of source domains. Each channel is further divided into a subdomain-specific feature extraction channel and a global general feature extraction channel, used to simultaneously extract cross-domain common features and the unique features of each source domain from multi-source domain data.
  • the types of branch channels can include source domain branches and target domain branches as shown in Figure 3. Both source domain branches and target domain branches include corresponding subdomain-specific feature extraction channels and global general feature extraction channels.
  • the subdomain-specific feature extraction channels in the source domain branches are used to extract subdomain features (or unique features) of the data input to that source domain branch to obtain the corresponding source domain-specific features.
  • the global general feature extraction channels in the source domain branches are used to extract global features (or cross-domain common features) of the data input to that source domain branch to obtain the corresponding source domain general features.
  • Source domain features can include source domain-specific features and source domain general features.
  • the subdomain-specific feature extraction channel in the target domain branch is used to extract subdomain features from the data input to that target domain branch to obtain the corresponding target domain-specific features.
  • the global general feature extraction channel in the target domain branch is used to extract global features from the data input to that target domain branch to obtain the corresponding target domain general features.
  • Target domain features can include both target domain-specific and target domain general features.
  • source domain features represent the source domain aspect features of the corresponding source domain
  • target domain features represent the target domain aspect features of the corresponding target domain.
  • Source domain-specific features in source domain features represent information unique to the corresponding source domain
  • target domain-specific features in target domain features represent information unique to the corresponding target domain.
  • the specific source and target domains are determined based on the actual situation.
  • the number of branch channels in the feature extraction module can be set according to actual needs.
  • Step S203 which involves processing the training sample set using the feature extraction module to obtain processing results, and determining the source domain loss function value and target domain loss function value of the feature extraction module based on these results, may include: using the source domain branch in the feature extraction module to extract features from the data of each source domain in the source domain sample data, obtaining source domain features for each source domain; inferring the source domain classification result for the corresponding source domain based on the source domain features; and determining the source domain loss function value of the feature extraction module based on the source domain classification results and the true domain labels of each source domain; and using the target domain branch in the feature extraction module to extract features from the target domain sample data, obtaining target domain features for each second target domain; inferring the target domain classification result for the corresponding second target domain based on the target domain features; and determining the target domain loss function value of the feature extraction module based on the target domain classification results and the true domain labels of
  • the source domain loss function value of the feature extraction module can be determined by the following equation (3):
  • L ⁇ sub>ds ⁇ /sub> represents the source domain loss function
  • n ⁇ sub>bs ⁇ /sub> represents the total number of samples used in a specific source domain during one training process.
  • This represents the source domain classification result (or genus classification result) of the i-th sample in the source domain.
  • This represents the true domain label of the i-th sample in the source domain.
  • the target domain branch of the feature extraction module directly processes the target domain sample data for testing fault classification accuracy, without processing the source domain data.
  • the source domain data is specifically used for parameter adjustment during training, such as adjusting the parameters of the diagnostic model through backpropagation.
  • the target domain loss function value of the feature extraction module can be determined by the following equation (4):
  • L dt represents the target domain loss function
  • n bt represents the total number of samples used in a target domain during one training process. This represents the target domain classification result (or genus classification result) of the i-th sample in the target domain. This represents the true domain label of the i-th sample in the target domain, when the sample in the target domain is correctly classified.
  • target domain is misclassified
  • This diagnostic method also incorporates a domain adaptation module within the multi-channel domain adaptation network. After feature extraction and filtering, the contributions of all samples unsuitable for migration are eliminated, while key information is assigned greater weight. For example, the multi-channel data features output by the feature extraction module can be weighted and summed using the following formula (5) to form a feature map for classification by the domain adaptation module:
  • f ⁇ sub>s,t ⁇ /sub> represents the feature map calculated by the domain adaptation module, which represents the comprehensive features of the entire feature space; This represents the feature map output by the i-th feature extraction module, which is determined jointly by Transformer and MSCNN.
  • the input data is first processed by Transformer to obtain temporal features, and then the temporal features are processed by MSCNN to obtain the output results of the feature extraction modules corresponding to Transformer and MSCNN.
  • This output result may include subdomain-specific features and global general features.
  • the subdomain-specific features and global general features under the first target domain can be determined based on the trained Transformer and MSCNN.
  • the output results of the feature extraction module are obtained based on the subdomain-specific features and global general features. Then, based on the actual number of feature extraction modules set, the feature map, i.e., the domain transfer features, calculated by the domain adaptation module is determined.
  • equation (6) represents the label of the i-th fault category obtained from the diagnosis; c represents the index of the fault category, with the number of categories ranging from 1 to C; Let f ⁇ sub>s,t ⁇ /sub> represent the preset fault category label, and f ⁇ sub>s,t ⁇ /sub> represent the domain migration feature. This represents the similarity score between the feature map domain transfer features and the preset fault category label on fault category c.
  • the relational loss of the domain adaptation module is determined by the relational loss function.
  • Step S203 involves processing the source and target domain features using the domain adaptation module to obtain the fault category prediction results for each abnormal operation data in the target domain sample data. Based on these fault category prediction results, the relational loss function value of the domain adaptation module is determined. This may include: calculating the target and source domain features using the domain adaptation module to obtain the domain adaptation sample features; determining the fault category prediction results for the target domain sample data based on the domain adaptation sample feature degree and the predetermined fault category; and determining the relational loss function value of the domain adaptation module based on the fault category prediction results and the actual fault labels of the target domain sample data.
  • the relational loss function value of the domain adaptation module can be determined by the following formula (7):
  • One of the loss functions may include three corresponding loss functions: PK-MMD1, PK-MMD2, and PK-MMD3.
  • PK-MMD1 corresponds to the first feature distribution difference function
  • PK-MMD2 to the second feature distribution difference function
  • PK-MMD3 to the third feature distribution difference function.
  • the feature distribution difference function measures the distribution difference between source domain sample data in different source domains.
  • the feature distribution difference function is used as one of the loss functions to adjust the weights of the diagnostic model.
  • the first, second, and third feature distribution difference functions can be calculated synchronously after the weights of each layer in the diagnostic model are determined to update the parameters of the diagnostic model. This embodiment does not limit the order in which they are calculated.
  • step S203 determining the feature distribution difference function value using a multinomial kernel function and the training sample set, may include: determining the first feature distribution difference function value based on the source domain sample data according to the definition rules of the multinomial kernel function; determining the second feature distribution difference function value based on the output of the first fully connected layer network pair; and determining the third feature distribution difference function value based on the output of the second fully connected layer network pair; and determining the feature distribution difference function value based on the first, second, and third feature distribution difference function values.
  • the output of the first fully connected layer network pair is determined based on the source domain sample data, and the output of the second fully connected layer network pair is determined similarly.
  • the first, second, and third feature distribution difference function values can be calculated simultaneously.
  • L represents the total loss function
  • ⁇ 0 represents the weight corresponding to the relation loss function Lr
  • ⁇ 1 represents the weight corresponding to the first feature distribution difference function
  • LPK -MMD1 represents the first feature distribution difference function
  • ⁇ 2 represents the weight corresponding to the second feature distribution difference function
  • LPK -MMD2 represents the second feature distribution difference function
  • ⁇ 3 represents the weight corresponding to the third feature distribution difference function
  • LPK -MMD3 represents the third feature distribution difference function
  • ⁇ 4 represents the weights corresponding to the source domain loss function Lds and the target domain loss function Ldt .
  • GK-MMD Gaussian Kernel-induced Maximum Mean Discrepancy
  • MMD has evolved into various variants by selecting different kernel functions. Among them, Gaussian Kernel-induced Maximum Mean Discrepancy (GK-MMD) is the most commonly used, but it has three significant drawbacks in application.
  • GK-MMD relies on the average distance for calculation, ignoring the influence of higher-order moments, which limits the accuracy of calculating the differences in the distribution of transferable features, thus affecting the overall quality of transfer learning.
  • GK-MMD has high computational complexity. Since its computational complexity is quadratic with the number of samples (O( n2 + 2mn + m2 ), it leads to significant memory consumption and high computational costs when processing large-scale datasets.
  • the algorithm is sensitive to the parameter settings of the Gaussian kernel.
  • the performance of the Gaussian kernel depends on the choice of bandwidth parameter, lacking the flexibility of adjusting more parameters. Inappropriate bandwidth parameter selection can lead to overfitting or underfitting.
  • the GK-MMD metric results fluctuate significantly when the kernel width changes slightly. Therefore, the model based on GK-MMD has difficulty converging at the optimal parameter point during the distribution adaptation process.
  • k(x,y) represents the polynomial kernel function, used to calculate the kernel value between input vectors x and y. It maps the input features to a high-dimensional space to capture the nonlinear relationship of the data; the slope a represents the contribution of the higher-order moments to the difference in sample distribution. The larger the slope value, the greater the influence of the higher-order moments on the distribution difference; the intercept b is a constant term and is usually set to 1; c represents the order of the polynomial, which determines the dimension of the feature space mapped to; k( ⁇ ) represents the polynomial of the element-wise product between input vectors x and y.
  • the formula for calculating PK-MMD is as follows: x ⁇ sub>i ⁇ /sub>, x ⁇ sub>j ⁇ /sub> , y ⁇ sub>i ⁇ /sub> , and y ⁇ sub> j ⁇ /sub> represent the eigenvectors of the source or target domain, which are determined based on the actual processing procedure.
  • PK-MMD The computational complexity of PK-MMD is O(c(c+3)/2+ ⁇ (n+m)), where O( ⁇ ) represents the time cost of matrix multiplication.
  • the polynomial kernel by mapping to a higher-dimensional space to extract the nonlinear features of the data, makes PK-MMD perform better when handling complex datasets. Its flexible and variable parameters also provide opportunities to adjust the model complexity; choosing appropriate kernel parameters can balance the model's metric accuracy and computational efficiency.
  • source domain sample data and target domain sample data are used as training data and input into the feature extraction module of the multi-channel domain adaptation network through different channels.
  • the feature extraction module After acquiring the training data, the feature extraction module focuses on both spatial and temporal aspects to capture feature information. After feature extraction and filtering, all samples whose contributions are unsuitable for transfer are removed, and key information is given higher weights.
  • the multi-channel data features output by the feature extraction module are linearly transformed and converted into feature maps for classification by the domain adaptation module.
  • the model is trained using training data collected under different operating conditions, and the optimal connection parameters of the multi-channel domain adaptation network are obtained by learning the data features in the training data.
  • the monitoring data of the validation set is input into the trained multi-channel domain adaptation network to calculate the confusion matrix, fault diagnosis time (FDT), and diagnostic accuracy, thus evaluating the multi-channel domain adaptation network to obtain a multi-channel domain adaptation network that meets the preset evaluation conditions.
  • the novel cross-unit fault diagnosis method for chemical processes proposed in this embodiment utilizes Transformer and MSCNN to extract cross-domain features from sample data in each domain.
  • the multi-channel features undergo linear transformation to convert them into feature maps.
  • the feature maps enter the domain adaptation module, which calculates the similarity correlation between sample data by sharing weights.
  • the Tennessee-Eastman (TE) process is a classic industrial process simulation dataset in the field of fault diagnosis. By simulating real chemical production processes and introducing various fault conditions into the control environment, it has become a commonly used benchmark simulation model for multivariate process monitoring methods.
  • the main chemical reactions involved in this process are as follows: A(g) + C(g) + D(g) ⁇ G(l), A(g) + C(g) + E(g) ⁇ H(l), A(g) + E(g) ⁇ F(l), and 3D(g) ⁇ 2F(l).
  • This irreversible exothermic chemical reaction process includes four gaseous feedstocks, two liquid products, and one byproduct. The reaction environment is protected by an inert gas.
  • This example uses the basic operating conditions of the TE simulation for the experiment, with a data acquisition cycle of 3 minutes. Analysis of all monitored variables in the reaction process revealed that the component variables of the new model exhibited very small trends and low data acquisition frequency. Therefore, only 12 manipulated variables and 30 continuously measured variables were selected for modeling. All variables are labeled with their serial numbers in Figure 8 to more intuitively illustrate the measurement locations and potential coupling relationships. Due to the low sampling frequency of the component variables, this example only selects manipulated variables and continuously measured variables to build the dataset, totaling 42 variables. Since the control system of the latest TEP model can effectively control faults 15, 16, 23, and 28, these four types of disturbances are not considered (i.e., Table 1 does not include the disturbance information corresponding to disturbance serial numbers 15, 16, 23, and 28). The disturbances studied in this example are shown in Table 1 below. Table 1 illustrates the various disturbances in the TEP dataset.
  • the TE process was used as a case study to validate the method's effectiveness in cross-condition transfer fault diagnosis.
  • TE process simulation data for five different operating conditions were collected and used in the experiment.
  • labeled data from one operating condition was selected as the training set to diagnose the operational status of other unlabeled operating conditions.
  • Table 2 shows the accuracy of MSDAN in unsupervised fault diagnosis of the TE process across the target domain under different operating conditions. Based on the results in the table, the average diagnostic rate of the MSDAN method in all experiments was calculated to be 95.7%. to Representing five source domains, to The five target domains are represented. Observing the results in Table 2, it can be found that MSDAN performs well in pairwise migration and mutual diagnosis tasks in most operating conditions, and the fault diagnosis accuracy of each migration experiment exceeds 90%, indicating that the model maintains strong robustness in complex scenarios across operating conditions.
  • Figure 10 shows the fault diagnosis confusion matrix of MSDAN with condition 1 as the training set and condition 4 as the test set. Only faults 9 and 15, which are difficult to diagnose, did not reach 90% accuracy. From the raw data, fault 9 only caused random changes in the feed temperature (D) represented by variable 24, and fault 15, representing condenser cooling water valve stickiness, did not cause drastic fluctuations in the measured variables. Therefore, the characteristics of most variables for these two faults are similar to those under normal conditions, making accurate diagnosis difficult. However, the experimental results also demonstrate that the remaining 18 faults were accurately identified by the deep transfer network, and the overall diagnostic accuracy is satisfactory.
  • this example further extends the MSDAN model structure by enriching the training set samples of the source domain with other operating condition data not used in pairwise transfer experiments. More source domain feature extraction and domain adaptation channels are added to the network structure to evaluate the model's feature learning ability for multiple source domain data.
  • Table 4 shows the accuracy results of different depth transfer learning models in multi-source domain cross-operating condition fault diagnosis tasks. Taking 94.5% in Table 4(a) as an example, 94.5% represents the diagnostic accuracy when the model is transferred to target domain 2 after training with data from source domain (0+1). The results demonstrate that the overall classification performance tends to improve when the model is trained with more source domain data.
  • MSDAN can fully learn the fault features of different operating conditions represented by multiple source domains, improving the fault diagnosis accuracy for the target operating condition and performing the best among all methods.
  • MSDAN also has strong flexibility in model design. When the experiment includes more data from different domains with similar feature distributions, MSDAN can be extended into an enhanced model that learns more effective features from multi-source domain data and transfers them to the target domain task, thus providing design ideas for building a more general fault diagnosis model.
  • This disclosure proposes a cross-unit fault diagnosis method for chemical processes based on a Multi-channel Domain Adaptive Network (MSDAN). It not only introduces a novel feature extraction network built on Transformer-MSCNN, employing a modified polynomial kernel-induced maximum mean difference (PK-MMD) as a measure of the difference in probability distributions between source and target domain data, but also proposes that during training, source and target domain data are fed into different channels in parallel as input to the MSDAN. Simultaneously, normal and fault samples from the source domain are also labeled and fed into different channels of the feature extractor to extract common inter-domain features and specific domain discriminative features for fault classification and domain label classification.
  • MSDAN Multi-channel Domain Adaptive Network
  • the difference in feature distributions between the target and source domains is minimized, achieving cross-domain transfer of fault category information.
  • the cross-unit fault diagnosis method for chemical processes proposed in this disclosure significantly reduces the diagnostic model's dependence on labeled information, lowers the demand for manually labeled data, and can fully learn the fault characteristics of different operating conditions represented by multiple source domains, improving the fault diagnosis accuracy for the target operating condition represented by the target domain. This provides a foundation for subsequent fault diagnosis research on cross-unit industrial cases.
  • Figure 12 shows a block diagram of a cross-unit fault diagnosis device for chemical processes based on a multi-channel domain adaptation network according to an embodiment of the present disclosure.
  • the cross-unit chemical process 100 includes an acquisition module 101, a determination module 102, a calculation module 103, and a training module 104.
  • the acquisition module 101 is used to acquire a fault diagnosis task for the equipment to be diagnosed under a target process flow.
  • the determination module 102 is used to determine the target domain data required to perform the fault diagnosis task based on the fault diagnosis task and the equipment to be diagnosed.
  • the target domain data includes various operating data of the equipment to be diagnosed operating under a first target domain, which is determined according to the target process flow.
  • the calculation module 103 is used to input the target domain data into the trained multi-channel domain adaptation network for calculation to obtain a diagnosis result for the fault diagnosis task.
  • Training module 104 is used for: acquiring a target domain sample dataset and a source domain sample dataset, wherein the target domain sample dataset includes target domain sample data of multiple different sample devices operating in multiple different second target domains, and the source domain sample dataset includes source domain sample data of each of the sample devices operating in multiple different source domains, wherein each of the target domain sample data and each of the source domain sample data includes multiple normal operation data and multiple abnormal operation data, and each of the sample devices, each of the second target domains, and each of the source domains are determined according to different process flows in the chemical process; labeling each normal operation data and each of the abnormal operation data in the source domain sample dataset to obtain a source domain labeled dataset; constructing a training sample set based on the source domain labeled dataset and the target domain sample dataset; training the initialized multi-channel domain adaptation network based on a preset loss function and the training sample set to
  • the multi-channel domain adaptation network includes a feature extraction module and a domain adaptation module.
  • the initialization of the multi-channel domain adaptation network is trained based on a preset loss function and the training sample set to obtain a trained multi-channel domain adaptation network.
  • the feature extraction module includes a source domain branch and a target domain branch; wherein, processing the training sample set using the feature extraction module to obtain processing results, and determining the source domain loss function value and target domain loss function value of the feature extraction module based on the processing results, includes: using the source domain branch to extract features from the data of each source domain in the source domain sample data to obtain source domain features of each source domain, inferring the source domain classification result of the corresponding source domain based on the source domain features of each source domain, and determining the source domain loss function value of the feature extraction module based on the source domain classification result and the true domain label of each source domain; using the target domain branch to extract features from the target domain sample data to obtain target domain features of each second target domain, inferring the target domain classification result of the corresponding second target domain based on the target domain features, and determining the target domain loss function value of the feature extraction module based on the target domain classification result and the true domain label of each second target domain.
  • the domain adaptation module processes the source domain features and the target domain features to obtain fault category prediction results for each abnormal operation data in the target domain sample data. Based on each fault category prediction result, the relational loss function value of the domain adaptation module is determined. This includes: using the domain adaptation module to calculate the target domain features and the source domain features to obtain domain-adapted sample features; determining the fault category prediction results for the target domain sample data based on the domain-adapted sample feature degree and a predetermined fault category; and determining the relational loss function value of the domain adaptation module based on the fault category prediction results and the true fault labels of the target domain sample data.
  • the source domain features include source domain-specific features representing information unique to the source domain
  • the target domain features include target domain-specific features representing information unique to the second target domain
  • the domain adaptation module includes a first fully connected layer network pair and a second fully connected layer network pair; wherein, determining the feature distribution difference function value using a polynomial kernel function and the training sample set includes: determining a first feature distribution difference function value based on the source domain sample data according to the definition rules of the polynomial kernel function, determining a second feature distribution difference function value based on the output of the first fully connected layer network pair, and determining a third feature distribution difference function value based on the output of the second fully connected layer network pair; and determining the feature distribution difference function value based on the first feature distribution difference function value, the second feature distribution difference function value, and the third feature distribution difference function value.
  • the target domain data is input into a trained multi-channel domain adaptation network for computation to obtain a diagnostic result for the fault diagnosis task.
  • This includes: extracting sub-domain features from the target domain data to obtain sub-domain specific features representing information unique to the first target domain; and extracting global features from the target domain data to obtain global universal features representing common information shared by the first target domain and each of the source domains.
  • Domain migration features are then determined based on the sub-domain specific features and the global universal features. Fault diagnosis is performed based on the domain migration features to obtain a diagnostic result for the fault diagnosis task.
  • the functions or modules of the apparatus provided in this disclosure can be used to perform the methods described in the above method embodiments.
  • the specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.
  • This disclosure also proposes a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement the above-described method.
  • the computer-readable storage medium can be volatile or non-volatile.
  • This disclosure also proposes an electronic device, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.
  • This disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of an electronic device, the processor in the electronic device performs the above-described method.
  • FIG. 13 shows a block diagram of a cross-plant fault diagnosis apparatus for chemical processes based on a multi-channel domain adaptive network according to an embodiment of the present disclosure.
  • apparatus 1900 may be provided as a server or terminal device.
  • apparatus 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions executable by the processing component 1922, such as application programs.
  • the application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions.
  • processing component 1922 is configured to execute instructions to perform the methods described above.
  • Device 1900 may also include a power supply component 1926 configured to perform power management of device 1900, a wired or wireless network interface 1950 configured to connect device 1900 to a network, and an input/output interface 1958 (I/O interface).
  • Device 1900 can operate on an operating system stored in memory 1932, such as Windows Server TM , Mac OS X TM , Unix TM , Linux TM , FreeBSD TM , or similar.
  • a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of the apparatus 1900 to perform the described method.
  • This disclosure can be a system, method, and/or computer program product.
  • a computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.
  • a computer-readable storage medium may be a tangible device capable of holding and storing instructions used by an instruction execution device.
  • a computer-readable storage medium may be, for example—but not limited to—an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof.
  • Computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combinations thereof.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • SRAM static random access memory
  • CD-ROM compact disc read-only memory
  • DVD digital multifunction disc
  • memory sticks floppy disks
  • mechanical encoding devices such as punch cards or recessed protrusions storing instructions thereon, and any suitable combinations thereof.
  • Computer-readable storage media as used herein is not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.
  • the computer-readable program instructions described herein can be downloaded from the computer-readable storage media to various computing/processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and/or wireless network, to an external computer or external storage device.
  • Networks may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
  • Each computing/processing device's network adapter card or network interface receives computer-readable program instructions from the network and forwards these instructions to computer-readable storage media within the respective computing/processing device.
  • the computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C” or similar languages.
  • the computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server.
  • the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
  • electronic circuits such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing state information of computer-readable program instructions. These electronic circuits can execute computer-readable program instructions to implement various aspects of this disclosure.
  • These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions/actions specified in one or more blocks of the flowchart and/or block diagram.
  • These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and/or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions/actions specified in one or more blocks of the flowchart and/or block diagram.
  • Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions/actions specified in one or more boxes of a flowchart and/or block diagram.
  • each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function.
  • the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.
  • each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本公开涉及一种基于多通道域适应网络的化工过程跨装置故障诊断方法及装置，方法包括获取针对目标工艺流程下的待诊断设备的故障诊断任务，基于故障诊断任务和待诊断设备确定出执行故障诊断任务所需的目标域数据，目标域数据包括待诊断设备运行在第一目标域下的多种运行数据，第一目标域是根据目标工艺流程确定出的，将目标域数据输入至训练后的多通道域适应网络进行计算，得到针对故障诊断任务的诊断结果。根据本公开实施例的化工过程跨装置故障诊断方法及装置能够实现故障类别信息的跨域迁移，在相似工艺流程中不同装置上实现高准确性、低误报率的故障诊断，具备有效的跨装置通用能力。

