Complex electromechanical system anomaly detection method and device based on domain adaptive causal decoupling network

Abstract

The invention relates to the technical field of anomaly detection of electromechanical systems, in particular to a complex electromechanical system anomaly detection method and device based on a domain adaptive causal decoupling network. The method comprises the steps that a training data set and causal information of the electromechanical system are acquired, the training data set comprises system monitoring data and corresponding system fault label data, and the causal information is used for indicating the action relation among multiple components of the electromechanical system; according to the training data set and the causal information, an anomaly detection model based on a domain self-adaptive causal decoupling network is obtained through training, the domain self-adaptive causal decoupling network is used for indicating the corresponding relation between the system monitoring data and the component-level health state representation, and the anomaly detection model is used for conducting anomaly detection on the electromechanical system. According to the embodiment of the invention, the domain self-adaptive anomaly detection model is obtained through training by combining domain self-adaptive and causal decoupling technologies, so that the model can adapt to a changing system operation environment.

Description

Technical Field

[0001] The present disclosure relates to the technical field of abnormality detection of electromechanical systems, and in particular to a method and device for abnormality detection of complex electromechanical systems based on a domain adaptive causal decoupling network. Background Art

[0002] Anomaly detection, as a key technology, aims to identify potential system failures and plays a vital role in enhancing the reliability and safety of industrial systems. With the deepening of digital transformation in the industrial field, massive condition monitoring data provides rich materials for data-driven anomaly detection methods.

[0003] Although traditional supervised learning techniques, such as Support Vector Machine (SVM), Artificial Neural Network (ANN) and Convolutional Neural Network (CNN), have demonstrated their excellent performance in many fields, most of these methods are based on a key assumption: the training data and real-time monitoring data should follow the principle of independent and identically distributed (IID). However, in the ever-changing actual industrial environment, this idealized assumption is often difficult to achieve. Therefore, ensuring that the anomaly detection model can still maintain its high performance under dynamically changing operating conditions has become a major challenge in the field of anomaly detection in complex systems. Summary of the invention

[0004] In view of this, the present disclosure proposes a complex electromechanical system anomaly detection method and device based on a domain adaptive causal decoupling network.

[0005] According to one aspect of the present disclosure, a complex electromechanical system anomaly detection method based on a domain adaptive causal decoupling network is provided, the method comprising:

[0006] Acquire a training data set and causal information of the electromechanical system, wherein the training data set includes system monitoring data and corresponding system fault label data, wherein the system monitoring data includes a plurality of variables related to the health state of the electromechanical system, the system fault label data is used to indicate whether the electromechanical system is in a fault state, and the causal information is used to indicate the functional relationship between a plurality of components of the electromechanical system;

[0007] According to the training data set and the causal information, an anomaly detection model based on a domain adaptive causal decoupling network is trained. The domain adaptive causal decoupling network is used to indicate the correspondence between the system monitoring data and the component-level health status representation. The component-level health status representation is used to indicate the health status of each of the multiple components of the electromechanical system. The anomaly detection model is used to perform anomaly detection on the electromechanical system.

[0008] In one possible implementation, the types of the multiple variables include at least one of system monitoring parameters, system operating condition variables and system operating modes, the system monitoring parameters include variables collected by a data collection device set at a specified position of the electromechanical system, the system operating condition variables include external condition variables and / or environmental variables of the electromechanical system, and the system operating mode is the operating mode adopted by the electromechanical system when implementing its functions.

[0009] In another possible implementation, the training, according to the training data set and the causal information, to obtain an anomaly detection model based on a domain adaptive causal decoupling network includes:

[0010] According to the training data set and the causal information, training is performed to obtain the domain adaptive causal decoupling network;

[0011] Decoupling the component-level health status representation from the system monitoring data through the domain adaptive causal decoupling network;

[0012] The anomaly detection model is determined according to the component-level health status representation.

[0013] In another possible implementation, the training to obtain the domain adaptive causal decoupling network according to the training data set and the causal information includes:

[0014] According to the training data set and the causal information, a domain adaptive causal decoupling network is constructed, wherein the domain adaptive causal decoupling network includes a causal adjustment matrix and a coordinate rotation matrix, wherein the causal adjustment matrix is ​​used to indicate the influence of the system operating condition variables and / or the system operating mode on the causal information, and the coordinate rotation matrix is ​​used to match the coordinate system of the system monitoring parameters to the coordinate system of the component-level health status representation;

[0015] The causal adjustment matrix and the coordinate rotation matrix are optimized by minimizing the loss function, and the domain adaptive causal decoupling network is obtained by training.

[0016] In another possible implementation, determining the anomaly detection model according to the component-level health status representation includes:

[0017] Determining a domain-stable anomaly detection model according to the component-level health status representation, the domain-stable anomaly detection model being used to indicate a corresponding relationship between the component-level health status representation and anomaly detection results, the anomaly detection results being used to indicate whether the electromechanical system is in a fault state;

[0018] The anomaly detection model is determined according to the domain adaptive causal decoupling network and the domain stable anomaly detection model.

[0019] In another possible implementation, the anomaly detection model includes: the domain adaptive causal decoupling network and the domain stable anomaly detection model, the input parameter of the domain adaptive causal decoupling network is the system monitoring data, and the output parameter is the component-level health status representation; the input parameter of the domain stable anomaly detection model is the component-level health status representation, and the output parameter is the anomaly detection result.

[0020] In another possible implementation, the method further includes:

[0021] Acquiring real-time monitoring data of the electromechanical system during operation;

[0022] According to the real-time monitoring data, the pre-trained abnormality detection model is called to output an abnormality detection result, and the abnormality detection result is used to indicate whether the electromechanical system is in a fault state.

[0023] According to another aspect of the present disclosure, a complex electromechanical system anomaly detection device based on a domain adaptive causal decoupling network is provided, the device comprising:

[0024] an acquisition module, configured to acquire a training data set and causal information of an electromechanical system, wherein the training data set includes system monitoring data and corresponding system fault label data, wherein the system monitoring data includes a plurality of variables related to a health state of the electromechanical system, the system fault label data is used to indicate whether the electromechanical system is in a fault state, and the causal information is used to indicate a functional relationship between a plurality of components of the electromechanical system;

[0025] A training module is used to train an anomaly detection model based on a domain adaptive causal decoupling network according to the training data set and the causal information, wherein the domain adaptive causal decoupling network is used to indicate the correspondence between the system monitoring data and the component-level health status representation, the component-level health status representation is used to indicate the health status of each of the multiple components of the electromechanical system, and the anomaly detection model is used to perform anomaly detection on the electromechanical system.

[0026] In one possible implementation, the types of the multiple variables include at least one of system monitoring parameters, system operating condition variables and system operating modes, the system monitoring parameters include variables collected by a data collection device set at a specified position of the electromechanical system, the system operating condition variables include external condition variables and / or environmental variables of the electromechanical system, and the system operating mode is the operating mode adopted by the electromechanical system when implementing its functions.

[0027] In another possible implementation, the training module is further used to:

[0028] According to the training data set and the causal information, training is performed to obtain the domain adaptive causal decoupling network;

[0029] Decoupling the component-level health status representation from the system monitoring data through the domain adaptive causal decoupling network;

[0030] The anomaly detection model is determined according to the component-level health status representation.

