Cyber-physical system driven electromechanical actuator anomaly detection method and system

Abstract

This invention provides a method and system for anomaly detection of electromechanical actuators based on cyber-physical fusion, belonging to the field of computer data processing technology. It integrates physical mechanisms with a dynamic priority generation mechanism based on random exploration, significantly improving the sensitivity of anomaly detection and the efficiency of system resource utilization while ensuring comprehensive detection. By constructing a deep fusion framework of physical mechanism models and data-driven models, this invention solves the problems of resource waste and detection blind spots under traditional fixed or polling strategies, significantly improving the efficiency of system resource utilization and the real-time response capability of detection. It introduces a closed-loop control process of resource idle prediction and dynamic supplementary inspection, actively recovering computing resources saved from healthy data sources and immediately reinvesting them in other high-risk potential fault points, achieving dynamic expansion of the detection coverage. This enhances the system's robustness in dealing with concurrent anomalies and complex operating conditions, achieving a synergistic improvement in detection comprehensiveness and efficiency.

Description

Technical Field

[0001] This invention relates to the field of computer data processing technology, and in particular to a method and system for detecting anomalies in electromechanical actuators based on cyber-physical fusion. Background Technology

[0002] As core execution units in modern industrial equipment, the reliability of electromechanical actuators directly affects the safety and performance of the entire system. With the development of cyber-physical systems technology, real-time sensing and dynamic control of electromechanical actuators through the integration of computing, communication, and control technologies has become an important trend. Against this backdrop, utilizing computer systems to process massive amounts of sensor data to achieve early anomaly detection of electromechanical actuators is a key technological aspect for ensuring their reliable operation.

[0003] In existing technologies, anomaly detection methods for electromechanical actuators are mainly divided into two categories. One is based on precise physical models, which predict normal behavior by establishing a mathematical model of the actuator. When the actual measured value deviates from the model's prediction, it is judged as an anomaly. The other utilizes machine learning or deep learning algorithms to learn normal behavior patterns from massive amounts of historical operating data and identify data that deviates from these patterns. In multi-sensor monitoring scenarios, the system typically uses a fixed priority or simple polling strategy to allocate computing resources, processing information from different data sources sequentially.

[0004] However, the aforementioned existing technical solutions have obvious drawbacks. Physical model-based methods require extremely high model accuracy and are difficult to cope with model mismatch problems caused by dynamic factors such as equipment aging and changes in operating conditions. Pure data-driven methods rely heavily on a large number of well-labeled fault samples. For early faults or novel unknown faults with sparse samples, their generalization ability and detection reliability are insufficient. Static resource allocation strategies make it difficult for the system to balance comprehensiveness and efficiency. Indiscriminate monitoring of all data sources will cause huge waste of resources, while selective monitoring is prone to creating detection blind spots, leading to the omission of key abnormal signals. Summary of the Invention

[0005] This invention provides a method and system for detecting anomalies in electromechanical actuators based on cyber-physical fusion, which integrates physical mechanisms with a dynamic priority generation mechanism of random exploration. While ensuring comprehensive detection, it significantly improves the sensitivity of anomaly detection and the efficiency of system resource utilization.

[0006] To address the aforementioned issues, embodiments of the present invention provide an electromechanical actuator anomaly detection method and system based on cyber-physical fusion, which integrates physical mechanisms with a dynamic priority generation mechanism of random exploration, thereby significantly improving the sensitivity of anomaly detection and the efficiency of system resource utilization while ensuring comprehensive detection.

[0007] The first aspect of this invention provides a method for detecting anomalies in electromechanical actuators based on cyber-physical fusion, comprising: S101: Establish a mechanistic model of the electromechanical actuator; S102: Acquire the first feature data and the second feature data of the electromechanical actuator, and perform feature processing. The first feature data is physical sensor data, and the second feature data is information source data. S103: Calculate the degree of conformity between the operating state and the theoretical behavior based on the mechanism model and feature processing results, and generate a fusion index; S104: Generate a first sequence and a second sequence, and construct a dynamic priority list. The first sequence is a random perturbation sequence, and the second sequence is a fusion degree guidance sequence. S105: Select the focus data source according to the dynamic priority list, perform anomaly detection on the focus data source, and generate preliminary anomaly detection results; S106: Monitor the computing resources released during the detection process, select high-priority non-focus data sources for supplementary detection, and update the anomaly detection results.