Description

基于多通道域适应网络的化工过程跨装置故障诊断方法及装置
本公开要求于2024年7月12日提交中国专利局、申请号为202410937242.7，发明名称为“基于多通道域适应网络的化工过程跨装置故障诊断方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及化工过程控制技术领域，尤其涉及一种基于多通道域适应网络的化工过程跨装置故障诊断方法及装置。
背景技术
随着人工智能和工业大数据技术的蓬勃发展，许多基于数据驱动的过程控制技术被相继提出，以解决化工过程中的故障诊断的问题。相关技术中的故障诊断方法主要基于统计概率建模的技术和基于深度学习的技术，其中基于深度学习的技术仍占据主流。
然而，基于深度学习的故障诊断方法主要用于单个设备例如轴承、皮带的故障诊断，由于单个设备监测变量少、故障特征明显，诊断效果较好。由于化工过程中的工艺流程存在变量多维耦合、工况动态波动的特点，相比而言单个设备的应用场景更加复杂，目前针对化工过程控制技术领域的跨装置故障诊断问题还没有效果较好的技术方案，通用的诊断模型较少且在分类准确率上也亟需提升。
公开内容
有鉴于此，本公开提出了一种基于多通道域适应网络的化工过程跨装置故障诊断方法及装置，能够实现故障类别信息的跨域迁移，在相似工艺流程中不同装置上实现高准确性、低误报率的故障诊断，具备有效的跨装置通用能力。
根据本公开的一方面，提供了一种基于多通道域适应网络的化工过程跨装置故障诊断方法，所述方法包括：获取针对目标工艺流程下的待诊断设备的故障诊断任务；基于所述故障诊断任务和所述待诊断设备确定出执行所述故障诊断任务所需的目标域数据，所述目标域数据包括所述待诊断设备运行在第一目标域下的多种运行数据，所述第一目标域是根据所述目标工艺流程确定出的；将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果；其中，所述方法还包括所述多通道域适应网络的训练过程，所述训练过程包括以下步骤：获取目标域样本数据集和源域样本数据集，所述目标域样本数据集包括多个不同的样本设备运行在多个不同的第二目标域下的目标域样本数据，所述源域样本数据集包括各所述样本设备运行在多个不同的源域下的源域样本数据，其中，各所述目标域样本数据和各所述源域样本数据均包括多个正常运行数据和多个异常运行数据，各所述样本设备、各所述第二目标域、各所述源域均是根据化工过程中不同工艺流程确定出的；对所述源域样本数据集中的各正常运行数据和各异常运行数据分别进行标注，得到源域标注数据集，根据所述源域标注数据集和所述目标域样本数据集构建训练样本集；基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，其中，所述损失函数包括基于多项式核诱导最大均值差异构建出的特征分布差异函数。
在一种可能的实现方式中，所述多通道域适应网络包括特征提取模块和域适应模块；其中，基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，包括：利用所述特征提取模块对所述训练样本集进行处理，得到处理结果，基于所述处理结果确定出所述特征提取模块的源域损失函数值和目标域损失函数值，所述处理结果包括源域特征、目标域特征、源域分类结果、目标域分类结果；利用所述域适应模块对所述源域特征和所述目标域特征进行处理，得到所述目标域样本数据中的各异常运行数据的故障类别预测结果，基于各所述故障类别预测结果确定出所述域适应模块的关系损失函数值；利用多项式核函数和所述训练样本集确定出特征分布差异函数值；根据所述源域损失函数值、所述目标域损失函数值、所述关系损失函数值、所述特征分布差异函数值确定出当前多通道域适应网络的总损失函数值，并基于所述总损失函数值进行当前多通道域适应网络的参数更新。
在一种可能的实现方式中，所述特征提取模块包括源域分支和目标域分支；其中，利用所述特征提取模块对所述训练样本集进行处理，得到处理结果，基于所述处理结果确定出所述特征提取模块的源域损失函数值和目标域损失函数值，包括：利用源域分支对所述源域样本数据中各所述源域的数据进行特征提取，得到各所述源域的源域特征，基于各所述源域的源域特征推测出对应源域的源域分类结果，基于各所述源域分类结果和各所述源域的真实域标签确定出所述特征提取模块的源域损失函数值；利用目标域分支对所述目标域样本数据进行特征提取，得到各所述第二目标域的目标域特征，基于各所述目标域特征推测出对应第二目标域的目标域分类结果，基于各所述目标域分类结果和各所述第二目标域的真实域标签确定出所述特征提取模块的目标域损失函数值。
在一种可能的实现方式中，利用所述域适应模块对所述源域特征和所述目标域特征进行处理，得到所述目标域样本数据中的各异常运行数据的故障类别预测结果，基于各所述故障类别预测结果确定出所述域适应模块的关系损失函数值，包括：利用所述域适应模块对所述目标域特征和所述源域特征进行计算，得到域适应样本特征；基于所述域适应样本特征度和预定的故障类别确定出所述目标域样本数据的故障类别预测结果；根据所述故障类别预测结果和所述目标域样本数据的真实故障标签确定出所述域适应模块的关系损失函数值。
在一种可能的实现方式中，所述源域特征包括表示源域中特有信息的源域特定特征，所述目标域特征包括表示第二目标域中特有信息的目标域特定特征，所述域适应模块包括第一全连接层网络对和第二全连接层网络对；其中，利用多项式核函数和所述训练样本集确定出特征分布差异函数值，包括：按照所述多项式核函数的定义规则，基于所述源域样本数据确定出第一特征分布差异函数值，并基于所述第一全连接层网络对的输出结果确定出第二特征分布差异函数值，并基于所述第二全连接层网络对的输出结果确定出第三特征分布差异函数值；根据所述第一特征分布差异函数值、所述第二特征分布差异函数值、所述第三特征分布差异函数值确定出所述特征分布差异函数值。
在一种可能的实现方式中，将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果，包括：对所述目标域数据进行子域特征提取，得到表示所述第一目标域中特有信息的子域特定特征，并对所述目标域数据进行全局特征提取，得到表示所述第一目标域与各所述源域所共有的通用信息的全局通用特征；基于所述子域特定特征和所述全局通用特征确定出域迁移特征；基于所述域迁移特征进行故障诊断，得到针对所述故障诊断任务的诊断结果。
在一种可能的实现方式中，对所述目标域数据进行子域特征提取，得到表示所述目标域中特有信息的子域特定特征，并对所述目标域数据进行全局特征提取，得到表示所述目标域与各所述源域所共有的通用信息的全局通用特征，包括：对所述目标域数据进行时间尺度上的子域特征提取，得到子域时序特征，对所述子域时序特征进行空间尺度上的子域特征提取，得到所述子域特定特征，以及对所述目标域数据进行时间尺度上的全局特征提取，得到全局时序特征，对所述全局时序特征进行空间尺度上的全局特征提取，得到所述全局特定特征。
根据本公开的另一方面，提供了一种基于多通道域适应网络的化工过程跨装置故障诊断装置，包括：获取模块，用于获取针对目标工艺流程下的待诊断设备的故障诊断任务；确定模块，用于基于所述故障诊断任务和所述待诊断设备确定出执行所述故障诊断任务所需的目标域数据，所述目标域数据包括所述待诊断设备运行在第一目标域下的多种运行数据，所述第一目标域是根据所述目标工艺流程确定出的；计算模块，用于将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果；其中，所述装置还包括训练模块，所述训练模块用于：获取目标域样本数据集和源域样本数据集，所述目标域样本数据集包括多个不同的样本设备运行在多个不同的第二目标域下的目标域样本数据，所述源域样本数据集包括各所述样本设备运行在多个不同的源域下的源域样本数据，其中，各所述目标域样本数据和各所述源域样本数据均包括多个正常运行数据和多个异常运行数据，各所述样本设备、各所述第二目标域、各所述源域均是根据化工过程中不同工艺流程确定出的；对所述源域样本数据集中的各正常运行数据和各异常运行数据分别进行标注，得到源域标注数据集，根据所述源域标注数据集和所述目标域样本数据集构建训练样本集；基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，其中，所述损失函数包括基于多项式核诱导最大均值差异构建出的特征分布差异函数。
在一种可能的实现方式中，所述多通道域适应网络包括特征提取模块和域适应模块；其中，基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，包括：利用所述特征提取模块对所述训练样本集进行处理，得到处理结果，基于所述处理结果确定出所述特征提取模块的源域损失函数值和目标域损失函数值，所述处理结果包括源域特征、目标域特征、源域分类结果、目标域分类结果；利用所述域适应模块对所述源域特征和所述目标域特征进行处理，得到所述目标域样本数据中的各异常运行数据的故障类别预测结果，基于各所述故障类别预测结果确定出所述域适应模块的关系损失函数值；利用多项式核函数和所述训练样本集确定出特征分布差异函数值；根据所述源域损失函数值、所述目标域损失函数值、所述关系损失函数值、所述特征分布差异函数值确定出当前多通道域适应网络的总损失函数值，并基于所述总损失函数值进行当前多通道域适应网络的参数更新。
在一种可能的实现方式中，所述特征提取模块包括源域分支和目标域分支；其中，利用所述特征提取模块对所述训练样本集进行处理，得到处理结果，基于所述处理结果确定出所述特征提取模块的源域损失函数值和目标域损失函数值，包括：利用源域分支对所述源域样本数据中各所述源域的数据进行特征提取，得到各所述源域的源域特征，基于各所述源域的源域特征推测出对应源域的源域分类结果，基于各所述源域分类结果和各所述源域的真实域标签确定出所述特征提取模块的源域损失函数值；利用目标域分支对所述目标域样本数据进行特征提取，得到各所述第二目标域的目标域特征，基于各所述目标域特征推测出对应第二目标域的目标域分类结果，基于各所述目标域分类结果和各所述第二目标域的真实域标签确定出所述特征提取模块的目标域损失函数值。
在一种可能的实现方式中，利用所述域适应模块对所述源域特征和所述目标域特征进行处理，得到所述目标域样本数据中的各异常运行数据的故障类别预测结果，基于各所述故障类别预测结果确定出所述域适应模块的关系损失函数值，包括：利用所述域适应模块对所述目标域特征和所述源域特征进行计算，得到域适应样本特征；基于所述域适应样本特征度和预定的故障类别确定出所述目标域样本数据的故障类别预测结果；根据所述故障类别预测结果和所述目标域样本数据的真实故障标签确定出所述域适应模块的关系损失函数值。
在一种可能的实现方式中，所述源域特征包括表示源域中特有信息的源域特定特征，所述目标域特征包括表示第二目标域中特有信息的目标域特定特征，所述域适应模块包括第一全连接层网络对和第二全连接层网络对；其中，利用多项式核函数和所述训练样本集确定出特征分布差异函数值，包括：按照所述多项式核函数的定义规则，基于所述源域样本数据确定出第一特征分布差异函数值，并基于所述第一全连接层网络对的输出结果确定出第二特征分布差异函数值，并基于所述第二全连接层网络对的输出结果确定出第三特征分布差异函数值；根据所述第一特征分布差异函数值、所述第二特征分布差异函数值、所述第三特征分布差异函数值确定出所述特征分布差异函数值。
在一种可能的实现方式中，将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果，包括：对所述目标域数据进行子域特征提取，得到表示所述第一目标域中特有信息的子域特定特征，并对所述目标域数据进行全局特征提取，得到表示所述第一目标域与各所述源域所共有的通用信息的全局通用特征；基于所述子域特定特征和所述全局通用特征确定出域迁移特征；基于所述域迁移特征进行故障诊断，得到针对所述故障诊断任务的诊断结果。
在一种可能的实现方式中，对所述目标域数据进行子域特征提取，得到表示所述目标域中特有信息的子域特定特征，并对所述目标域数据进行全局特征提取，得到表示所述目标域与各所述源域所共有的通用信息的全局通用特征，包括：对所述目标域数据进行时间尺度上的子域特征提取，得到子域时序特征，对所述子域时序特征进行空间尺度上的子域特征提取，得到所述子域特定特征，以及对所述目标域数据进行时间尺度上的全局特征提取，得到全局时序特征，对所述全局时序特征进行空间尺度上的全局特征提取，得到所述全局特定特征。