[0031] In another possible implementation, the training module is further used to:

[0032] According to the training data set and the causal information, a domain adaptive causal decoupling network is constructed, wherein the domain adaptive causal decoupling network includes a causal adjustment matrix and a coordinate rotation matrix, wherein the causal adjustment matrix is ​​used to indicate the influence of the system operating condition variables and / or the system operating mode on the causal information, and the coordinate rotation matrix is ​​used to match the coordinate system of the system monitoring parameters to the coordinate system of the component-level health status representation;

[0033] The causal adjustment matrix and the coordinate rotation matrix are optimized by minimizing the loss function, and the domain adaptive causal decoupling network is obtained by training.

[0034] In another possible implementation, the training module is further used to:

[0035] Determining a domain-stable anomaly detection model according to the component-level health status representation, the domain-stable anomaly detection model being used to indicate a corresponding relationship between the component-level health status representation and anomaly detection results, the anomaly detection results being used to indicate whether the electromechanical system is in a fault state;

[0036] The anomaly detection model is determined according to the domain adaptive causal decoupling network and the domain stable anomaly detection model.

[0037] In another possible implementation, the anomaly detection model includes: the domain adaptive causal decoupling network and the domain stable anomaly detection model, the input parameter of the domain adaptive causal decoupling network is the system monitoring data, and the output parameter is the component-level health status representation; the input parameter of the domain stable anomaly detection model is the component-level health status representation, and the output parameter is the anomaly detection result.

[0038] In another possible implementation, the device further includes: a calling module, configured to:

[0039] Acquiring real-time monitoring data of the electromechanical system during operation;

[0040] According to the real-time monitoring data, the pre-trained abnormality detection model is called to output an abnormality detection result, and the abnormality detection result is used to indicate whether the electromechanical system is in a fault state.

[0041] According to another aspect of the present disclosure, a computing device is provided, the device comprising: a processor; 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.

[0042] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor.

[0043] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of a computing device, the processor in the computing device executes the above method.

[0044] The disclosed embodiment provides a complex electromechanical system anomaly detection method based on a domain adaptive causal decoupling network, by acquiring a training data set and causal information of the electromechanical system, the training data set includes system monitoring data and corresponding system fault label data, the system monitoring data includes multiple variables related to the health state of the electromechanical system, the system fault label data is used to indicate whether the electromechanical system is in a fault state, and the causal information is used to indicate the action relationship between multiple components of the electromechanical system; according to the training data set and the causal information, an anomaly detection model based on a domain adaptive causal decoupling network is trained, the domain adaptive causal decoupling network is used to indicate the corresponding relationship between the system monitoring data and the component-level health state representation, the component-level health state representation is used to indicate the respective health states of multiple components of the electromechanical system, and the anomaly detection model is used to perform anomaly detection on the electromechanical system; that is, by combining domain adaptation and causal decoupling technology, a domain adaptive anomaly detection model can be trained, so that the model can adapt to the changing system operating environment, and the method can more accurately identify anomalies of the electromechanical system, and can maintain a high accuracy even when the data distribution changes.

[0045] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0047] Figure 1 A flowchart of a complex electromechanical system anomaly detection method based on a domain adaptive causal decoupling network provided by an exemplary embodiment of the present disclosure is shown.

[0048] Figure 2 A schematic diagram showing the cause-effect relationship of different types of variables in a mechatronic system provided by an exemplary embodiment of the present disclosure is shown.

[0049] Figure 3 A schematic diagram showing the influence of different system operation modes on the causal relationship structure provided by an exemplary embodiment of the present disclosure is shown.

[0050] Figure 4 A schematic diagram showing the influence of system operating condition variables on the strength of causal relationship under the same system operating mode provided by an exemplary embodiment of the present disclosure is shown.

[0051] Figure 5 A schematic diagram of the structure of a domain-adaptive causal decoupling network provided by an exemplary embodiment of the present disclosure is shown.

[0052] Figure 6A schematic diagram of a causal network between system monitoring parameters provided by an exemplary embodiment of the present disclosure is shown.

[0053] Figure 7 A schematic diagram of a two-dimensional t-SNE projection of system monitoring parameters and YM provided by an exemplary embodiment of the present disclosure is shown.

[0054] Figure 8 A schematic diagram of a component-level health status representation and a two-dimensional t-SNE projection of YM provided by an exemplary embodiment of the present disclosure is shown.

[0055] Fig. 9 A schematic structural diagram of a complex electromechanical system anomaly detection device based on a domain adaptive causal decoupling network provided by an exemplary embodiment of the present disclosure is shown.

[0056] Fig.10 It is a block diagram of a device for executing a complex electromechanical system anomaly detection method based on a domain adaptive causal decoupling network according to an exemplary embodiment. DETAILED DESCRIPTION

[0057] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0058] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0059] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0060] How to ensure that the anomaly detection model can maintain its performance under changing operating environments has become one of the key challenges facing anomaly detection in complex systems. To address this problem, transfer learning techniques have been introduced to adapt well-trained models to new domains, that is, new operating conditions. However, for complex systems, due to the lack of prior knowledge and the complex interactions between monitoring features, finding the most effective fine-tuning strategy is often a time-consuming and difficult task. In this case, domain adaptation methods based on feature mapping have become a widely considered solution. This method achieves model migration by encoding data from the source domain and the target domain into a unified latent feature space, making data from different domains difficult to distinguish in this space.

[0061] Although traditional domain adaptation methods have achieved certain results, they usually ignore the diversity of system monitoring variables and system failure mechanisms (i.e., causal information). Current research shows that directly using and encoding all original monitoring variables may cause the latent feature space to contain information that is difficult to generalize, which in turn produces unsatisfactory prediction results in the target domain. Therefore, it is particularly important to understand the actual meaning of different monitoring variables, that is, to analyze their specific impact on the system state.

[0062] Causal relationships can reveal the most basic causal relationships in observed data. Data-based causal discovery techniques have been used to explore the causal information of the system to improve the stability and interpretability of domain adaptation. These methods identify invariant conditional distributions between different domains by constructing joint causal reasoning frameworks, mechanism transfer, and other methods to adapt to different distributions caused by non-parametric shifts.

[0063] In view of the limitations of current research, the embodiments of the present disclosure propose a complex electromechanical system anomaly detection method based on a domain-adaptive causal decoupling network, so that the anomaly detection model can adapt to the changing system operating environment. First, by constructing a general causal framework for complex systems, the different categories of system monitoring variables and system causal information are analyzed. Secondly, a domain-adaptive causal strength matrix is ​​proposed to characterize the impact of operating modes and conditions on the system causal information (structure and strength). Then, a domain-adaptive causal decoupling network is designed to learn a domain-adaptive representation of component-level health status representation. Finally, based on the obtained component-level health status representation, a domain-adaptive anomaly detection model is constructed. The embodiments of the present disclosure aim to decouple the complex interactions within complex electromechanical systems and reveal potential, domain-adaptive causal information, thereby improving the accuracy and interpretability of anomaly detection.