[0008] In one optional implementation, the establishment of the mechanism model of the electromechanical actuator includes a core set of dynamic equations comprising electromagnetic dynamics equations, mechanical dynamics equations, and thermodynamic equations, which are used to describe the electromagnetic, mechanical, and thermodynamic responses of the actuator when it receives a specific control command.

[0009] In one optional implementation, feature processing is performed on the first feature data and the second feature data, including extracting time-domain features and frequency-domain features to form an initial feature set, performing dimensionality reduction processing on the initial feature set, and normalizing and fusing the dimensionality-reduced feature set to generate a comprehensive feature vector.

[0010] In one alternative implementation, the time-domain features are obtained by averaging the overall amplitude, dispersion, and impulsiveness of the signal, and the frequency-domain features are obtained by performing a fast Fourier transform on the time-series data.

[0011] In one optional implementation, the physical sensor data includes vibration acceleration, current, temperature, and displacement signals, and the information source data includes at least one of control commands, target rotational speed, load torque, and medium temperature.

[0012] In one alternative implementation, generating a dynamic priority list includes obtaining the system load parameters of the current system, adjusting the weight ratio of the first sequence and the second sequence in the dynamic weight function according to the system load parameters, and applying the adjusted dynamic weight function to perform a weighted combination of the first sequence and the second sequence.

[0013] In one optional implementation, acquiring first and second characteristic data of the electromechanical actuator includes at least two physical sensors and an information source data acquisition module, with the physical sensors deployed at key parts of the actuator.

[0014] A second aspect of this invention provides an electromechanical actuator anomaly detection system based on cyber-physical fusion, the system comprising: The model building module is used to establish the mechanistic model of electromechanical actuators. The data processing module is used to acquire the first and second feature data of the electromechanical actuator and perform feature processing. The fusion degree calculation module is used to calculate the degree of conformity between the running state and the theoretical behavior based on the mechanism model and feature processing results, and generate the fusion degree index. The priority list module is used to generate the first and second sequences and construct a dynamic priority list. The anomaly detection module is used to select the focus data source based on the dynamic priority list, perform anomaly detection on the focus data source, and generate preliminary anomaly detection results. The supplementary inspection and update module is used to monitor the computing resources released during the detection process, select high-priority non-focus data sources for supplementary inspection, and update the abnormal detection results.

[0015] A third aspect of the present invention provides an electronic device, characterized in that it includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described electromechanical actuator anomaly detection method based on cyber-physical fusion.

[0016] A fourth aspect of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the above-described electromechanical actuator anomaly detection method based on cyber-physical fusion drive.

[0017] The present invention has at least the following advantages or beneficial effects: (1) Integration and accuracy: This invention improves the sensitivity and accuracy of identifying weak fault characteristics such as early and gradual changes by constructing a deep integration framework of physical mechanism model and data-driven model and using the integration degree index as the core benchmark, effectively reducing the false alarm rate.

[0018] (2) Efficient resource allocation: The random exploration strategy that ensures broad coverage is adaptively integrated with the physical guidance strategy that focuses on high-risk areas, so that monitoring resources can be intelligently allocated according to the real-time load and health status of the system, which solves the problems of resource waste and detection blind spots under the traditional fixed or polling strategy.

[0019] (3) Strong robustness: The closed-loop control process of resource idle prediction and dynamic supplementary inspection is introduced. By actively recovering the computing resources saved on healthy data sources and immediately reinvesting them in other high-risk potential fault points, the detection coverage is dynamically expanded, which enhances the system's robustness in dealing with concurrent anomalies and complex working conditions.