根据本公开的另一方面，提供了一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为在执行所述存储器存储的指令时，实现上述方法。
根据本公开的另一方面，提供了一种非易失性计算机可读存储介质，其上存储有计算机程序指令，其中，所述计算机程序指令被处理器执行时实现上述方法。
根据本公开的另一方面，提供了一种计算机程序产品，包括计算机可读代码，或者承载有计算机可读代码的非易失性计算机可读存储介质，当所述计算机可读代码在电子设备的处理器中运行时，所述电子设备中的处理器执行上述方法。
根据下面参考附图对示例性实施例的详细说明，本公开的其它特征及方面将变得清楚。
附图说明
包含在说明书中并且构成说明书的一部分的附图与说明书一起示出了本公开的示例性实施例、特征和方面，并且用于解释本公开的原理。
图1至图2示出根据本公开实施例提供的基于多通道域适应网络的化工过程跨装置故障诊断方法的示意图。
图3示出根据本公开实施例提供的多通道域适应网络的示意图。
图4示出根据本公开实施例提供的特征提取模块的示意图。
图5示出根据本公开实施例提供的多头注意力机制的示意图。
图6示出根据本公开实施例提供的变换器模型的示意图。
图7示出高斯核诱导最大均值差异在不同带宽参数下的变化趋势的示意图。
图8示出田纳西-伊斯曼过程的工艺流程的示意图。
图9示出根据本公开实施例提供的田纳西-伊斯曼过程在正常工况与故障工况下的运行情况的对比示意图。
图10示出根据本公开实施例提供的跨工况故障诊断混淆矩阵的示意图。
图11示出根据本公开实施例提供的不同深度迁移学习方法在田纳西-伊斯曼过程的故障诊断时间的对比结果的雷达示意图。
图12至图13示出根据本公开实施例提供的基于多通道域适应网络的化工过程跨装置故障诊断装置的框图。
具体实施方式
以下将参考附图详细说明本公开的各种示例性实施例、特征和方面。附图中相同的附图标记表示功能相同或相似的元件。尽管在附图中示出了实施例的各种方面，但是除非特别指出，不必按比例绘制附图。在这里专用的词“示例性”意为“用作例子、实施例或说明性”。这里作为“示例性”所说明的任何实施例不必解释为优于或好于其它实施例。另外，为了更好的说明本公开，在下文的具体实施方式中给出了众多的具体细节。本领域技术人员应当理解，没有某些具体细节，本公开同样可以实施。在一些实例中，对于本领域技术人员熟知的方法、手段、元件和电路未作详细描述，以便于凸显本公开的主旨。为了方便本领域技术人员理解本公开实施例提供的技术方案，下面先对技术方案实现的技术环境进行说明。
目前化工过程故障诊断方法之所以不能很好适用于多工况下的化工生产过程，主要原因在于，这些化工过程故障诊断方法主要基于深度学习，而在不同的工艺参数、质量要求、设备运行情况下，监测的过程数据分布随之变化，传统深度学习故障诊断方法建模时都假设训练数据和测试数据的分布一致，加之化工过程数据具有高维度、非线性的特性，如果直接将上述模型直接应用于多工况生产过程，则会导致方法失效。传统的方法是对有监督算法模型进行微调，但此种方法在源域和目标域数据分布差异较大时容易发生过拟合，从而过度学习了源域数据的特定分布特征，而忽略了更多能与目标域特征进行对齐的全局通用特征。
为了解决上述技术问题，本公开实施例提供了一种基于多通道域适应网络(MSDAN)的化工过程跨装置故障诊断方法，方法包括获取针对目标工艺流程下的待诊断设备的故障诊断任务；基于故障诊断任务和待诊断设备确定出执行故障诊断任务所需的目标域数据，目标域数据包括待诊断设备运行在第一目标域下的多种运行数据，第一目标域是根据目标工艺流程确定出的；将目标域数据输入至训练后的多通道域适应网络进行计算，得到针对故障诊断任务的诊断结果；其中，方法还包括多通道域适应网络的训练过程，训练过程包括以下步骤：获取目标域样本数据集和源域样本数据集，目标域样本数据集包括多个不同的样本设备运行在多个不同的第二目标域下的目标域样本数据，源域样本数据集包括各样本设备运行在多个不同的源域下的源域样本数据，其中，各目标域样本数据和各源域样本数据均包括多个正常运行数据和多个异常运行数据，各样本设备、各第二目标域、各源域均是根据化工过程中不同工艺流程确定出的；对源域样本数据集中的各正常运行数据和各异常运行数据分别进行标注，得到源域标注数据集，根据源域标注数据集和目标域样本数据集构建训练样本集；基于预设的损失函数和训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，其中，损失函数包括基于多项式核诱导最大均值差异构建出的特征分布差异函数。这样，能够实现故障类别信息的跨域迁移，在相似工艺流程中不同装置上实现高准确性、低误报率的故障诊断，具备有效的跨装置通用能力。
图1至图2示出根据本公开实施例提供的基于多通道域适应网络的化工过程跨装置故障诊断方法的示意图。图3示出根据本公开实施例提供的多通道域适应网络的示意图。图4示出根据本公开实施例提供的特征提取模块的示意图。图5示出根据本公开实施例提供的多头注意力机制的示意图。图6示出根据本公开实施例提供的变换器模型的示意图。图7示出高斯核诱导最大均值差异在不同带宽参数下的变化趋势的示意图。图8示出田纳西-伊斯曼过程的工艺流程的示意图。图9示出根据本公开实施例提供的田纳西-伊斯曼过程在正常工况与故障工况下的运行情况的对比示意图。图10示出根据本公开实施例提供的跨工况故障诊断混淆矩阵的示意图。图11示出根据本公开实施例提供的不同深度迁移学习方法在田纳西-伊斯曼过程的故障诊断时间的对比结果的雷达示意图。
现结合图1至图11对本公开实施例提供的化工过程跨装置故障诊断方法(下文简称诊断方法)进行示意性说明。本诊断方法不仅包括基于多通道域适应网络的实际故障诊断方法，还包括多通道域适应网络的训练方法。多通道域适应网络即故障诊断模型包括特征提取模块和域适应模块。特征提取模块的数量可根据实际需求设置为一个或多个。
如图1所示，本公开实施例提供的化工过程跨装置故障诊断方法可包括用于故障诊断模型的在线诊断阶段的下述步骤S101至步骤S103。通过步骤S101至步骤S103能够实现故障类别信息的跨域迁移，实现针对待诊断设备的高准确性、低误报率的故障诊断。
步骤S101、获取针对目标工艺流程下的待诊断设备的故障诊断任务。
目标工艺流程可根据化工过程中实际所关注的工艺流程确定。相应的，待诊断设备也可根据化工过程中实际所关注的工艺流程确定，数量可以为一个也可以为多个。
步骤S102、基于故障诊断任务和待诊断设备确定出执行故障诊断任务所需的目标域数据。
目标域数据包括待诊断设备运行在第一目标域下的多种运行数据，运行数据具体可根据化工过程中实际工艺流程和实际的待诊断设备确定，本公开实施例对此不做限定。
第一目标域也是根据目标工艺流程确定出的。实际应用时所用的第一目标域、训练时所涉及的第二目标域本质上都是目标域，即是指需要应用从源域中学到的知识的新的数据集合。通常目标域的数据分布与源域有所不同，而且可能没有或只有少量标注数据。其中，源域是指迁移学习中已经拥有标注数据的数据集合，通常用于训练模型，以便从中学习到有用的特征和知识。相应的，目标域数据是指需要对其进行预测或分类的数据集合，具体的，多通道域适应网络即故障诊断模型需要应用从源域中学到的知识对目标域数据、目标样本数据进行推断。多源域数据也即后文的源域样本数据集是指来自多个不同的源域的数据集合，多源域数据可以提供更多的多样性和丰富的信息，有助于提升目标域的学习效果。
步骤S103、将目标域数据输入至训练后的多通道域适应网络进行计算，得到针对故障诊断任务的诊断结果。
在一种可能的实现方式中，步骤S103可包括：对目标域数据进行子域特征提取，得到表示第一目标域中特有信息的子域特定特征，并对目标域数据进行全局特征提取，得到表示第一目标域与各源域所共有的通用信息的全局通用特征，例如可通过特征提取模块确定出子域特定特征和全局通用特征；基于子域特定特征和全局通用特征确定出域迁移特征；基于域迁移特征进行故障诊断，得到针对故障诊断任务的诊断结果，例如可基于域适应模块对子域特定特征和全局通用特征确定出的总特征进行处理以得到最终诊断结果。这样，通过分别提取目标域数据的子域特定特征和全局通用特征，能够更全面地捕捉目标域数据的特性，子域特定特征涵盖针对第一目标域中的独特信息，全局通用特征则涵盖了目标域与多个源域之间的共同信息，这种双重特征的融合能够更精确地识别第一目标域中的故障模式，从而提高故障诊断的准确性。
在一种可能的实现方式中，步骤S103中的对目标域数据进行子域特征提取，得到表示目标域中特有信息的子域特定特征，并对目标域数据进行全局特征提取，得到表示目标域与各源域所共有的通用信息的全局通用特征，可包括：对目标域数据进行时间尺度上的子域特征提取，得到子域时序特征，对子域时序特征进行空间尺度上的子域特征提取，得到子域特定特征，以及对目标域数据进行时间尺度上的全局特征提取，得到全局时序特征，对全局时序特征进行空间尺度上的全局特征提取，得到全局特定特征。其中，进行时间尺度上的子域特征提取这一过程可基于变换器模型(Transformer)实现，进行空间尺度上的全局特征提取这一过程可基于多尺度卷积神经网络(MSCNN)实现，具体见后文。这样，通过在时间尺度和空间尺度上分别对目标域数据进行子域和全局的特征提取，能够捕获到更加细致和全面的特征信息，时间尺度上的特征提取有助于理解数据在时间序列上的变化趋势和周期性，而空间尺度上的特征提取则能够揭示数据在空间分布上的规律和差异性，这种多维度的特征提取方式显著增强了诊断模型对目标域特有信息和共有信息的捕捉能力，从而提高了故障诊断的精度。
这样，通过获取化工过程中目标域数据这些实时运行数据、对目标域数据进行特征提取得到子域特定特征和全局通用特征并确定出域迁移特征、基于域迁移特征确定出诊断结果这一系列步骤能够在相似工艺多套不同装置上或在不同工况下实现高准确性、低误报率的故障诊断，全局通用特征的提取不仅有助于多通道域适应网络在目标域上的表现，还促进了知识从源域到目标域的迁移和共享，这些通用特征反映了不同域之间的共同规律和特点，为多通道域适应网络在新领域上的快速适应提供了有力支持，同时，通过结合子域特定特征和全局通用特征进行故障诊断，多通道域适应网络能够更准确地识别出目标域中的特定故障模式，提高了诊断的针对性和有效性，进而提升模型跨装置通用能力。
如图2所示，本公开实施例提供的化工过程跨装置故障诊断方法还包括多通道域适应网络的训练过程，训练过程包括用于故障诊断模型的离线建模阶段的下述步骤S201至步骤S203。通过步骤S201至步骤S203能够有效地从源域和第二目标域下的数据中提取关键特征，并利用域适应机制减小域间差异，从而提升多通道域适应网络在目标域上的故障诊断能力，这种跨域适应能力使得多通道域适应网络能够在不同目标域下保持较高的诊断精度，同时利用多项式核函数计算特征分布差异函数值，有助于量化源域和目标域特征分布之间的差异，进而指导多通道域适应网络在训练过程中逐步减小这种差异，使得多通道域适应网络不仅能够在训练集上表现良好，还能在未见过的测试集上保持较高的泛化性能。
步骤S201、获取目标域样本数据集和源域样本数据集。
目标域样本数据集包括多个不同的样本设备运行在多个不同的第二目标域下的目标域样本数据，其中，多个不同的样本设备、多个不同的第二目标域均可根据化工过程中相似或不同的工艺流程确定出。以一个样本设备A为例，可获取样本设备A在各第二目标域下的目标域样本数据，该数据可包括一种或多种运行数据。
源域样本数据集包括各样本设备运行在多个不同的源域下的源域样本数据，其中，多个不同的样本设备、多个不同的源域均可根据化工过程中相似或不同的工艺流程确定出。以一个样本设备B为例，可获取样本设备B在各源域下的源域样本数据，该数据可包括一种或多种运行数据。
各目标域样本数据和各源域样本数据均包括多个正常运行数据和多个异常运行数据，以便多通道域适应网络基于这些正常运行数据和异常运行数据进行迁移学习。
样本设备的数量和种类、第二目标域的数量、源域的数量、运行数据的种类和数量均可根据实际需求灵活设置。
步骤S202、对源域样本数据集中的各正常运行数据和各异常运行数据分别进行标注，得到源域标注数据集，根据源域标注数据集和目标域样本数据集构建训练样本集。
通过仅对源域样本数据集进行标注，有助于在利用多通道域适应网络进行实际诊断时，增强其多工况的适应性，还能够应对需要关注的目标域下故障数据较少且缺乏标签的场景。