[0064] The disclosed embodiments are not only applicable to abnormality detection of complex electromechanical systems, but can also be extended to fault diagnosis of other complex systems such as electronic systems and software systems, as well as a wider range of complex classification task scenarios, and have good application prospects.

[0065] Below, several exemplary embodiments are used to introduce the complex electromechanical system anomaly detection method based on a domain adaptive causal decoupling network provided by the embodiments of the present disclosure.

[0066] Please refer to Figure 1 , which shows a flowchart of a complex electromechanical system anomaly detection method based on a domain adaptive causal decoupling network provided by an exemplary embodiment of the present disclosure, and this embodiment is illustrated by using the method in a computing device. The method includes the following steps.

[0067] Step 101, obtaining a training data set and causal information of the electromechanical system, wherein the training data set includes system monitoring data and corresponding system fault label data, the system monitoring data includes multiple variables related to the health status of the electromechanical system, the system fault label data is used to indicate whether the electromechanical system is in a fault state, and the causal information is used to indicate the functional relationship between multiple components of the electromechanical system.

[0068] The training data set includes the system monitoring data of the electromechanical system in normal and faulty states and its corresponding system fault label data. System monitoring data refers to data collected from the electromechanical system, such as temperature, pressure, vibration, etc., which reflect the health status of the electromechanical system. System monitoring data can be collected in real time by data acquisition devices (such as sensors), and data preprocessing techniques such as wavelet analysis, median filtering, Kalman filtering, etc. can be used to improve data quality and reduce the impact of noise and interference.

[0069] System fault label data is a label corresponding to system monitoring data, which is used to indicate whether the electromechanical system corresponding to the system monitoring data is normal or in a faulty state. These labels can be binary (faulty / no fault) or multi-category (different types of faults). System fault label data can be obtained from maintenance logs, fault records, or expert evaluations to mark whether each set of data corresponds to a system fault.

[0070] Causal information is information that describes how the various components of an electromechanical system interact and influence each other. This information helps to understand the causal relationship within the system. Causal information is used to indicate the interaction between multiple components of an electromechanical system. The interaction relationship is also called a causal relationship. That is, causal information is used to indicate the causal relationship structure and strength between multiple components of an electromechanical system. The causal relationship between various components in an electromechanical system can be determined through expert knowledge, historical data analysis, or causal inference technology.

[0071] In some embodiments, multiple sets of original monitoring data and corresponding system fault label data are collected, and the multiple sets of original monitoring data and corresponding system fault label data are preprocessed to obtain a training data set; based on the training data set, the causal information of the electromechanical system is determined by a preset algorithm.

[0072] Step 102: According to the training data set and causal information, an anomaly detection model based on a domain adaptive causal decoupling network is trained. The domain adaptive causal decoupling network is used to indicate the correspondence between the system monitoring data and the component-level health status representation. The component-level health status representation is used to indicate the health status of multiple components of the electromechanical system. The anomaly detection model is used to perform anomaly detection on the electromechanical system.

[0073] The computing device can train a domain-adaptive causal decoupling network using the collected training data set and causal information. This network can learn the correspondence between system monitoring data and component-level health status representation. Domain adaptation refers to the ability of the model to migrate from the source domain (training data set) to the target domain (actual application environment) and maintain or improve its performance in the target domain. In this method, the domain adaptation capability is achieved through data under different operating conditions contained in the training data set. This means that the model learns the system behavior under different operating conditions during the training process, so that it can adapt to various operating conditions that may be encountered in actual applications. Causal decoupling refers to decoupling the complex causal relationship between system monitoring data and component-level health status to identify and represent the health status of each component. By constructing a causal framework and a causal strength matrix, the model can understand the interactions and influences between different components, so as to more accurately predict the health status of each component. This decoupling capability enables the model to adaptively adjust to changing operating conditions to maintain the accuracy of its predictions.

[0074] Component-level health status representation means that the model can generate a health status representation for each component of the mechatronic system. This representation can capture the health changes of the component under different operating conditions, allowing the model to perform more refined anomaly detection for specific components and specific conditions.

[0075] In practical applications, domain-adaptive causal decoupling networks can dynamically adjust their parameters and structures based on real-time monitoring data to adapt to current operating conditions. This dynamic adjustment capability is achieved through continuous learning or online learning mechanisms, allowing the model to continuously optimize its performance to adapt to changing environments.

[0076] Based on the domain adaptive causal decoupling network, an anomaly detection model can be constructed. The purpose of this model is to monitor the electromechanical system and detect abnormal behavior in a timely manner, such as detecting whether the electromechanical system is in a faulty state. During the model training process, various machine learning algorithms can be used, such as random forests, support vector machines, neural networks, etc., as well as deep learning methods such as autoencoders, generative adversarial networks (GANs), etc. Through domain adaptation and causal decoupling training, the model not only performs well on the training dataset, but also has good generalization capabilities under unseen operating conditions. This generalization ability enables the model to accurately detect anomalies when faced with new or changing operating conditions.

[0077] After the model is trained, it can be evaluated to ensure its effectiveness in real-world applications. Metrics such as cross-validation, precision, and recall can be used to evaluate the performance of the model. Based on the evaluation results, the model may need to be fine-tuned to optimize its application in real-world mechatronic systems.

[0078] It should be noted that the implementation details of the model training process can be referred to the relevant description in the following embodiments and will not be introduced here.

[0079] In summary, the embodiments of the present disclosure provide a method for detecting anomalies in complex electromechanical systems based on a domain adaptive causal decoupling network, by acquiring a training data set and causal information of the electromechanical system, the training data set includes system monitoring data and corresponding system fault label data, the system monitoring data includes multiple variables related to the health state of the electromechanical system, the system fault label data is used to indicate whether the electromechanical system is in a fault state, and the causal information is used to indicate the functional relationship between multiple components of the electromechanical system; according to the training data set and the causal information, an anomaly detection model based on a domain adaptive causal decoupling network is trained, the domain adaptive causal decoupling network is used to indicate the corresponding relationship between the system monitoring data and the component-level health state representation, the component-level health state representation is used to indicate the respective health states of multiple components of the electromechanical system, and the anomaly detection model is used to perform anomaly detection on the electromechanical system; that is, by combining domain adaptation and causal decoupling technology, a domain adaptive anomaly detection model can be trained, so that the model can adapt to the changing system operating environment, and the method can more accurately identify anomalies of the electromechanical system, and maintain a high accuracy even when the data distribution changes.

[0080] In some embodiments, the system monitoring data includes multiple variables related to the health status of the electromechanical system, and the types of the multiple variables include at least one of system monitoring parameters, system operating condition variables, and system operating modes. The system monitoring parameters include variables collected by a data collection device set at a designated position of the electromechanical system, and the system operating condition variables include external condition variables and / or environmental variables of the electromechanical system. The system operating mode is the operating mode adopted by the electromechanical system when implementing a function. According to the training data set and causal information, an anomaly detection model based on a domain adaptive causal decoupling network is trained, including: according to the training data set and causal information, a domain adaptive causal decoupling network is trained; through the domain adaptive causal decoupling network, a component-level health status representation is decoupled from the system monitoring data; according to the component-level health status representation, an anomaly detection model is determined.