[0020] (4) Highly practical: It provides a complete solution from sensor deployment, data acquisition, algorithm analysis to system integration, which is easy to apply and promote in engineering and is suitable for condition monitoring and health management of various electromechanical actuators. Attached Figure Description

[0021] Figure 1 A flowchart illustrating the anomaly detection method for electromechanical actuators based on cyber-physical fusion driven by embodiments of the present invention. Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0023] In this embodiment of the invention, "instruction" can include direct and indirect instructions, as well as explicit and implicit instructions. The information indicated by a certain piece of information is called the information to be instructed. In specific implementation, there are many ways to instruct the information to be instructed, such as, but not limited to, directly instructing the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly instruct the information to be instructed by instructing other information, where there is a correlation between the other information and the information to be instructed. It can also instruct only a part of the information to be instructed, while the other parts are known or pre-agreed upon. For example, the instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. Simultaneously, common parts of various pieces of information can be identified and uniformly indicated to reduce the instruction overhead caused by individually indicating the same information.

[0024] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be elaborated upon here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In specific implementation, the required indication method can be selected according to specific needs. This embodiment of the invention does not limit the selected indication method; therefore, the indication methods involved in this embodiment of the invention should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0025] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information messages sent separately, and the sending period and / or timing of these sub-information messages can be the same or different. The specific sending method is not limited in this embodiment of the invention. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the sending device by sending configuration information to the receiving device.

[0026] "Predefined" or "pre-configured" can be achieved by pre-saving corresponding codes, tables, or other means that can be used to indicate relevant information in the device. This embodiment of the invention does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or electronic device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or electronic device. The type of memory can be any form of storage medium, and this embodiment of the invention does not limit this.

[0027] In the embodiments of this invention, "protocol" may refer to a protocol family in the field of communication, a standard protocol with a similar protocol family frame structure, or a related protocol applied to a future electromechanical actuator anomaly detection method and system based on cyber-physical fusion. The embodiments of this invention do not specifically limit this.

[0028] In this embodiment of the invention, descriptions such as "when," "under the circumstances," "if," and "if" all refer to the device making corresponding processing under certain objective circumstances, and are not limited to a specific time. They do not require the device to make a judgment action during implementation, nor do they imply any other limitations.

[0029] In the description of the embodiments of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. "And / or" in the embodiments of the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Furthermore, in the description of the embodiments of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple. Additionally, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first," "second," etc., do not limit the quantity or order of execution, and that "first," "second," etc., are not necessarily different. Furthermore, in the embodiments of this invention, words such as "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0030] The network architecture and business scenarios described in the embodiments of this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0031] Figure 1 This is a flowchart illustrating the method provided in an embodiment of the present invention. The specific process of this electromechanical actuator anomaly detection method based on cyber-physical fusion is as follows: S101: Establish a mechanistic model of the electromechanical actuator; In this embodiment, a mechanistic model is established to define the theoretical behavior of the electromechanical actuator. The mechanistic model quantifies the degree of deviation between the actual operating state of the electromechanical actuator and its theoretical ideal state, thereby generating a fusion index. The theoretical behavior is simulated by using a preset electromechanical actuator mechanistic model. This mechanistic model is a mathematical expression based on physical laws, which can describe the electromagnetic, mechanical and thermodynamic response of the actuator when it receives a specific control command. The acquired second characteristic data, such as the target position or speed command issued by the control system, is used as the input of the mechanistic model. Based on these inputs, the model solves its internal dynamic equations to simulate in real time the output signal waveform that the physical sensor should have under fault-free ideal operating conditions. The mechanistic model describes the electromagnetic, mechanical, and thermodynamic responses of an actuator under specific control commands, and its core dynamic equations are: Electromagnetic dynamics equations: ; in, Armature voltage, For armature resistance, For armature current, For armature inductance, The back electromotive force coefficient, This represents the angular velocity of the motor.

[0032] Mechanical dynamics equations: ; in, For electromagnetic torque, For load torque, For rotational inertia, is the damping coefficient.

[0033] Thermodynamic equation: ; in, For heat capacity, For winding temperature, For copper loss, For heat dissipation coefficient, For heat dissipation area, The ambient temperature.