步骤S203、基于预设的损失函数和训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络。
多通道域适应网络的损失可包括域类损失(源域损失和目标域损失)、关系损失、特征分布差异损失三部分，相应的，损失函数可包括特征提取模块的源域损失函数和目标域损失函数、域适应模块的关系损失函数、基于多项式核诱导最大均值差异(Polynomial Kernel-induced Maximum Mean Discrepancy，PK-MMD)构建出的特征分布差异函数。
可根据实际需求初始化多通道域适应网络的参数，本公开实施例对此不做限定。在训练多通道域适应网络的过程中，可基于损失函数对应的具体数值进行当前多通道域适应网络的参数更新。在一种可能的实现方式中，步骤S203可包括：利用特征提取模块对训练样本集进行处理，得到处理结果，基于处理结果确定出特征提取模块的源域损失函数值和目标域损失函数值，处理结果可包括源域特征、目标域特征、源域分类结果、目标域分类结果；利用域适应模块对源域特征和目标域特征进行处理，得到目标域样本数据中的各异常运行数据的故障类别预测结果，基于各故障类别预测结果确定出域适应模块的关系损失函数值；利用多项式核函数和训练样本集确定出特征分布差异函数值；根据源域损失函数值、目标域损失函数值、关系损失函数值、特征分布差异函数值确定出当前多通道域适应网络的总损失函数值，并基于总损失函数值进行当前多通道域适应网络的参数更新。这样，通过综合考虑源域损失函数值、目标域损失函数值、关系损失函数值和特征分布差异函数值来确定总损失函数值，多通道域适应网络能够在训练过程中全面评估故障诊断模型的性能，并基于这些评估结果进行参数更新，这种多层次的评估机制有助于提升诊断结果的可靠性和准确性。
现结合多通道域适应网络的示例结构对损失函数的计算过程进行示意性说明。在一些实施例中，如图3所示，多通道域适应网络结构包括两个主要模块，即特征提取模块和域适应模块。
本诊断方法在多通道域适应网络中设计了一种全新的特征提取模块，即Transformer-MSCNN。特征提取模块是由Transformer模型与多尺度卷积神经网络串联结合形成。例如，如图4所示，将源域样本数据中的正常运行数据(或称为正常样本)和源域样本数据中的异常运行数据(或称为带有标签信息的故障样本)作为不同通道输入进特征提取模块内，Transformer确定出的时序特征经全局通用特征提取通道和子域特定特征提取通道处理后形成了包含该源域关键信息的特征图谱，为后续的样本分类任务提供了强有力的源域知识支持，其中，全局通用特征提取通道旨在通过域自适应归纳域间的共性特征，而子域特定特征提取通道则提取域特定的判别特征便于故障分类和域标签分类。Transformer和MSCNN分别从时间尺度和空间尺度上对样本数据加以关注，以在不同维度上捕捉更加丰富的特征信息。Transformer主要关注不同变量之间的全局关系，有助于提取迁移任务中的跨域共享信息。MSCNN聚焦于数据的局部特征，补充了多通道域适应网络对不同尺度数据特征的学习能力。
在本公开实施例的特征提取模块中，也引入了注意力机制以增强多通道域适应网络对数据特征的理解能力，所使用的多头注意力机制(Multi-head Attention Mechanism)是自注意力机制的另一种变形。多头注意力机制对输入数据并行地执行多个自注意力单元操作，每个自注意力操作都可被看作一个新的子空间，其工作流程如图5所示，共分为输入数据切割、注意力权重计算、特征融合与输出三个步骤，多头注意力机制的前期计算与原有自注意力机制类似，即将原始数据序列线性变换后得到的查询(Query)、键(Key)、值(Value)向量(简称为Q、K、V向量)分别经过相应的变换矩阵进行线性变换后输入到缩放点积注意力模块(Scaled Dot-product Attention)中，不同之处在于它的点积计算需要执行h次，h为注意力头的数量。随后该机制计算向量间的注意力得分并对值做加权求和，再将所有缩放点积的结果进行拼接，经线性变换后输出即可得到多头注意力机制权重增强后的特征结果。这一机制赋予了多通道域适应网络在不同的表征子空间内学习其关联信息的能力，也是Transformer模型得以捕捉复杂变量关系的关键。例如，缩放点积注意力的计算如下：
式(1)中，hi表示第i个注意力头的输出结果；f表示缩放点积注意力函数，该函数对输入的Q、K、V向量进行点积计算得到注意力权重，然后对V向量进行加权求和以生成输出；Wi q表示Query变换矩阵，用于将输入的Q向量线性变换到子空间；表示Key变换矩阵，用于将输入的K向量线性变换到子空间；表示Value变换矩阵，用于将输入的V向量线性变换到子空间；q表示Query向量，在注意力机制中，q用于匹配键(Key)，以便计算注意力权重；k表示Key向量，k与q进行匹配，计算出注意力权重；v表示Value向量，v是最终进行加权求和得到输出结果的向量。
在一些实施例中，如图6所示，Transformer模型的主体结构由编码器和解码器组成，编码器用于处理输入序列，解码器用于生成输出序列(侧重时序特征)，两者均通过多头注意力(Multi-head Attention)机制与前馈神经网络(FFN)堆叠形成，自注意力层通过并行地学习序列中不同位置的信息来增强模型的表示能力。Transformer模型在各子层输出处都添加了残差连接，以避免训练过程的梯度消失问题。解码器的输出结果是每个输出元素的概率分布，进而分析出输入序列中各元素的位置信息和重要程度。关于超参数设置方面，Transformer在编码器和解码器中的注意力头数可均设置为3，MSCNN的卷积核可根据实际需求设置，前后分别连接全连接层整合各单元提取的特征，学习率默认为0.001，网络参数通过反向传播进行更新。
特征提取器模块的损失函数可归纳为下式(2)示出的通用表示：
式(2)中，L′表示特征提取器模块的损失函数，其中n是样本总量，x代表变量维度，y为样本真实标签，为样本分类标签。
在一些实施例中，特征提取模块可根据源域总数布置等量的分支通道，每条通道内又分成子域特定特征提取通道和全局通用特征提取通道，用来同时提取多源域数据中的跨域共同特征和各源域的自有特征，分支通道的种类可包括图3示出的源域分支和目标域分支。源域分支和目标域分支均包括对应的子域特定特征提取通道和全局通用特征提取通道，源域分支中的子域特定特征提取通道用于提取输入至该源域分支的数据的子域特征(或称自有特征)以得到对应的源域特定特征，源域分支中的全局通用特征提取通道用于提取输入至该源域分支的数据的全局特征(或称跨域共同特征)以得到对应的源域通用特征，源域特征可包括源域特定特征和源域通用特征。目标域分支中的子域特定特征提取通道用于提取输入至该目标域分支的数据的子域特征以得到对应的目标域特定特征，目标域分支中的全局通用特征提取通道用于提取输入至该目标域分支的数据的全局特征以得到对应的目标域通用特征，目标域特征可包括目标域特定特征和目标域通用特征。无论是在线诊断阶段还是离线建模阶段，从本质上来说，源域特征表示的是对应源域的源域方面特征，目标域域特征表示的是对应目标域的目标域方面特征，源域特征中的源域特定特征表示的是对应源域中特有的信息，目标域特征中的目标域特定特征表示的是对应目标域中特有的信息，具体源域和目标域根据实际情况确定。特征提取模块的分支通道数量可根据实际需求设置。
损失函数之一的特征提取模块的域类损失通过源域损失函数和目标域损失函数确定。步骤S203中的利用特征提取模块对训练样本集进行处理，得到处理结果，基于处理结果确定出特征提取模块的源域损失函数值和目标域损失函数值，可包括：利用特征提取模块中的源域分支对源域样本数据中各源域的数据进行特征提取，得到各源域的源域特征，基于各源域的源域特征推测出对应源域的源域分类结果，基于各源域分类结果和各源域的真实域标签确定出特征提取模块的源域损失函数值；利用特征提取模块中的目标域分支对目标域样本数据进行特征提取，得到各第二目标域的目标域特征，基于各目标域特征推测出对应第二目标域的目标域分类结果，基于各目标域分类结果和各第二目标域的真实域标签确定出特征提取模块的目标域损失函数值。
例如，特征提取模块的源域损失函数值可通过下式(3)确定：
式(3)中，Lds表示源域损失函数，nbs表示一次训练过程中某一特定源域所用样本总量，表示该源域的第i个样本的源域分类结果(或称属类分类结果)，表示该源域的第i个样本的真实域标签，该源域的样本属于该特定源域即该源域被正确分类时该源域被错误分类时
特征提取模块的目标域分支直接对目标域样本数据进行处理以用于测试故障分类准确性，不会对源域数据处理，源域数据具体用于训练过程中的参数调整过程，例如可通过反向梯度传播的方式调整诊断模型的参数。例如，特征提取模块的目标域损失函数值可通过下式(4)确定：
式(4)中，Ldt表示目标域损失函数，nbt表示一次训练过程中某一目标域所用样本总量，表示该目标域的第i个样本的目标域分类结果(或称属类分类结果)，表示该目标域的第i个样本的真实域标签，该目标域的样本被正确分类时该目标域被错误分类时
本诊断方法在多通道域适应网络中还设计了域适应模块。经过特征提取及筛选后，所有不适合迁移的样本的贡献度将被筛除，而关键信息则被赋予较大权重。例如，可通过下式(5)对特征提取模块输出的多通道数据特征经加权求和后形成用于域适应模块分类的特征图谱：
式(5)中，fs,t表示域适应模块计算得到的特征图谱，它表示整个特征空间的综合特征；表示第i个特征提取模块输出的特征图谱，该特征图谱是基于Transformer和MSCNN共同确定的。例如输入数据先输入至Transformer进行处理得到时序特征，再将该时序特征输入至MSCNN中进行处理得到该Transformer和该MSCNN对应的特征提取模块的输出结果，这个输出结果可包括子域特定特征和全局通用特征，在故障诊断模型的在线诊断阶段中，可基于训练后的Transformer和MSCNN确定出第一目标域下的子域特定特征和全局通用特征，从而基于子域特定特征和全局通用特征得到特征提取模块的输出结果，进而基于实际设置的特征提取模块的数量确定出用于域适应模块计算得到的特征图谱即域迁移特征。
域适应模块中最后一层全连接层与归一化指数(softmax)函数构成样本分类器，分类器可表示为下式(6)：
式(6)中，代表诊断得到的第i个故障类别标签；c表示故障类别的索引，类别数从1到C；表示预设的第i个故障类别标签，fs,t表示域迁移特征，表示特征图谱域迁移特征和预设的故障类别标签在故障类别c上的相似度评分。
损失函数之一的域适应模块的关系损失通过关系损失函数确定。步骤S203中的利用域适应模块对源域特征和目标域特征进行处理，得到目标域样本数据中的各异常运行数据的故障类别预测结果，基于各故障类别预测结果确定出域适应模块的关系损失函数值，可包括：利用域适应模块对目标域特征和源域特征进行计算，得到域适应样本特征；基于域适应样本特征度和预定的故障类别确定出目标域样本数据的故障类别预测结果；根据故障类别预测结果和目标域样本数据的真实故障标签确定出域适应模块的关系损失函数值。例如，域适应模块的关系损失函数值可通过下式(7)确定：
式(7)中，Lr表示关系损失函数，nbs表示一次训练过程中某一特定源域所用样本总量，表示诊断得到的第i个故障类别标签，表示目标域样本数据的第i个真实故障标签。
由于子域特定特征与全局通用特征相比更难以实现特征对齐，因此本诊断法方法在不同通道的多层网络间同时引入多项式核诱导最大均值差异算法，从而实现特征对齐。例如，如图3所示，可在多通道域适应网络中的三处引入PK-MMD的计算，即PK-MMD1、PK-MMD2、PK-MMD3。在一些实施例中，可在特征提取模块内，将PK-MMD1设置在子域特定特征提取通道的最后一层卷积网络上；可在包括第一全连接层网络对和第二全连接层网络对的域适应模块内，将PK-MMD2设置在第一全连接层网络对之间、将PK-MMD3设置在第二全连接层网络对之间，其中，第一全连接层网络对可基于源域样本数据进行处理，得到相应的输出结果，第二全连接层网络对同理于此，全连接层网络对的处理过程具体根据诊断模型的实际结构确定。