[0081] That is to say, the complex electromechanical system anomaly detection method based on the domain adaptive causal decoupling network can include four parts: causal information analysis of complex electromechanical systems, decoupled component-level health status representation, domain adaptive causal decoupling network construction, and domain adaptive anomaly detection model construction. First, the causal information of the complex electromechanical system is analyzed in detail, that is, the influence of the system operation mode and system operation condition variables on the causal relationship structure and strength between components. Considering that it is usually impossible to directly learn the domain adaptive causal information, the embodiment of the present disclosure proposes a domain adaptive causal decoupling network. In the domain adaptive causal decoupling network, the fault information transmitted between components is gradually stripped from the system monitoring parameters by using a linear causal model to achieve the purpose of decoupling to obtain the component-level health status representation. Based on the domain adaptive causal decoupling network, a component-level health status representation that can adapt to the system operation condition can be obtained. According to the component-level health status representation, an adaptive and inherently interpretable anomaly detection model can be established using an interpretable machine learning model. These four parts are introduced in turn below.

[0082] Part I: Causal information analysis of complex electromechanical systems.

[0083] Assume that the training data set of the electromechanical system is D = [V, Y], V ∈ R N×K is the system monitoring data related to the health status of the electromechanical system, Y∈R N×1 is the system fault label data, that is, the record data of whether the electromechanical system is in a fault state. The training data set includes N samples, and the system monitoring data includes K variables, where N and K are both positive integers. In this embodiment, the multiple variables V included in the system monitoring data can be K) is divided into three categories: system monitoring parameters η, system operating condition variables C and system operating mode M. Among them, system monitoring parameters refer to variables collected by data collection devices (such as sensors) set at designated locations of the electromechanical system based on expert experience. System operating condition variables refer to the collected system exogenous variables, that is, the external condition variables and / or environmental variables of the electromechanical system. The system operating mode refers to the operating mode (that is, the operation or setting mode) when it realizes different functions, which is usually determined by relevant staff based on actual needs and experience. Multiple variables V can be arranged in the order of system monitoring parameters η, system operating condition variables C and system operating mode M, that is, η=(η1,η2,...,η H )=(V1,V2,...,V H ), C=(C1,C2,...,C Q )=(V H+1 ,V H+2 ,...,V H+Q ).

[0084] Schematically, based on the classified variable categories, the causal relationship of different types of variables in the electromechanical system can be described as Figure 2 The general structure shown. The variables in the solid box (i.e., system monitoring parameters, system operating condition variables, and system operating mode) are usually observable and collectable, while the variables in the dashed box (i.e., the health status of each component) cannot be observed. Among them, the health status of each component directly determines the fault state of the complex electromechanical system and directly affects the system monitoring data. The system operating mode and system operating condition variables affect the system monitoring parameters by affecting the interaction relationship between components (i.e., the causal relationship structure and strength). Different system operating modes often correspond to different combinations and connection relationships of components within the system, so that the system can achieve different functions. Different system operating condition variables will affect the frequency and intensity of interaction between components. In addition, it is often impossible to determine that the system operating mode and system operating condition variables will inevitably affect all system monitoring parameters.

[0085] Taking the electromechanical system as an example, a high-speed rail electromechanical control system, the health status of each component cannot be observed but directly affects the system fault state. System operating condition variables, such as external temperature, humidity, required speed, input voltage, etc., represent the application environment monitored instantaneously by the electromechanical system, and therefore will not affect the health status of each component, but will affect the system monitoring parameters (such as line current, internal temperature). The system operation mode corresponds to the functions implemented by the electromechanical system. Usually, the train driver selects different operation modes according to mileage, stations, emergencies, etc., so there is no causal relationship between it and the system application environment, and it will not affect the health status of each component, but it will affect the system monitoring parameters.

[0086] In some embodiments, the system monitoring parameters include multiple state monitoring values, and there is a one-to-one correspondence between the multiple state monitoring values ​​and the multiple components, that is, each state monitoring value is used to uniquely indicate the health status of a component, and the causal information of the electromechanical system is the causal relationship between the system monitoring parameters.

[0087] In a single system operation mode and system operation condition, when it is assumed that the electromechanical system contains H' = H components and each component has only a unique state monitoring value, H is a positive integer greater than 1. The structural causal relationship between the components is assumed to be a linear regression equation, and the component-level health status representation U' = [U1', U2', ..., U' H ] to simplify the causal mechanism, the causal information of the electromechanical system (i.e., the generation mechanism of the system monitoring parameter η) can be expressed as follows:

[0088]

[0089] Among them, A S It is the overall causal strength matrix of the system. The overall causal strength matrix of the system is used to indicate the interaction relationship between multiple components of the electromechanical system (i.e., causal relationship structure and causal relationship strength). I is the unit matrix.

[0090] In different system operation modes, the causal relationship structure between components usually changes. Figure 3 As shown in the figure, it shows the effect of different system operation modes on the causal relationship structure, where the M1 system operation mode and the M2 system operation mode use different component combinations to achieve different system functions. Under the same system operation mode, different system operating condition variables will affect the causal relationship strength between components. Figure 4 As shown, it shows a schematic diagram of the influence of system operating condition variables on the causal relationship strength under the same system operating mode. (1) And system operating condition C (2) The strength of the interaction between the corresponding components is different. For example, different values ​​(such as 0.5, 0.6, 0.7, etc.) can be used to represent the strength of the causal relationship between the components. Figure 3 and Figure 4 The solid lines in the figure represent used components and structural relationships, and the dotted lines represent unused components and structural relationships.

[0091] Based on the above considerations, for a complex electromechanical system containing m system operation modes, the generation process of the system monitoring parameter η can be expressed as follows:

[0092]

[0093] in, It is M i The causal strength matrix between H components under the system operation mode is affected by the system operation condition variables, i is a positive integer, the value range of i is 1 to m, and m is a positive integer greater than 1.

[0094] The second part is to decouple the component-level health status representation.

[0095] When the causal relationships between components are all linear, according to the causal information of the complex electromechanical system (i.e., the generation process of the system monitoring parameter η shown in the above formula), the process of decoupling the component-level health status representation U′ is as follows:

[0096]

[0097] In order to prevent the change in dimension from affecting the fault information in the data, it is usually hoped that the characterization learning process does not change the dimension of the data. Therefore, the embodiment of the present disclosure normalizes the formula for decoupling the component-level health status characterization as shown below:

[0098]

[0099] in, is a diagonal matrix whose j-th row and j-th column element is (Right now The sum of the elements in the jth row of ), and all other elements are 0. Causal Strength Matrix The degree matrix of .

[0100] The disclosed embodiment uses a linear causal model multiple times to fit the nonlinear causal relationship that is prevalent in complex electromechanical systems, and decouples the component-level health status representation from the system monitoring parameters. Therefore, under the nonlinear causal mechanism, the component-level health status representation U′ can be gradually decoupled from the system monitoring parameter η by the following formula:

[0101]

[0102] Among them, U j ′ and U j ' +1 are the input parameters and output parameters of the jth causal information decoupling process. The input parameter of the first causal information decoupling is the system monitoring parameter η, and the output parameter of the last causal information decoupling is the component-level health status representation U′.