[0034] S102: Acquire the first and second feature data of the electromechanical actuator and perform feature processing; In this embodiment, first feature data and second feature data of the electromechanical actuator are acquired. The first feature data is physical sensor data, and the second feature data is information source data.

[0035] Physical sensors are mounted on key parts of electromechanical actuators, such as the coil end, gearbox housing, bearing housing, and connecting rod connection, using magnetic bases or adhesive methods. Information source data is acquired through an acquisition module integrated into the control system, and data acquisition is achieved through at least two physical sensors and one information source data acquisition module.

[0036] The first and second feature data are processed using the following steps: 1. Extract the time-domain and frequency-domain features of the first and second feature data to form an initial feature set. The time-domain features are obtained by mean quantization of the overall amplitude, dispersion, and impulsiveness of the signal. The frequency-domain features are obtained by performing a fast Fourier transform on the time series data. 2. Perform dimensionality reduction processing on the initial feature set to generate dimensionality-reduced features. The dimensionality reduction processing selects principal components that can explain the variance, retains core information while removing noise and secondary information, and obtains a dimensionality-reduced feature set with lower dimensionality and more concentrated information. 3. Normalize and fuse the dimensionality-reduced feature set, converting each feature value into the value of its deviation from the mean divided by the standard deviation, eliminating the scale difference between different features, and generating a comprehensive feature vector.

[0037] Principal Component Analysis (PCA) is an unsupervised learning method that aims to map original high-dimensional data to a low-dimensional space through linear transformation, while preserving the variance of the data as much as possible. The basic steps of implementing PCA in matrix operations are as follows: First, mean the sample data and subtract it from the original data to obtain the covariance matrix; then, calculate the eigenvalues ​​and eigenvectors of this matrix and sort them according to the magnitude of the eigenvalues; finally, truncate the main eigenvectors according to the required data dimension, thereby reducing data redundancy and preventing the drowning out of effective features during the dimensionality reduction process.

[0038] The formula for maximizing the variance of a data sample projected onto its dimension after dimensional transformation is: ; In the formula: For data sample dimensions; For the target subspace dimensional vector; It is the average vector.

[0039] Sample data Dimensional reduction Dimensional Data Its implementation formula is:

[0040] The reduced feature set is normalized and fused by converting each feature value into its deviation from the mean divided by the standard deviation, thus eliminating scale differences between different features and generating the comprehensive feature vector; let the reduced feature set be... ,in The feature dimensions after dimensionality reduction. For the first The original values ​​of each dimensionality-reduced feature. Standardization is performed on each feature value: ; It is the first The mean of each feature in the sample set is given by the formula: ; in, For the sample size, For the first The first sample One eigenvalue; It is the first The standard deviation of a feature within the sample set is given by the formula: ; Combine all standardized feature values ​​in their original dimensional order to generate a comprehensive feature vector. ; S103: Calculate the degree of conformity between the operating state and the theoretical behavior based on the mechanism model and feature processing results, and generate a fusion index; In this embodiment, the acquired second feature data is used as the input to the mechanism model. Based on the input, the model solves the dynamic equations to simulate the output signal waveform that the physical sensor should have under ideal working conditions without faults.

[0041] The simulated signal is subjected to the same feature extraction and dimensionality reduction fusion process as when generating the comprehensive feature vector, generating a theoretical feature vector that matches the comprehensive feature vector.

[0042] The geometric distance between the integrated feature vector and the theoretical feature vector in the feature space is calculated using Euclidean distance to determine the difference between real-world measurements and cyber-physical model predictions. The formula is as follows: ; Where D represents the degree of difference, A i B is the i-th component of the composite eigenvector. iThis is the i-th component of the theoretical feature vector. The geometric distance between the two vectors in the feature space is calculated, and based on the calculated dissimilarity D, a final fusion index is generated through a non-linear mapping function. This index aims to transform unbounded dissimilarity into a bounded, intuitive consistency score; for example, an exponential function like the following can be used: C = exp(-α*D); Where C is the integration index, with a value range between 0 and 1, exp is the natural exponential function, and α is an adjustable sensitivity coefficient used to control the decay rate of the index as the degree of difference changes. It can be calibrated through historical data or set according to the tolerance of the application scenario. When the degree of difference D approaches 0, the index C approaches 1, indicating that the physical system is highly consistent with the model. When the degree of difference increases, the index C decreases rapidly, indicating that the system state deviates seriously from the theoretical expectation.