损失函数之一的特征分布差异函数可包括PK-MMD1、PK-MMD2、PK-MMD3这三处各自对应的损失函数，其中，PK-MMD1对应第一特征分布差异函数，PK-MMD2对应第二特征分布差异函数，PK-MMD3对应第三特征分布差异函数。特征分布差异函数是用于衡量不同源域中源域样本数据之间的分布差异。将特征分布差异函数作为损失函数之一来调整诊断模型的权重。第一特征分布差异函数、第二特征分布差异函数、第三特征分布差异函数可在诊断模型中每层权重确定后直接同步计算，以进行诊断模型的参数更新，本公开实施例对其计算顺序不做限定。
例如，步骤S203中的利用多项式核函数和训练样本集确定出特征分布差异函数值可包括：按照多项式核函数的定义规则，基于源域样本数据确定出第一特征分布差异函数值，并基于第一全连接层网络对的输出结果确定出第二特征分布差异函数值，并基于第二全连接层网络对的输出结果确定出第三特征分布差异函数值；根据第一特征分布差异函数值、第二特征分布差异函数值、第三特征分布差异函数值确定出特征分布差异函数值。第一全连接层网络对的输出结果是基于源域样本数据确定出的，第二全连接层网络对的输出结果同理于此。在本例中，第一特征分布差异函数值、第二特征分布差异函数值、第三特征分布差异函数值可同时计算得到。
整个训练过程需最小化损失函数，以输出训练后的多通道适应网络。在一些实施例中，在训练过程中，还可为域类损失、关系损失、特征分布差异损失这三部分损失预设对应的权重函数λ，由于PK-MMD在多通道域适应网络中的三处被使用，可将多通道适应网络的加权总损失函数展开表示为下式(8)：
L＝λ0Lr+λ1LPK-MMD1+λ2LPK-MMD2+λ3LPK-MMD3+λ4(Lds+Ldt)  式(8)
式(8)中，L表示总损失函数，λ0表示关系损失函数Lr对应的权重，λ1表示第一特征分布差异函数对应的权重，LPK-MMD1表示第一特征分布差异函数，λ2表示第二特征分布差异函数对应的权重，LPK-MMD2表示第二特征分布差异函数，λ3表示第三特征分布差异函数对应的权重，LPK-MMD3表示第三特征分布差异函数，λ4表示源域损失函数Lds和目标域损失函数Ldt对应的权重。通过上式(8)得到总损失值，反向传播后更新模型权重，随后循环该过程，直到式(8)定义的总损失最小化，诊断模型训练完毕。在模型测试过程中，模型权重不再改变，通过使用目标域样本数据进行测试，计算分类准确率。
现对本公开实施例使用的PK-MMD进行说明。最大均值差异(Maximum Mean Discrepancy，MMD)是一种迁移学习常用的统计距离度量，用于衡量源域与目标域数据的概率分布之间的差异。对于给定的源域和目标域其概率分布分别为X和Y，则最大均值差异定义为下式(9)：
式(9)中，φ(·)代表核函数，它能够将输入x映射至一个希尔伯特空间中。在实际应用中，由于源域与目标域的概率分布X和Y难以显式表达或任务中未知，MMD常通过样本的经验估计来近似计算，例如下式(10)：
式(10)中，其中n和m分别指源域和目标域中的样本数量，k(·)代表一个正定核函数，用于在特征空间中计算样本对的相似度。
MMD通过选择不同的核函数形成了多种变体，其中高斯核诱导最大均值差异(Gaussian Kernel-induced Maximum Mean Discrepancy，GK-MMD)最为常用，但其在应用中存在三个明显的缺点。一是GK-MMD依赖于平均距离进行计算，而忽略了高阶矩的影响，限制了该方法对可迁移特征分布差异的计算精度，从而影响迁移学习的整体质量。二是GK-MMD计算复杂度高，由于其计算复杂度与样本数量成二次方关系，即O(n2+2mn+m2)，处理大规模数据集将导致计算时内存消耗明显、计算成本较高。三是算法对于高斯核的参数设定比较敏感，高斯核性能取决于带宽参数的选择，缺乏更多参数可调节的灵活性，如果带宽参数选择不当会导致过拟合或欠拟合。如图7所示，假定两域数据集分别满足N(0,1)和N(μt,1)的高斯分布，GK-MMD的度量结果在内核宽度小幅变化时就产生了较大波动，因此基于GK-MMD的模型在分布适应过程中很难在最优参数点处收敛。
为了使本诊断方法克服上述不足，本本公开实施例提出了多项式核诱导最大均值差异用于改进不同域数据分布差异的度量方式，采用多项式核函数替代高斯核函数，不仅能将输入特征映射至更高维的空间，进而计算点积以捕捉数据的非线性关系，还能通过改变核参数直观调节算法性能。例如，可使用下式(11)示出的多项式核函数形式：
k(x,y)＝(axTy+b)c,c＝1,2,…                 式(11)
式(11)中，k(x,y)表示多项式核函数，用于计算输入向量x和y之间的核值，它将输入特征映射到高维空间，以捕捉数据的非线性关系；斜率a代表高阶矩对样本分布差异的贡献度，斜率值越大，高阶矩对分布差的影响越大；截距b为常数项且通常设置为1；c代表的多项式阶数决定了映射至特征空间的维度；k(·)代表输入向量x和y之间元素乘积的多项式。从而可得到 即PK-MMD的计算公式，该式中，xi、xj、yi、yj表示源域或目标域的特征向量，具体根据实际处理过程确定。根据二项式定理，PK-MMD的经验估计值计算结果可表示为 当c＝1时，平均距离为 当c>1时，计算值为样本对各阶中心矩距离的加权和，多项式核函数在两类样本分布下的期望值差异反映了该样本对之间的相似度PK-MMD的计算复杂度为O(c(c+3)/2+ε(n+m))，其中O(ε)代表矩阵乘法的时间成本。多项式核通过映射到更高维空间以提取数据的非线性特征，使得PK-MMD在处理复杂数据集时效果更好，其参数灵活可变的性质也为调整模型复杂度提供了机会，选择合适的核参数能够兼顾模型的度量精度和计算效率。
在本公开实施例提出了一种新的化工过程跨装置故障诊断方法，利用Transformer-MSCNN进行跨域特征提取，随后通过特征筛选后，经过线性变换转换为特征图谱，特征图谱进入域适应模块，通过共享权重的方式计算样本之间的相似关联度，通过PK-MMD对齐各域数据分布，构建损失函数、调整权重，可以很好地实现故障类别信息的跨域迁移，特别是对于各种故障都具有良好的识别能力，综合性能优秀，能够使诊断模型学习到来自不同源域的共有特征，对于提升模型跨装置通用诊断能力具有重大现实意义。本故障诊断方法通过充分提取训练样本集的多个工况下的故障数据特征，将源域特征迁移至目标域，使目标工况在可用于训练的故障样本稀缺且不包含标签信息的情况下，仍能保持高精度的故障识别效果。
本公开实施例提供的故障诊断工作流程分为离线建模和在线诊断两个阶段，将带有故障标签的源域数据投入多通道域适应网络模型进行离线训练，在线阶段激活预训练模型将目标域特征与源域特征分布差异最小化，实现故障类别信息的跨域迁移。
在一些实施例中，可通过以下离线建模过程实现多通道域适应网络即故障诊断模型的训练。首先，根据实际需求设置多通道域适应网络中特征提取模块对应的神经网络的结构参数，随机初始化其连接参数，其中，特征提取模块的结构参数可包括输入层单元数、隐层单元数、每批数据量的大小、使用训练集中的全部样本训练一次的周期大小、避免过拟合的随机失活值，连接参数可包括权重、偏置、Transformer架构和CNN架构的超参数。接着，将源域样本数据和目标域样本数据(源域的正常样本、源域的故障样本、第二目标域的正常样本、第二目标域的故障样本)作为训练数据以不同的通道输入至多通道域适应网络中特征提取模块，特征提取模块获取训练数据后，从位置空间和时间尺度两个方面加以关注以捕捉特征信息，经过特征提取及筛选后，所有不适合迁移的样本贡献度被筛除，对关键信息给予更高的权重，特征提取模块输出的多通道数据特征经过线性变换，折合成用于域适应模块分类的特征图谱。然后，在域适应模块中，特征图谱之间通过共享权重的方式计算相似关联度，通过损失函数进行约束，实现不同工况特征的跨域迁移，其中，可使用最大均值差异(MMD)的衍生方法即PK-MMD进行损失函数的构建，PK-MMD可设置在特征提取模块的最后一层卷积网络、域适应模块中的两对全连接层网络之间这三处，从而可以较好度量源域样本数据和目标域样本数据的分布差异，域适应模块的最后一层全连接层与softmax函数构成样本分类器，对目标域样本数据进行分类，使用不同工况下采集的训练数据训练模型，通过学习训练数据中的数据特征，得到多通道域适应网络的最优连接参数。接着，将验证集的监测数据输入已完成训练的多通道域适应网络，计算混淆矩阵、故障诊断时间(Fault Diagnosis Time，FDT)、诊断准确率，对多通道域适应网络进行评估，以得到满足预设的评估条件的多通道域适应网络。
在一些实施例中，可通过以下在线监控步骤过程实现化工过程跨装置故障检测任务。首先，获取化工过程中待诊断装置的实时运行数据即目标域数据并进行标准化得到输入数据。然后，将输入数据输入特征提取模块进行计算，得到特征图谱，在特征提取模块中，可利用子域特定特征提取通道提取表示当前目标域的子域特定特征，可利用全局通用特征提取通道提取表示多通道域适应网络训练时所用的源域的通用特征，其中，可通过Transformer和MSCNN分别从时间尺度和位置空间尺度这两个视角对输入数据的各部分加以关注。最后，将特征图谱输入域适应模块进行计算，得到最终的诊断结果，诊断结果可指示待诊断装置的故障情况。
这样，本公开实施例提出的新的化工过程跨装置故障诊断方法利用Transformer和MSCNN对各域样本数据进行跨域特征提取，随后通过特征筛选后，多通道特征经过线性变换，转换为特征图谱，特征图谱进入域适应模块，通过共享权重的方式计算样本数据之间的相似关联度，通过PK-MMD对齐各域数据分布，构建损失函数、调整权重，能够很好地实现故障类别信息的跨域迁移，特别是对于各种故障都具有良好的识别能力，使多通道域适应网络学习到来自不同源域的共有特征，综合性能优秀，对于提升模型跨装置通用诊断能力具有重大现实意义。
为了验证本公开实施例所提出的方法的可行性与有效性，通过在田纳西-伊士曼过程(Tennessee Eastman Process，TEP)中的实验验证本方法的有效性，并与经典的故障诊断方法：堆叠自编码器深度迁移网络(Deep Transfer Network Composed of Stacked Auto-Encoder，DTN)、卷积神经网络辅助分类的深度适配网络(Deep Adaptation Network with CNN，DAN-CNN)、联合适配网络(Join Adaptation Network with CNN，JAN-CNN)、动态对抗跨域适应网络模型(Dynamic Adversarial Adaptation Network，DAAN)进行了性能对比。
田纳西-伊斯曼过程是故障诊断领域经典的工业过程模拟数据集，它通过模拟真实的化工生产过程并在控制环境下引入多种故障工况成为了多变量过程监控方法常用的基准仿真模型。该过程主要涉及的化学反应如下：A(g)+C(g)+D(g)→G(l)、A(g)+C(g)+E(g)→H(l)、A(g)+E(g)→F(l)、3D(g)→2F(l)，该不可逆放热化学反应过程共包含四种气体原料、两种液态产物和一种副产物，反应环境由一种惰性气体保护，其中，四种气体原料为A(g)、C(g)、D(g)、E(g)，两种液态产物为G(l)、H(l)，一种副产物为F(l)。TE过程涵盖五个关键的工艺单元，包括反应器、冷凝器、循环压缩机、气液分离器与汽提塔。原始版本的TE数据集共包含12个操作变量、19个组分变量与22个过程测量变量，它能够模拟20种不同类型的故障工况用于测试故障诊断方法的分类性能。随后根据反应产率和产品组成比例设置了除基本运行工况之外的六种新稳态工况，并为TE过程增加了19个控制策略，通常被用于化工过程多工况故障诊断和过程控制优化研究。后来增添了8个过程测量变量和24个组分变量。本示例文针对TE过程的研究使用的TE仿真模型的工艺流程图如图8所示，如图9所示，可获取TE过程在正常工况和故障工况下变量的波动趋势。
本示例中采用TE模拟的基本运行工况开展实验，数采周期设定为3分钟。在对该反应过程所有监测变量分析时发现，新模型的组分变量变化趋势很小且数采频次较低，因此仅选择12个操作变量和30个连续测量变量用于建模，将所有变量按序号标注在图8中，以便于更直观地展示变量的测量位置与潜在的耦合关系。由于组分变量的采样频率较低，本实例只选择操纵变量和连续测量变量来建立数据集，总共有42个变量，由于最新TEP模型的控制系统可以有效地控制故障15、16、23、28，因此不考虑这4种类型的扰动(即表1不包括扰动序号15、16、23、28对应的扰动信息)。本示例研究的扰动如下表1所示。表1示出了TEP数据集中的各种扰动介绍。
表1 TEP数据集中的各种扰动介绍