[0103] It can be seen that the causal strength matrix affected by the system operating conditions under each system operating mode is the key basis for decoupling the component-level health status representation. However, the system monitoring data of complex electromechanical systems are often limited and biased, and the system operating conditions are complex and changeable. It is unrealistic to directly mine the causal information under each system operating mode and system operating condition based on the system monitoring data. It is difficult to achieve and the validity of the results cannot be guaranteed. In addition, there are correlations between the causal information of the system under different system operating modes and system operating conditions. Directly distinguishing and treating them separately also ignores these correlations. Therefore, it is almost impossible to directly decouple the component-level health status representation based on adaptive causal relationships.

[0104] Part III: Construction of domain-adaptive causal decoupling network.

[0105] In order to fully decouple the causal mechanism in the complex electromechanical system, the embodiment of the present disclosure designs a domain-adaptive causal decoupling network to indirectly learn the influence of the system operating conditions on the causal information between components. In fact, the domain-adaptive causal decoupling network is a decoupled causal representation learning model, which is named to distinguish it from other decoupling models. The proposed domain-adaptive causal decoupling network decouples the system operating mode into the component-level health state representation, that is, the decoupled health state representation is interpretable (separable) to the system operating mode. In addition, the system operating condition variables are used as adjustment parameters of the overall causal strength matrix of the system, thereby improving the credibility of the process of obtaining the causal strength matrix. Here, the overall causal strength matrix of the system refers to the causal strength matrix obtained based on all modes and conditions. By analyzing actual application cases, it is found that in most cases, the influence of the system operating conditions on the strength of the component action is relatively simple, so the embodiment of the present disclosure uses a single-layer neural network to fit the corresponding relationship between the system operating conditions and the causal information. In some embodiments, the causal adjustment matrix affected by the system operating condition variables is determined according to the sample weight matrix, the system operating condition variables, the coefficient weight matrix of the system operating condition variables, and the adjoint weight matrix of the system operating condition variables. That is, according to the sample weight matrix, the system operating condition variables, the coefficient weight matrix of the system operating condition variables, and the adjoint weight matrix of the system operating condition variables, the causal adjustment matrix is ​​determined by a preset algorithm (such as an activation function). In principle, the causal adjustment matrix W affected by the system operating condition variables is set C ∈R H×H as follows:

[0106] W C =Sigmoid(αCβ+γ)

[0107] Among them, W C It is used to indirectly find the causal strength matrix Yes, W. Cis a linear matrix with unknown parameters, which is related to the overall causal intensity matrix A of the system S Multiplication can be expressed as Part of the information, that is, the causal information affected by the working conditions. K×N Is the sample weight matrix, which is set to a full 1 matrix to adjust the data dimension and ensure that the data has the correct shape and size before entering the neural network. β∈R Q×K is the coefficient weight matrix of the system operating condition variable C. The coefficient weight matrix represents the influence of the system operating condition variable C on the causal relationship strength. It is a parameter matrix that is optimized through the learning process to best reflect the association between the operating condition variable and the causal relationship strength between components. γ∈R K×K It is the adjoint weight matrix of the system operating condition variable C. The adjoint weight matrix is ​​used to further adjust and optimize the output of the causal adjustment matrix. It can be regarded as a correction or enhancement of the coefficient weight matrix output. It is also a parameter matrix and needs to be optimized through the training process. Sigmoid() is the Sigmoid function, also known as the S-type function. The Sigmoid function is one of the commonly used activation functions in neural networks. Its definition is shown in the following formula:

[0108]

[0109] The characteristic of this function is that it can map the input value x to the interval (0,1), so that the output value has nonlinear characteristics, which is very important for neural networks to process complex data and pattern recognition.

[0110] In addition, the previous article assumes that the electromechanical system contains H components and each component has only a unique state monitoring value, so the coordinate rotation matrix should also be set in the decoupling process to match the coordinate system of the system monitoring parameters to the coordinate system of the component-level health status representation. This matrix is ​​used to adjust the direction and scale of the system monitoring parameters to ensure that they can accurately reflect the health status of the component.

[0111] Based on the above considerations, the schematic diagram of the structure of the domain adaptive causal decoupling network is as follows: Figure 5 As shown in Figure 1, the domain adaptive causal decoupling network contains multiple causal decoupling layers, such as layer 1, layer 2, until layer J, where J is a positive integer greater than 1. Each layer is responsible for converting the coordinate system of the system monitoring parameters to the coordinate system of the component-level health status representation. The operation process of the jth causal decoupling layer is as follows:

[0112]

[0113] Where j is a positive integer, and the value range of j is from 1 to J. S is the overall causal intensity matrix of the system; U′ j and U′j+1 are the input parameters and output parameters of the j-th causal decoupling process respectively; yes The degree matrix contains the measurement of each component condition monitoring value, H is the H-order identity matrix; W j ∈R H×H is the coordinate rotation matrix of the jth causal decoupling layer, which is used to adjust the coordinate system.

[0114] Through multiple causal decoupling layers, the domain-adaptive causal decoupling network can gradually decouple system monitoring parameters to the component level, so that the health status of each component can be analyzed independently. The domain-adaptive causal decoupling network can dynamically adjust the system's overall causal strength matrix and coordinate rotation matrix according to changes in system operating conditions to adapt to different system states and environments. Ultimately, the vector output by the network provides a clear component-level health status representation, which helps with system maintenance and fault diagnosis.

[0115] The optimization goal of the domain adaptive causal decoupling network is to make the decoupled causal representation vector interpretable for the system operation mode and fault state. Interpretability means that the output of the model can be understood and explained by humans. For the domain adaptive causal decoupling network, this means that the component-level health status representation vector output by the network should be able to clearly reflect the state of the system to distinguish different system operation modes and fault states, so that system engineers or analysts can understand how the health status of each component is related to the overall system performance. Schematically, referring to the silhouette coefficient used in the clustering task, the loss function Loss of the proposed domain adaptive causal decoupling network is DA Can be:

[0116] Loss DA =-silhouette_score(U′,YM)

[0117] Among them, YM is a variable obtained by label encoding the combination of system fault label data Y and system operation mode M, indicating how many forms of combinations of Y and M there are; silhouette_score() is a function for calculating the average silhouette coefficient.

[0118] In some embodiments, a domain-adaptive causal decoupling network can be constructed based on a training data set and causal information. The domain-adaptive causal decoupling network includes a causal adjustment matrix and a coordinate rotation matrix. The causal adjustment matrix is ​​used to indicate the influence of system operating condition variables and / or system operating modes on causal information, and the coordinate rotation matrix is ​​used to match the coordinate system of system monitoring parameters to the coordinate system of component-level health status representation. By minimizing the loss function, the causal adjustment matrix and the coordinate rotation matrix are optimized, and the domain-adaptive causal decoupling network is obtained by training.