[0043] By introducing a pre-defined electromechanical actuator mechanism model as a reference, the paradigm of anomaly detection is elevated from simple data statistical anomalies to the level of system-level physical law imbalances.

[0044] S104: Generate the first and second sequences, and construct a dynamic priority list. In this embodiment, a first sequence and a second sequence are generated. The first sequence is a random perturbation sequence, and the second sequence is a fusion degree guide sequence.

[0045] All data sources are randomly sorted to generate the first sequence; the time series changes of the integration index are monitored; the data sources are sorted according to the degree of deterioration of the integration index to generate the second sequence.

[0046] A dynamic priority list is generated by fusing the first sequence and the second sequence using a dynamic weighting function. The specific steps are as follows: 1. Obtain the current system load parameters. These parameters are real-time indicators that measure the stress on system computing resources. They can typically be quantified as a combination of CPU utilization, memory usage, or network bandwidth, and normalized to a value between 0 and 1. ; 2. Adjust the weight ratio of the first sequence and the second sequence in the dynamic weighting function according to the system load parameters. Let the weight of the second sequence be Wc, the weight of the first sequence be Wr, and the sum of the two be 1. The weights can be determined by the following logistic function: ; Where L is the current system load parameter, L0 is a preset load threshold, usually set to 0.5, representing a moderate system load, and k is a positive gain coefficient used to adjust the sensitivity of the weights to changes in load. This formula ensures that when the system load L is low, Wc is small, resulting in a larger weight Wr for the first sequence, and the system tends to explore broadly; when the system load L is high, Wc is close to 1, and the system tends to focus on the high-risk data sources indicated by the second sequence.

[0047] 3. Apply the adjusted weights to perform a weighted fusion of the two sequences. For each data source j, calculate its final priority score FinalScore(j) based on its rank in the second sequence Rankc(j) and its rank in the first sequence Rankr(j): ; The smaller the ranking value, the higher the priority. After calculating the final priority score of all data sources, all data sources are sorted in ascending order of the score. The resulting new sorted list is the final dynamic priority list.

[0048] S105: Select the focus data source according to the dynamic priority list, perform anomaly detection on the focus data source, and generate preliminary anomaly detection results; In this embodiment, the data source with the highest ranking is selected as the focus data source according to the dynamic priority list, and the comprehensive feature vector of the focus data source is input into the anomaly classification algorithm to generate a preliminary anomaly probability.

[0049] The initial anomaly probability is corrected based on the fusion degree index, and an initial anomaly detection result is generated based on the corrected initial anomaly probability.

[0050] S106: Monitor the computing resources released during the detection process, select high-priority non-focus data sources for supplementary detection, and update the anomaly detection results; In this embodiment, the detection process of the focus data source is monitored, and the computing resources released due to the shortened detection time are predicted. The specific steps are as follows: (1) Evaluate the stability of the fusion index of the focal data source. The stability calculation formula is as follows: ; in, To assess the time window, The mean blending degree within the window. The smaller the value, the more stable the integration.

[0051] when ( To stabilize the threshold, shorten the detection time and calculate the resource release amount. Generate resource idle prediction signals.

[0052] (2) Dynamic supplementary inspection scheduling: Select non-focus data sources with a priority higher than the supplementary inspection eligibility threshold from the dynamic priority list to form a candidate supplementary inspection list; Based on resource release To allocate resources to the candidate list, the resource allocation formula supporting parallel detection is as follows: ; in, Candidate data sources Priority ranking ensures that high-priority data sources receive more resources; Finally, parallel anomaly detection is performed on the data source that obtained the resources, and supplementary detection results are generated and integrated into the anomaly detection results.