继续采用TE过程作为研究案例对方法的跨工况迁移故障诊断效果进行验证。实验中共有5种工况的TE过程模拟数据被收集使用。迁移学习实验选择一种工况的标记数据作为训练集，用于诊断其他无标签信息工况的运行状态。
表2示出了MSDAN对TE过程跨工况目标域无监督故障诊断的准确率，根据表中结果进一步计算MSDAN方法在所有实验中的平均诊断率达到了95.7％。至表示五种源域，至表示五种目标域。观察表2的结果，可以发现MSDAN在绝大多数工况两两迁移相互诊断的任务中都表现良好，每项迁移实验的故障诊断准确率都超过了90％，说明模型在跨工况复杂场景中保持着较强的鲁棒性。
表2 MSDAN对TE过程跨工况目标域无监督故障诊断的准确率
图10展示了MSDAN以工况1为训练集、工况4为测试集的故障诊断混淆矩阵，仅有故障9和故障15这两类难以诊断的故障结果尚未达到90％，从原始数据来看，故障9仅引起了变量24所代表的D进料温度随机变化，故障15所代表的冷凝器冷却水阀门粘滞未引起所测量变量的剧烈波动，因此两种故障的多数变量特征与正常工况相似，实现精确诊断的难度较大。不过，实验结果同样证明其余18种故障均被该深度迁移网络精确地识别，整体诊断精度令人满意。
此外，本示例定义了一项新的故障诊断方法性能指标即FDT。故障诊断时间被定义为从变量扰动引入系统并产生故障数据特征起至该类故障被连续三次正确识别所经历的总时长。在实际化工生产中工艺流程庞大复杂，面对过程监控系统中的大量数据和控制信号，操作工程师往往在系统连续多次发出同类故障报警分析后才会关注该报警信息，并思考采取何种调控手段处置这一异常事件。同时，连续三次正确分类也代表着模型对该类故障的诊断效果趋于稳定，使操作人员更有信心依据模型的输出结果采取行动。下表3示出了不同深度迁移学习方法在TE过程的故障诊断时间(min)结果对比结果，其展现了不同深度迁移学习方法在针对TE过程由工况1训练迁移至工况4使用的故障诊断时间对比，结果显示MSDAN的平均诊断用时最短，且在多数故障类型上都能从故障一开始发生就做出准确判断。
表3不同深度迁移学习方法在TE过程的故障诊断时间(min)结果对比
为了使故障诊断时间指标更为直观，以每种故障耗时最长的故障诊断时间为基准，将该类故障的其他诊断用时做标准化处理，绘制成图11所示的雷达图，图11中闭合曲线越靠近圆心则代表诊断速度越快，可以明显看出MSDAN的故障诊断最为高效，且没有出现在某类故障上诊断用时明显长于其他方法的情况，这说明MSDAN模型在确保诊断精度的同时具有更早稳定识别出故障的能力。
鉴于MSDAN利用多通道对源域特征和目标域特征分别提取造就的模型分类性能，本示例进一步扩展MSDAN的模型结构，利用两两迁移实验中未使用的其他工况数据丰富源域的训练集样本，在网络结构中增设更多条源域特征提取与域适应通道，评估模型对多个源域数据的特征学习能力。表4示出了不同深度迁移学习模型在多源域跨工况故障诊断任务中的准确率结果，以表4中(a)中94.5％为例，94.5％表示用源域(0+1)里的数据训练诊断模型后，迁移到目标域2时的诊断准确率，结果证明当模型利用更多源域数据训练时，整体的分类性能有增强的趋势，MSDAN在多数情况下能够充分学习多源域所代表的不同工况的故障特征，提升了对目标工况的故障诊断精度，并在所有方法中表现最好。总体而言，MSDAN在模型设计层面也具备较强的灵活性，当实验包含更多特征分布相似的不同域数据时，MSDAN可以扩展成利用多源域数据学习更多有效特征迁移至目标域任务的增强版模型，从而为构建通用性更强的故障诊断模型提供了设计思路。
表4不同深度迁移学习模型在多源域跨工况故障诊断任务中的准确率结果
本公开实施例提出基于多通道域适应网络(MSDAN)的化工过程跨装置故障诊断方法，不仅提出全新的基于Transformer-MSCNN构建的特征提取网络，采取改良的多项式核诱导最大均值差异(PK-MMD)作为衡量源域和目标域数据概率分布之间的差异量度；还提出训练时另源域数据和目标域数据进入不同通道，并行作为MSDAN的输入，同时源域的正常与故障样本也被分类标注投入特征提取器的不同通道，分别提取出域间共性特征和特定域判别特征，用于故障分类和域标签分类；并且，在线诊断阶段将目标域特征和源域特征分布差异最小化，实现故障类别信息的跨域迁移。本公开实施例提出的化工过程跨装置故障诊断方法能够显著减轻诊断模型对标注信息的依赖，降低对人工标注数据的需求量，能够充分学习多源域所代表的不同工况的故障特征，提升对目标域所代表的目标工况的故障诊断精度，为后续跨装置工业案例的故障诊断研究提供了基础。
图12示出根据本公开实施例提供的基于多通道域适应网络的化工过程跨装置故障诊断装置的框图。如图12所示，化工过程跨装置100包括获取模块101、确定模块102、计算模块103、训练模块104。获取模块101，用于获取针对目标工艺流程下的待诊断设备的故障诊断任务。确定模块102，用于基于所述故障诊断任务和所述待诊断设备确定出执行所述故障诊断任务所需的目标域数据，所述目标域数据包括所述待诊断设备运行在第一目标域下的多种运行数据，所述第一目标域是根据所述目标工艺流程确定出的。计算模块103，用于将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果。训练模块104，用于：获取目标域样本数据集和源域样本数据集，所述目标域样本数据集包括多个不同的样本设备运行在多个不同的第二目标域下的目标域样本数据，所述源域样本数据集包括各所述样本设备运行在多个不同的源域下的源域样本数据，其中，各所述目标域样本数据和各所述源域样本数据均包括多个正常运行数据和多个异常运行数据，各所述样本设备、各所述第二目标域、各所述源域均是根据化工过程中不同工艺流程确定出的；对所述源域样本数据集中的各正常运行数据和各异常运行数据分别进行标注，得到源域标注数据集，根据所述源域标注数据集和所述目标域样本数据集构建训练样本集；基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，其中，所述损失函数包括基于多项式核诱导最大均值差异构建出的特征分布差异函数。
在一种可能的实现方式中，所述多通道域适应网络包括特征提取模块和域适应模块；其中，基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，包括：利用所述特征提取模块对所述训练样本集进行处理，得到处理结果，基于所述处理结果确定出所述特征提取模块的源域损失函数值和目标域损失函数值，所述处理结果包括源域特征、目标域特征、源域分类结果、目标域分类结果；利用所述域适应模块对所述源域特征和所述目标域特征进行处理，得到所述目标域样本数据中的各异常运行数据的故障类别预测结果，基于各所述故障类别预测结果确定出所述域适应模块的关系损失函数值；利用多项式核函数和所述训练样本集确定出特征分布差异函数值；根据所述源域损失函数值、所述目标域损失函数值、所述关系损失函数值、所述特征分布差异函数值确定出当前多通道域适应网络的总损失函数值，并基于所述总损失函数值进行当前多通道域适应网络的参数更新。
在一种可能的实现方式中，所述特征提取模块包括源域分支和目标域分支；其中，利用所述特征提取模块对所述训练样本集进行处理，得到处理结果，基于所述处理结果确定出所述特征提取模块的源域损失函数值和目标域损失函数值，包括：利用源域分支对所述源域样本数据中各所述源域的数据进行特征提取，得到各所述源域的源域特征，基于各所述源域的源域特征推测出对应源域的源域分类结果，基于各所述源域分类结果和各所述源域的真实域标签确定出所述特征提取模块的源域损失函数值；利用目标域分支对所述目标域样本数据进行特征提取，得到各所述第二目标域的目标域特征，基于各所述目标域特征推测出对应第二目标域的目标域分类结果，基于各所述目标域分类结果和各所述第二目标域的真实域标签确定出所述特征提取模块的目标域损失函数值。
在一种可能的实现方式中，利用所述域适应模块对所述源域特征和所述目标域特征进行处理，得到所述目标域样本数据中的各异常运行数据的故障类别预测结果，基于各所述故障类别预测结果确定出所述域适应模块的关系损失函数值，包括：利用所述域适应模块对所述目标域特征和所述源域特征进行计算，得到域适应样本特征；基于所述域适应样本特征度和预定的故障类别确定出所述目标域样本数据的故障类别预测结果；根据所述故障类别预测结果和所述目标域样本数据的真实故障标签确定出所述域适应模块的关系损失函数值。
在一种可能的实现方式中，所述源域特征包括表示源域中特有信息的源域特定特征，所述目标域特征包括表示第二目标域中特有信息的目标域特定特征，所述域适应模块包括第一全连接层网络对和第二全连接层网络对；其中，利用多项式核函数和所述训练样本集确定出特征分布差异函数值，包括：按照所述多项式核函数的定义规则，基于所述源域样本数据确定出第一特征分布差异函数值，并基于所述第一全连接层网络对的输出结果确定出第二特征分布差异函数值，并基于所述第二全连接层网络对的输出结果确定出第三特征分布差异函数值；根据所述第一特征分布差异函数值、所述第二特征分布差异函数值、所述第三特征分布差异函数值确定出所述特征分布差异函数值。
在一种可能的实现方式中，将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果，包括：对所述目标域数据进行子域特征提取，得到表示所述第一目标域中特有信息的子域特定特征，并对所述目标域数据进行全局特征提取，得到表示所述第一目标域与各所述源域所共有的通用信息的全局通用特征；基于所述子域特定特征和所述全局通用特征确定出域迁移特征；基于所述域迁移特征进行故障诊断，得到针对所述故障诊断任务的诊断结果。
在一种可能的实现方式中，对所述目标域数据进行子域特征提取，得到表示所述目标域中特有信息的子域特定特征，并对所述目标域数据进行全局特征提取，得到表示所述目标域与各所述源域所共有的通用信息的全局通用特征，包括：对所述目标域数据进行时间尺度上的子域特征提取，得到子域时序特征，对所述子域时序特征进行空间尺度上的子域特征提取，得到所述子域特定特征，以及对所述目标域数据进行时间尺度上的全局特征提取，得到全局时序特征，对所述全局时序特征进行空间尺度上的全局特征提取，得到所述全局特定特征。
在一些实施例中，本公开实施例提供的装置具有的功能或包含的模块可以用于执行上文方法实施例描述的方法，其具体实现可以参照上文方法实施例的描述，为了简洁，这里不再赘述。
本公开实施例还提出一种计算机可读存储介质，其上存储有计算机程序指令，所述计算机程序指令被处理器执行时实现上述方法。计算机可读存储介质可以是易失性或非易失性计算机可读存储介质。
本公开实施例还提出一种电子设备，包括：处理器；用于存储处理器可执行指令的存储器；其中，所述处理器被配置为在执行所述存储器存储的指令时，实现上述方法。
本公开实施例还提供了一种计算机程序产品，包括计算机可读代码，或者承载有计算机可读代码的非易失性计算机可读存储介质，当所述计算机可读代码在电子设备的处理器中运行时，所述电子设备中的处理器执行上述方法。
图13示出根据本公开实施例提供的基于多通道域适应网络的化工过程跨装置故障诊断装置的框图。例如，装置1900可以被提供为一服务器或终端设备。参照图13，装置1900包括处理组件1922，其进一步包括一个或多个处理器，以及由存储器1932所代表的存储器资源，用于存储可由处理组件1922的执行的指令，例如应用程序。存储器1932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1922被配置为执行指令，以执行上述方法。
装置1900还可以包括一个电源组件1926被配置为执行装置1900的电源管理，一个有线或无线网络接口1950被配置为将装置1900连接到网络，和一个输入输出接口1958(I/O接口)。装置1900可以操作基于存储在存储器1932的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM，LinuxTM，FreeBSDTM或类似。
在示例性实施例中，还提供了一种非易失性计算机可读存储介质，例如包括计算机程序指令的存储器1932，上述计算机程序指令可由装置1900的处理组件1922执行以完成上述方法。本公开可以是系统、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本公开的各个方面的计算机可读程序指令。计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。用于执行本公开操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本公开的各个方面。
这里参照根据本公开实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
以上已经描述了本公开的各实施例，上述说明是示例性的，并非穷尽性的，并且也不限于所披露的各实施例。在不偏离所说明的各实施例的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择，旨在最好地解释各实施例的原理、实际应用或对市场中的技术改进，或者使本技术领域的其它普通技术人员能理解本文披露的各实施例。