[0119] That is, the embodiment of the present disclosure proposes a trainable parameter in the domain adaptive causal decoupling network, namely, the causal adjustment matrix W in the above formula C and the coordinate rotation matrix W j is optimized sequentially. First, all W j It is set to the unit matrix (i.e., no coordinate rotation is performed), and the causal condition matrix W is optimized by minimizing the loss function C (Actually, this is to obtain the coefficient weight matrix β and the accompanying weight matrix γ). C , W j It is also optimized by minimizing the loss function. In addition, since the adaptive causal decoupling network in the field of graph convolution operations also has strong feature extraction performance, that is, it can efficiently decouple causal information, the model usually contains a maximum of three layers. When optimizing the model structure, gradually increase the number of layers and train W in sequence. C and W j , schematically, when the training fitting accuracy is less than the preset accuracy threshold, the number of layers of the model structure is increased, and when the training fitting accuracy is greater than or equal to the preset accuracy threshold, the training stops. The training goal is to minimize the loss function as much as possible to obtain a component-level health status representation U′ that is more interpretable to system faults and operating modes and can adapt to system operating conditions.

[0120] Part 4, construction of domain adaptive anomaly detection model.

[0121] In some embodiments, according to the component-level health status representation, determining an anomaly detection model includes: determining a domain-stable anomaly detection model according to the component-level health status representation, the domain-stable anomaly detection model is used to indicate the corresponding relationship between the component-level health status representation and the anomaly detection result, and the anomaly detection result is used to indicate whether the electromechanical system is in a fault state; determining the anomaly detection model according to the domain-adaptive causal decoupling network and the domain-stable anomaly detection model. Schematically, based on the domain-adaptive component-level health status representation U′, the domain-stable anomaly detection model can be defined as the following formula:

[0122]

[0123] Considering that the optimization goal of component-level health status representation is to make the samples in the data [U′, YM] cluster according to different YM, the obtained component-level health status representation has high separability, and there is no need to use complex machine learning models to fit the mapping relationship between it and the system fault label data Y. In order to make the anomaly detection model of complex electromechanical systems inherently interpretable, as shown in the above formula, the domain-stable anomaly detection model based on component-level health status representation can usually choose a simple and interpretable machine learning model, such as logistic regression, decision tree, etc. In addition, the relationship between component-level health status representation and system failure is usually stable, that is, when a component degrades to a certain threshold, the corresponding system failure is valid under different working conditions. Therefore, the domain-stable anomaly detection model based on component-level health status representation is domain-stable. Then, the adaptive anomaly detection model is obtained by combining two models: a domain-adaptive causal decoupling network based on system monitoring data, and a domain-stable anomaly detection model based on component-level health status representation. That is, the anomaly detection model includes: a domain-adaptive causal decoupling network and a domain-stable anomaly detection model. The input parameter of the domain-adaptive causal decoupling network is the system monitoring data, and the output parameter is the component-level health status representation; the input parameter of the domain-stable anomaly detection model is the component-level health status representation, and the output parameter is the anomaly detection result.

[0124] After the anomaly detection model is trained, the application process of the anomaly detection model may include: obtaining real-time monitoring data of the electromechanical system during operation; based on the real-time monitoring data, calling the pre-trained anomaly detection model, and outputting an anomaly detection result, the anomaly detection result is used to indicate whether the electromechanical system is in a fault state. Among them, based on the real-time monitoring data, calling the pre-trained anomaly detection model and outputting an anomaly detection result may further include: pre-processing the real-time monitoring data to obtain pre-processed real-time monitoring data, inputting the pre-processed real-time monitoring data into the pre-trained anomaly detection model, and outputting an anomaly detection result. The anomaly detection result is usually a probability value or a classification label, indicating that the electromechanical system is in a normal or faulty state.

[0125] In some embodiments, interpretation and decision making can be performed based on the anomaly detection results output by the anomaly detection model. If an anomaly is detected, appropriate measures may need to be taken, such as sounding an alarm, automatically shutting down, performing maintenance, etc. In some embodiments, the anomaly detection model can be evaluated and iteratively improved based on actual system performance and maintenance records. This may include retraining the model to improve its accuracy and robustness. In some embodiments, the anomaly detection model is integrated into the monitoring system of the electromechanical system to achieve automated anomaly detection and response.

[0126] In an illustrative example, the high-speed rail electromechanical control system is taken as the research object to analyze and verify the effectiveness of the proposed adaptive anomaly detection model. In order to verify the domain adaptive performance of the model, the observation data of the high-speed rail electromechanical control system is first divided into three sets: training set, test set 1 and test set 2. Among them, test set 1 and test set 2 are sets consisting of the top 10% samples of train speed and traction, respectively, and the remaining samples are used as training sets.

[0127] The high-speed train brake control system includes pneumatic and electrical equipment, and various devices are combined through microelectronic technology to achieve different functions. There are many factors that may affect the health of the system, including train operating conditions, brake control system operating conditions, system component status, environmental factors, etc. In order to comprehensively monitor these factors, sensors are installed at key locations based on expert experience, and operating and environmental variables are recorded. Specifically, monitoring tools are set up at key locations of the circuit system to collect information such as voltage, current, and temperature; sensors are set up on key components of the mechanical system to collect vibration signals, temperature, power, etc.; at the same time, state variables such as braking mode, traction level, train speed, position, running time, etc. displayed by the software system are recorded, as well as environmental variables such as external temperature, humidity, and weather. The collected raw monitoring data contains 43 variables that may be related to the system status, such as train speed, wind speed, line voltage, line current, internal temperature, external temperature, braking mode, braking level, etc. For the convenience of explanation, these variables are only represented as X1, X2,..., X43.

[0128] Before causal discovery and anomaly modeling, the original monitoring data needs to be preprocessed. First, detect meaningless variables (such as unique value variables and ID information variables), and then convert character variables into numerical variables through one-hot encoding. Delete data samples with missing values, and finally normalize all monitoring variables through z-score standardization. After data preprocessing, the resulting data set contains 73,007 samples and 38 monitoring variables. These monitoring variables include 2 system operating condition variables, 2 operating mode variables, and 4 environmental factors. The remaining 30 monitoring variables are system monitoring parameters, denoted as V1, V2,..., V30.

[0129] First, it is necessary to mine the causal information of the brake control system, that is, to explore the causal relationship between the system monitoring parameters based on the training data set under different operating modes and conditions. Due to the limited expert and physical knowledge and the inability to conduct randomized controlled experiments, data-based causal discovery is used to reveal the causal relationship between the system monitoring parameters.

[0130] Considering the potential confounding factors and selection bias that are common in complex system monitoring data, the Fast Causal Inference (FCI) algorithm can be used. For example, through the FCI function, the causal network between system monitoring parameters can be easily obtained.

[0131] In order to improve the accuracy and stability of the causal discovery results, some prior knowledge is added to the FCI function through the corresponding parameters. Schematically, the schematic diagram of the causal network between the system monitoring parameters is as follows Figure 6 This network intuitively demonstrates the causal relationship between multiple system monitoring parameters, providing an important basis for further analysis and optimization of the braking control system.

[0132] Based on the training data set, a domain-adaptive causal decoupling network is constructed. By gradually increasing the number of causal decoupling layers and training W in sequence C and W j , minimizing the loss function and decoupling the component-level health status representation U′ from the system monitoring parameters. In this case, the final domain-adaptive causal decoupling network contains two causal decoupling layers.