[0053] This invention also provides an electromechanical actuator anomaly detection system based on cyber-physical fusion, the system comprising: The model building module is used to establish the mechanistic model of electromechanical actuators. The data processing module is used to acquire the first and second feature data of the electromechanical actuator and perform feature processing. The fusion degree calculation module is used to calculate the degree of conformity between the running state and the theoretical behavior based on the mechanism model and feature processing results, and generate the fusion degree index. The priority list module is used to generate the first and second sequences and construct a dynamic priority list. The anomaly detection module is used to select the focus data source based on the dynamic priority list, perform anomaly detection on the focus data source, and generate preliminary anomaly detection results. The supplementary inspection and update module is used to monitor the computing resources released during the detection process, select high-priority non-focus data sources for supplementary inspection, and update the abnormal detection results.

[0054] Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Exemplarily, the electronic device may be a network device, or a chip (system) or other component or assembly that can be disposed in a network device. Figure 2 As shown, the electronic device 400 may include a processor 401. Optionally, the electronic device 400 may also include a memory 402 and / or a transceiver 403. The processor 401 is coupled to the memory 402 and the transceiver 403, for example, via a communication bus.

[0055] The following is combined Figure 2 A detailed description of each component of the electronic device 400 is provided below: The processor 401 is the control center of the electronic device 400. It can be a single processor or a collective term for multiple processing elements. For example, the processor 401 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0056] Optionally, the processor 401 can perform various functions of the electronic device 400 by running or executing software programs stored in the memory 402 and calling data stored in the memory 402, such as performing the aforementioned functions. Figure 2 The method and system for detecting anomalies in electromechanical actuators based on cyber-physical fusion are shown.

[0057] In a specific implementation, as one example, processor 401 may include one or more CPUs, for example... Figure 2 CPU0 and CPU1 are shown in the diagram.

[0058] In a specific implementation, as one example, the electronic device 400 may also include multiple processors. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0059] The memory 402 is used to store the software program that executes the solution of the present invention, and is controlled by the processor 401 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0060] Optionally, the memory 402 may be a read-only memory or other type of static storage device capable of storing static information and instructions, a random access memory or other type of dynamic storage device capable of storing information and instructions, or an electrically erasable programmable read-only memory, a read-only optical disc or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 402 may be integrated with the processor 401 or may exist independently and be accessible through the interface circuit of the electronic device 400. Figure 2 (Not shown in the image) is coupled to processor 401, but this embodiment of the invention does not specifically limit this.

[0061] Transceiver 403 is used for communication with other electronic devices. For example, if electronic device 400 is a terminal, transceiver 403 can be used to communicate with a network device or with another terminal device. As another example, if electronic device 400 is a network device, transceiver 403 can be used to communicate with a terminal or with another network device.

[0062] Alternatively, transceiver 403 may include a receiver and a transmitter. Figure 2 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0063] Optionally, the transceiver 403 can be integrated with the processor 401, or it can exist independently and be connected via the interface circuit of the electronic device 400. Figure 2 (Not shown in the image) is coupled to processor 401, but this embodiment of the invention does not specifically limit this.

[0064] Understandable, Figure 2 The structure of the electronic device 400 shown does not constitute a limitation on the electronic device. Actual electronic devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0065] Furthermore, the technical effects of the electronic device 400 can be referred to the technical effects of the electromechanical actuator anomaly detection method and system based on cyber-physical fusion driving described in the above method embodiments, and will not be repeated here.

[0066] It should be understood that the processor in the embodiments of the present invention can be a central processing unit, or it can be other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0067] It should also be understood that the memory in the embodiments of the present invention may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, or flash memory. The volatile memory may be random access memory, which serves as an external cache. By way of example, but not limitation, many forms of random access memory are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronously linked dynamic random access memory, and direct memory bus random access memory.