Claims (10)

  1. 一种基于多通道域适应网络的化工过程跨装置故障诊断方法，其特征在于，所述方法包括：
    获取针对目标工艺流程下的待诊断设备的故障诊断任务；
    基于所述故障诊断任务和所述待诊断设备确定出执行所述故障诊断任务所需的目标域数据，所述目标域数据包括所述待诊断设备运行在第一目标域下的多种运行数据，所述第一目标域是根据所述目标工艺流程确定出的；
    将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果；
    其中，所述方法还包括所述多通道域适应网络的训练过程，所述训练过程包括以下步骤：
    获取目标域样本数据集和源域样本数据集，所述目标域样本数据集包括多个不同的样本设备运行在多个不同的第二目标域下的目标域样本数据，所述源域样本数据集包括各所述样本设备运行在多个不同的源域下的源域样本数据，其中，各所述目标域样本数据和各所述源域样本数据均包括多个正常运行数据和多个异常运行数据，各所述样本设备、各所述第二目标域、各所述源域均是根据化工过程中不同工艺流程确定出的；
    对所述源域样本数据集中的各正常运行数据和各异常运行数据分别进行标注，得到源域标注数据集，根据所述源域标注数据集和所述目标域样本数据集构建训练样本集；
    基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，其中，所述损失函数包括基于多项式核诱导最大均值差异构建出的特征分布差异函数。
  2. 根据权利要求1所述的方法，其特征在于，所述多通道域适应网络包括特征提取模块和域适应模块；
    其中，基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，包括：
    利用所述特征提取模块对所述训练样本集进行处理，得到处理结果，基于所述处理结果确定出所述特征提取模块的源域损失函数值和目标域损失函数值，所述处理结果包括源域特征、目标域特征、源域分类结果、目标域分类结果；
    利用所述域适应模块对所述源域特征和所述目标域特征进行处理，得到所述目标域样本数据中的各异常运行数据的故障类别预测结果，基于各所述故障类别预测结果确定出所述域适应模块的关系损失函数值；
    利用多项式核函数和所述训练样本集确定出特征分布差异函数值；
    根据所述源域损失函数值、所述目标域损失函数值、所述关系损失函数值、所述特征分布差异函数值确定出当前多通道域适应网络的总损失函数值，并基于所述总损失函数值进行当前多通道域适应网络的参数更新。
  3. 根据权利要求2所述的方法，其特征在于，所述特征提取模块包括源域分支和目标域分支；
    其中，利用所述特征提取模块对所述训练样本集进行处理，得到处理结果，基于所述处理结果确定出所述特征提取模块的源域损失函数值和目标域损失函数值，包括：
    利用源域分支对所述源域样本数据中各所述源域的数据进行特征提取，得到各所述源域的源域特征，基于各所述源域的源域特征推测出对应源域的源域分类结果，基于各所述源域分类结果和各所述源域的真实域标签确定出所述特征提取模块的源域损失函数值；
    利用目标域分支对所述目标域样本数据进行特征提取，得到各所述第二目标域的目标域特征，基于各所述目标域特征推测出对应第二目标域的目标域分类结果，基于各所述目标域分类结果和各所述第二目标域的真实域标签确定出所述特征提取模块的目标域损失函数值。
  4. 根据权利要求2所述的方法，其特征在于，利用所述域适应模块对所述源域特征和所述目标域特征进行处理，得到所述目标域样本数据中的各异常运行数据的故障类别预测结果，基于各所述故障类别预测结果确定出所述域适应模块的关系损失函数值，包括：
    利用所述域适应模块对所述目标域特征和所述源域特征进行计算，得到域适应样本特征；
    基于所述域适应样本特征度和预定的故障类别确定出所述目标域样本数据的故障类别预测结果；
    根据所述故障类别预测结果和所述目标域样本数据的真实故障标签确定出所述域适应模块的关系损失函数值。
  5. 根据权利要求2所述的方法，其特征在于，所述源域特征包括表示源域中特有信息的源域特定特征，所述目标域特征包括表示第二目标域中特有信息的目标域特定特征，所述域适应模块包括第一全连接层网络对和第二全连接层网络对；
    其中，利用多项式核函数和所述训练样本集确定出特征分布差异函数值，包括：
    按照所述多项式核函数的定义规则，基于所述源域样本数据确定出第一特征分布差异函数值，并基于所述第一全连接层网络对的输出结果确定出第二特征分布差异函数值，并基于所述第二全连接层网络对的输出结果确定出第三特征分布差异函数值；
    根据所述第一特征分布差异函数值、所述第二特征分布差异函数值、所述第三特征分布差异函数值确定出所述特征分布差异函数值。
  6. 根据权利要求1至5中任意一项所述的方法，其特征在于，将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果，包括：
    对所述目标域数据进行子域特征提取，得到表示所述第一目标域中特有信息的子域特定特征，并对所述目标域数据进行全局特征提取，得到表示所述第一目标域与各所述源域所共有的通用信息的全局通用特征；
    基于所述子域特定特征和所述全局通用特征确定出域迁移特征；
    基于所述域迁移特征进行故障诊断，得到针对所述故障诊断任务的诊断结果。
  7. 根据权利要求6所述的方法，其特征在于，对所述目标域数据进行子域特征提取，得到表示所述目标域中特有信息的子域特定特征，并对所述目标域数据进行全局特征提取，得到表示所述目标域与各所述源域所共有的通用信息的全局通用特征，包括：
    对所述目标域数据进行时间尺度上的子域特征提取，得到子域时序特征，对所述子域时序特征进行空间尺度上的子域特征提取，得到所述子域特定特征，以及
    对所述目标域数据进行时间尺度上的全局特征提取，得到全局时序特征，对所述全局时序特征进行空间尺度上的全局特征提取，得到所述全局特定特征。
  8. 一种基于多通道域适应网络的化工过程跨装置故障诊断装置，其特征在于，包括：
    获取模块，用于获取针对目标工艺流程下的待诊断设备的故障诊断任务；
    确定模块，用于基于所述故障诊断任务和所述待诊断设备确定出执行所述故障诊断任务所需的目标域数据，所述目标域数据包括所述待诊断设备运行在第一目标域下的多种运行数据，所述第一目标域是根据所述目标工艺流程确定出的；
    计算模块，用于将所述目标域数据输入至训练后的多通道域适应网络进行计算，得到针对所述故障诊断任务的诊断结果；
    其中，所述装置还包括训练模块，所述训练模块用于：
    获取目标域样本数据集和源域样本数据集，所述目标域样本数据集包括多个不同的样本设备运行在多个不同的第二目标域下的目标域样本数据，所述源域样本数据集包括各所述样本设备运行在多个不同的源域下的源域样本数据，其中，各所述目标域样本数据和各所述源域样本数据均包括多个正常运行数据和多个异常运行数据，各所述样本设备、各所述第二目标域、各所述源域均是根据化工过程中不同工艺流程确定出的；
    对所述源域样本数据集中的各正常运行数据和各异常运行数据分别进行标注，得到源域标注数据集，根据所述源域标注数据集和所述目标域样本数据集构建训练样本集；
    基于预设的损失函数和所述训练样本集对初始化后的多通道域适应网络进行训练，得到训练后的多通道域适应网络，其中，所述损失函数包括基于多项式核诱导最大均值差异构建出的特征分布差异函数。
  9. 一种电子设备，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为在执行所述存储器存储的指令时，实现权利要求1至7中任意一项所述的方法。
  10. 一种非易失性计算机可读存储介质，其上存储有计算机程序指令，其特征在于，所述计算机程序指令被处理器执行时实现权利要求1至7中任意一项所述的方法。
PCT/CN2025/108112 2024-07-12 2025-07-11 基于多通道域适应网络的化工过程跨装置故障诊断方法及装置 Pending WO2026012467A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410937242.7 2024-07-12
CN202410937242.7A CN118898016A (zh) 2024-07-12 2024-07-12 基于多通道域适应网络的化工过程跨装置故障诊断方法及装置