[0133] The proposed domain-adaptive causal decoupling network can decouple component-level health status representation from system monitoring parameters. Based on the causal information of complex electromechanical systems, the fault information transmitted to each other is extracted and decomposed from the system monitoring parameters one by one to obtain the health status representation of each component. The decoupling process is interpretable and credible. In addition, during the decoupling process, the influence of system operating condition variables on the causal strength matrix between system monitoring parameters can be learned, and the mapping function of system operating condition variables to the causal strength matrix can be obtained, thereby explaining the influence of operating conditions on system monitoring parameters and improving the interpretability of system monitoring data.

[0134] Indicative, Figure 7 A schematic diagram showing the two-dimensional t-distributed Stochastic Neighbor Embedding (t-SNE) projection of system monitoring parameters and YM is shown. Figure 8A schematic diagram of the component-level health status representation and the two-dimensional t-SNE projection of YM is shown. Among them, YM is a variable obtained by label encoding the combination of system fault label data Y and system operation mode M. t-SNE is a nonlinear dimensionality reduction technology for high-dimensional data visualization. It displays data points in two-dimensional or three-dimensional space by maintaining the local structure in high-dimensional space. As can be seen from the figure, the component-level health status representation is clustered under different system operation modes and system fault label data and has high separability, which means that the component-level health status representation can explain (distinguish) different system operation modes and fault states. Since the component-level health status representation has good separability, a classifier with intrinsic interpretability can be used to establish an anomaly detection model. Here, a single-layer perceptron with a Relu activation function is used to establish an anomaly detection model based on the component-level health status representation, which has strong interpretability.

[0135] Comparing the training and testing effects of different models, the proposed domain adaptive causal graph convolutional anomaly detection model is denoted as "domain adaptive DWGCN". The methods compared with the domain adaptive DWGCN include commonly used data-driven anomaly detection models, namely support vector machine (SVM), artificial neural network (ANN) and convolutional neural network (CNN), as well as the classic domain adaptation (DA) method based on multi-layer perceptron (MLP). The classic domain adaptation method based on multi-layer perceptron is denoted as MLP-DA. Table 1 shows the fitting performance comparison results of different models on the training set. Tables 2 and 3 are the generalization performance comparison results of different models on the test set and 1 test 2 respectively. Among them, the fitting performance is evaluated by two indicators: precision and recall.

[0136] Table 1

[0137] Model Accuracy Recall SVM 0.90860 0.57877 ANN 0.95454 0.86301 CNN 0.96124 0.84932 MLP-DA 0.95548 0.89711 Domain Adaptive DWGCN 0.96319 0.85136

[0138] Table 2

[0139]

[0140]

[0141] Table 3

[0142] Model Accuracy Recall SVM 0.00000 0.00000 ANN 0.42708 0.24193 CNN 0.36767 0.26041 MLP-DA 0.42708 0.53125 Domain Adaptive DWGCN 0.86301 0.67568

[0143] From the above table, we can see that the commonly used data-driven models (SVM, ANN and CNN) have poor generalization effects on test set 1 and test set 2. This is because the commonly used data-driven anomaly detection models are based on the independent and identically distributed assumption and have poor adaptability to changing system operating conditions. The classic domain adaptive method has better adaptive performance to operating conditions than the commonly used data-driven model, but it is much inferior to the proposed method. In addition, the proposed adaptive anomaly detection model is based on an interpretable domain adaptive causal decoupling network and anomaly detection model, which is more credible.

[0144] In summary, the scheme provided by the embodiment of the present disclosure has the following beneficial effects: 1. Improve detection accuracy: By combining domain adaptation and causal decoupling technology, the method can more accurately identify anomalies in the electromechanical system and maintain high accuracy even when the data distribution changes. 2. Enhance model generalization ability: The domain adaptive causal decoupling network can adapt to different operating environments and working conditions, so that the model not only performs well on training data, but also can achieve effective anomaly detection on real-time monitoring data. 3. Realize component-level health status characterization: Through component-level health status characterization, the method can provide detailed health assessment for each component of the electromechanical system, which is conducive to more refined maintenance and fault prediction. 4. Causal relationship analysis: Using causal information, the method can analyze and understand the interactions and influences between the internal components of the system, thereby providing more in-depth fault diagnosis information. 5. Data-driven decision support: Based on a large amount of system monitoring data, the method provides data-driven decision support for the operation and maintenance of the electromechanical system, which helps to achieve predictive maintenance and reduce unexpected downtime. 6. Reduce maintenance costs: Through accurate anomaly detection and component-level health status assessment, the method helps to reduce unnecessary maintenance work and reduce maintenance costs. 7. Improve system reliability and safety: Timely detection and handling of potential faults will help improve the reliability and safety of electromechanical systems and prevent major accidents. 8. Strong adaptability: This method does not rely on specific equipment or systems, has good adaptability, and can be widely used in different types of complex electromechanical systems. 9. User-friendly: Through intuitive fault labels and health status characterization, this method provides users with an easy-to-understand and easy-to-operate interface, improving user experience. 10. Promote intelligent development: The implementation of this method will help promote the development of electromechanical systems towards intelligence and automation, and provide technical support for industry and intelligent manufacturing.

[0145] The following is an apparatus embodiment of the present disclosure. For parts not described in detail in the apparatus embodiment, reference may be made to the technical details disclosed in the above method embodiment.

[0146] Please refer to Fig. 9, which shows a schematic diagram of the structure of a complex electromechanical system anomaly detection device based on a domain adaptive causal decoupling network provided by an exemplary embodiment of the present disclosure. The device can be implemented in whole or in part by software, hardware, or a combination of the two, which is called a computing device. The device includes: an acquisition module 92 and a training module 94.

[0147] an acquisition module 92, configured to acquire a training data set and causal information of the electromechanical system, wherein the training data set includes system monitoring data and corresponding system fault label data, wherein the system monitoring data includes multiple variables related to the health state of the electromechanical system, the system fault label data is used to indicate whether the electromechanical system is in a fault state, and the causal information is used to indicate the functional relationship between multiple components of the electromechanical system;

[0148] The training module 94 is used to train an anomaly detection model based on a domain adaptive causal decoupling network according to the training data set and causal information. The domain adaptive causal decoupling network is used to indicate the correspondence between the system monitoring data and the component-level health status representation. The component-level health status representation is used to indicate the health status of multiple components of the electromechanical system. The anomaly detection model is used to detect anomalies in the electromechanical system.

[0149] In one possible implementation, the types of multiple variables include at least one of system monitoring parameters, system operating condition variables and system operating modes. The system monitoring parameters include variables collected by a data collection device set at a specified position of the electromechanical system. The system operating condition variables include external condition variables and / or environmental variables of the electromechanical system. The system operating mode is the operating mode adopted by the electromechanical system when implementing its functions.

[0150] In another possible implementation, the training module 94 is further configured to:

[0151] According to the training data set and causal information, a domain-adaptive causal decoupling network is trained;

[0152] Through the domain-adaptive causal decoupling network, the component-level health status representation is decoupled from the system monitoring data;

[0153] Determine the anomaly detection model based on the component-level health status characterization.

[0154] In another possible implementation, the training module 94 is further configured to:

[0155] According to the training data set and causal information, a domain-adaptive causal decoupling network is constructed. The domain-adaptive causal decoupling network includes a causal adjustment matrix and a coordinate rotation matrix. The causal adjustment matrix is ​​used to indicate the influence of system operating condition variables and / or system operating modes on causal information. The coordinate rotation matrix is ​​used to match the coordinate system of system monitoring parameters to the coordinate system of component-level health status representation.

[0156] By minimizing the loss function, the causal adjustment matrix and the coordinate rotation matrix are optimized, and a domain-adaptive causal decoupling network is trained.

[0157] In another possible implementation, the training module 94 is further configured to:

[0158] According to the component-level health status representation, a domain-stable anomaly detection model is determined. The domain-stable anomaly detection model is used to indicate the corresponding relationship between the component-level health status representation and the anomaly detection result. The anomaly detection result is used to indicate whether the electromechanical system is in a fault state.

[0159] An anomaly detection model is determined based on a domain-adaptive causal decoupling network and a domain-stable anomaly detection model.

[0160] In another possible implementation, the anomaly detection model includes: a domain-adaptive causal decoupling network and a domain-stable anomaly detection model, the input parameter of the domain-adaptive causal decoupling network is the system monitoring data, and the output parameter is the component-level health status representation; the input parameter of the domain-stable anomaly detection model is the component-level health status representation, and the output parameter is the anomaly detection result.

[0161] In another possible implementation, the apparatus further includes: a calling module, configured to:

[0162] Obtain real-time monitoring data of electromechanical systems during operation;

[0163] According to the real-time monitoring data, the pre-trained anomaly detection model is called to output the anomaly detection result, which is used to indicate whether the electromechanical system is in a fault state.

[0164] It should be noted that the device provided in the above embodiment only uses the division of the above-mentioned functional modules as an example to implement its functions. In practical applications, the above-mentioned functions can be assigned to different functional modules according to actual needs, that is, the content structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0165] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0166] An embodiment of the present disclosure further provides a computing device, the device comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0167] The embodiment of the present disclosure also provides a non-volatile computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the above method is implemented.

[0168] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of a computing device, the processor in the computing device executes the above method.

[0169] Fig.10 1 is a block diagram of an apparatus 1900 for executing a complex electromechanical system anomaly detection method based on a domain adaptive causal decoupling network according to an exemplary embodiment. For example, the apparatus 1900 may be provided as a server or a terminal device. Fig.10 , the apparatus 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as an application, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0170] The device 1900 may also include a power supply component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input / output interface 1958 (I / O interface). The device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, MacOS X™, Unix™, Linux™, FreeBSD™ or the like.

[0171] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the device 1900 to perform the above method.

[0172] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0173] A computer-readable storage medium may be a tangible device that can hold and store 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 of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0174] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0175] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state 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" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, 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., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0176] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0177] 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 device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0178] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are 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 implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0179] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0180] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A complex electromechanical system anomaly detection method based on a domain adaptive causal decoupling network, characterized in that: The method comprises: Acquire a training data set and causal information of the electromechanical system, wherein the training data set includes system monitoring data and corresponding system fault label data, wherein the system monitoring data includes a plurality of variables related to the health state of the electromechanical system, the system fault label data is used to indicate whether the electromechanical system is in a fault state, and the causal information is used to indicate the functional relationship between a plurality of components of the electromechanical system; According to the training data set and the causal information, an anomaly detection model based on a domain adaptive causal decoupling network is trained. The domain adaptive causal decoupling network is used to indicate the correspondence between the system monitoring data and the component-level health status representation. The component-level health status representation is used to indicate the health status of each of the multiple components of the electromechanical system. The anomaly detection model is used to perform anomaly detection on the electromechanical system.

2. The method according to claim 1, characterized in that The types of the multiple variables include at least one of system monitoring parameters, system operating condition variables and system operating modes. The system monitoring parameters include variables collected by a data collection device set at a specified position of the electromechanical system. The system operating condition variables include external condition variables and / or environmental variables of the electromechanical system. The system operating mode is the operating mode adopted by the electromechanical system when realizing its functions.

3. The method according to claim 1 or 2, characterized in that: The training of an anomaly detection model based on a domain adaptive causal decoupling network according to the training data set and the causal information includes: According to the training data set and the causal information, training is performed to obtain the domain adaptive causal decoupling network; Decoupling the component-level health status representation from the system monitoring data through the domain adaptive causal decoupling network; The anomaly detection model is determined according to the component-level health status representation.

4. The method according to claim 3, characterized in that: The training of the domain adaptive causal decoupling network according to the training data set and the causal information includes: According to the training data set and the causal information, a domain adaptive causal decoupling network is constructed, wherein the domain adaptive causal decoupling network includes a causal adjustment matrix and a coordinate rotation matrix, wherein the causal adjustment matrix is ​​used to indicate the influence of the system operating condition variables and / or the system operating mode on the causal information, and the coordinate rotation matrix is ​​used to match the coordinate system of the system monitoring parameters to the coordinate system of the component-level health status representation; The causal adjustment matrix and the coordinate rotation matrix are optimized by minimizing the loss function, and the domain adaptive causal decoupling network is obtained by training.

5. The method according to claim 3, characterized in that: The determining the abnormality detection model according to the component-level health status representation includes: Determining a domain-stable anomaly detection model according to the component-level health status representation, the domain-stable anomaly detection model being used to indicate a corresponding relationship between the component-level health status representation and anomaly detection results, the anomaly detection results being used to indicate whether the electromechanical system is in a fault state; The anomaly detection model is determined according to the domain adaptive causal decoupling network and the domain stable anomaly detection model.

6. The method according to claim 5, characterized in that The anomaly detection model includes: the domain adaptive causal decoupling network and the domain stable anomaly detection model, the input parameter of the domain adaptive causal decoupling network is the system monitoring data, and the output parameter is the component-level health status representation; the input parameter of the domain stable anomaly detection model is the component-level health status representation, and the output parameter is the anomaly detection result.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Acquiring real-time monitoring data of the electromechanical system during operation; According to the real-time monitoring data, the pre-trained abnormality detection model is called to output an abnormality detection result, and the abnormality detection result is used to indicate whether the electromechanical system is in a fault state.

8. A complex electromechanical system anomaly detection device based on a domain adaptive causal decoupling network, characterized in that: The device comprises: an acquisition module, configured to acquire a training data set and causal information of an electromechanical system, wherein the training data set includes system monitoring data and corresponding system fault label data, wherein the system monitoring data includes a plurality of variables related to a health state of the electromechanical system, the system fault label data is used to indicate whether the electromechanical system is in a fault state, and the causal information is used to indicate a functional relationship between a plurality of components of the electromechanical system; A training module is used to train an anomaly detection model based on a domain adaptive causal decoupling network according to the training data set and the causal information, wherein the domain adaptive causal decoupling network is used to indicate the correspondence between the system monitoring data and the component-level health status representation, the component-level health status representation is used to indicate the health status of each of the multiple components of the electromechanical system, and the anomaly detection model is used to perform anomaly detection on the electromechanical system.

9. A computing device, characterized in that The device comprises: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method described in any one of claims 1 to 7 when executing the instructions stored in the memory.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images