Publications (1)

Publication Number Publication Date
WO2026012467A1 true WO2026012467A1 (zh) 2026-01-15

Family

ID=93262404

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/108112 Pending WO2026012467A1 (zh) 2024-07-12 2025-07-11 基于多通道域适应网络的化工过程跨装置故障诊断方法及装置

Country Status (2)

Country Link
CN (1) CN118898016A (zh)
WO (1) WO2026012467A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118898016A (zh) * 2024-07-12 2024-11-05 清华大学 基于多通道域适应网络的化工过程跨装置故障诊断方法及装置
CN119691579A (zh) * 2025-02-25 2025-03-25 北京弥天科技有限公司 冷热轧主机故障预测方法
CN119881542B (zh) * 2025-03-25 2025-07-04 内蒙古电力(集团)有限责任公司包头供电分公司 基于混合传感的配电网光纤复合故障智能定位与诊断方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112183581A (zh) * 2020-09-07 2021-01-05 华南理工大学 基于自适应迁移神经网络的半监督机械故障诊断方法
CN115563536A (zh) * 2022-09-28 2023-01-03 北京工业大学 基于子域自适应的滚动轴承故障诊断方法
US20230168150A1 (en) * 2020-12-31 2023-06-01 Soochow University Dynamic joint distribution alignment network-based bearing fault diagnosis method under variable working conditions
CN116401603A (zh) * 2023-04-26 2023-07-07 哈尔滨工程大学 一种基于迁移学习的多模态轴承故障智能诊断方法
CN116878885A (zh) * 2023-09-04 2023-10-13 佛山科学技术学院 一种基于自适应联合域适应网络的轴承故障诊断方法
CN118898016A (zh) * 2024-07-12 2024-11-05 清华大学 基于多通道域适应网络的化工过程跨装置故障诊断方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112183581A (zh) * 2020-09-07 2021-01-05 华南理工大学 基于自适应迁移神经网络的半监督机械故障诊断方法
US20230168150A1 (en) * 2020-12-31 2023-06-01 Soochow University Dynamic joint distribution alignment network-based bearing fault diagnosis method under variable working conditions
CN115563536A (zh) * 2022-09-28 2023-01-03 北京工业大学 基于子域自适应的滚动轴承故障诊断方法
CN116401603A (zh) * 2023-04-26 2023-07-07 哈尔滨工程大学 一种基于迁移学习的多模态轴承故障智能诊断方法
CN116878885A (zh) * 2023-09-04 2023-10-13 佛山科学技术学院 一种基于自适应联合域适应网络的轴承故障诊断方法
CN118898016A (zh) * 2024-07-12 2024-11-05 清华大学 基于多通道域适应网络的化工过程跨装置故障诊断方法及装置

Also Published As

Publication number Publication date
CN118898016A (zh) 2024-11-05

Similar Documents

Publication Publication Date Title
CN112639834B (zh) 用于数据分析的计算机实现的方法、计算机程序产品以及系统
US12001949B2 (en) Computer-implemented method, computer program product and system for data analysis
US20210056430A1 (en) Intelligent time-series analytic engine
CN112200104B (zh) 一种基于增强主成分分析新型贝叶斯框架的化工故障诊断方法
CN114970715B (zh) 小样本及不平衡数据约束下的变工况故障诊断方法及系统
CN109491338B (zh) 一种基于稀疏gmm的多模过程质量相关的故障诊断方法
CN106843195B (zh) 基于自适应集成半监督费舍尔判别的故障分类方法
CN118898016A (zh) 基于多通道域适应网络的化工过程跨装置故障诊断方法及装置
CN116538127B (zh) 轴流风机及其控制系统
EP4517585A1 (en) Long duration structured video action segmentation
Yang et al. A semi-supervised feature contrast convolutional neural network for processes fault diagnosis
Zhao et al. Make gating fairer: Fault attribute-driven bias calibration for generalized zero-shot industrial fault diagnosis
Cheng et al. Diagnosing the variance shifts signal in multivariate process control using ensemble classifiers
CN111401440B (zh) 目标分类识别方法、装置、计算机设备及存储介质
Ijaz et al. A Hybrid LATAM and Few-Shot Learning Framework for Fault Diagnosis in Wireless Sensor Networks
Tian et al. Cross-task fault diagnosis based on deep domain adaptation with local feature learning
CN114021654A (zh) 铝电解槽过热度识别方法、系统、设备及介质
CN115169458A (zh) 基于主动学习的自适应故障诊断方法、装置及相关介质
CN116994041B (zh) 一种基于滑窗处理与注意力机制的故障诊断方法及装置
Najafi et al. Real-Time Fault Diagnosis: A Transformer-Based Approach
CN105740815A (zh) 一种基于深度递归分层条件随机场的人体行为识别方法
Song et al. Exploring information-theoretic metrics associated with neural collapse in supervised training
Zhang et al. Cross‐Domain State‐of‐Charge Estimation of Li‐Ion Batteries Based on Source Domain Selection and Attention Mechanism
CN116975304A (zh) 知识图谱纠错方法、装置、电子设备及计算机程序产品
Zhao et al. Addressing Domain Shift via Knowledge Space Sharing for Generalized Zero-Shot Industrial Fault Diagnosis

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25836376

Country of ref document: EP

Kind code of ref document: A1