[0068] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0069] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0070] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0071] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0072] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0073] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0074] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0077] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0078] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for detecting anomalies in electromechanical actuators based on cyber-physical fusion, characterized in that, This method is applied to a detection terminal and includes the following steps: Acquire first feature data and second feature data of the electromechanical actuator, wherein the first feature data is physical sensor data and the second feature data is information source data; The first and second feature data are subjected to feature processing to generate a comprehensive feature vector. Obtain the mechanistic model used to define the theoretical behavior of the electromechanical actuator; Based on the comprehensive feature vector and the mechanism model, the degree of conformity between the operating state and the theoretical behavior is calculated, and a fusion index is generated. A first sequence and a second sequence are generated, wherein the first sequence is a random perturbation sequence and the second sequence is a fusion degree indicator sequence, and the second sequence is determined according to the changing trend of the fusion degree index. The first sequence and the second sequence are fused using a dynamic weighting function to generate a dynamic priority list; Select a focus data source based on the dynamic priority list, perform anomaly detection on the focus data source, and generate anomaly detection results.

2. The method for detecting anomalies in electromechanical actuators based on cyber-physical fusion drive according to claim 1, characterized in that, Feature processing is performed on the first feature data and the second feature data to generate a comprehensive feature vector, including: Extract the time-domain and frequency-domain features of the first and second feature data to form an initial feature set. The time-domain features are obtained by mean quantization of the overall amplitude, dispersion, and impulsiveness of the signal. The frequency-domain features are obtained by performing a fast Fourier transform on the time series data. The initial feature set is subjected to dimensionality reduction processing to generate dimensionality-reduced features. The dimensionality reduction processing selects principal components that can explain the variance, retains core information while removing noise and secondary information, and obtains a dimensionality-reduced feature set with lower dimensionality and more concentrated information. The reduced feature set is normalized and fused, and each feature value is converted into the value of its deviation from the mean divided by the standard deviation, thereby eliminating the scale difference between different features and generating the comprehensive feature vector.

3. The electromechanical actuator anomaly detection method based on cyber-physical fusion drive according to claim 2, characterized in that, Based on the comprehensive feature vector and the mechanism model, the degree of conformity between the operating state and the theoretical behavior is calculated, and a fusion index is generated, including: The mechanism model describes the electromagnetic, mechanical and thermodynamic response of the actuator when it receives a specific control command. The acquired second characteristic data is used as the input of the mechanism model. Based on the input, the model solves the dynamic equations to simulate the output signal waveform that the physical sensor should have under fault-free ideal working conditions. The simulated signal performs the same feature extraction and dimensionality reduction fusion process as when generating the comprehensive feature vector, generating a theoretical feature vector that matches the comprehensive feature vector; The geometric distance between the integrated feature vector and the theoretical feature vector in the feature space is calculated by Euclidean distance to determine the difference between the real-world measurement value and the prediction value of the cyber-physical model. Based on the calculated degree of difference, the final degree of integration index is generated through an exponential function, and the degree of difference is converted into a consistency score.

4. The electromechanical actuator anomaly detection method based on cyber-physical fusion drive according to claim 3, characterized in that, Generate a first sequence and a second sequence, wherein the first sequence is a random perturbation sequence and the second sequence is a fusion degree guide sequence, including: Randomly sort all data sources to generate the first sequence; Monitor the time series changes of the aforementioned fusion index; The data sources are sorted according to the degree of deterioration of the fusion index to generate the second sequence.

5. The method for detecting anomalies in electromechanical actuators based on cyber-physical fusion drive according to claim 1, characterized in that, By fusing the first sequence and the second sequence using a dynamic weighting function, a dynamic priority list is generated, including: Get the current system load parameters; The weight ratio of the first sequence and the second sequence in the dynamic weight function is adjusted according to the system load parameters. The first sequence and the second sequence are weighted and combined using the adjusted dynamic weight function to generate the dynamic priority list.

6. The method for detecting anomalies in electromechanical actuators based on cyber-physical fusion drive according to claim 5, characterized in that, Select a focus data source based on the dynamic priority list, perform anomaly detection on the focus data source, and generate anomaly detection results, including: The comprehensive feature vector of the focal data source is input into the anomaly classification algorithm to generate a preliminary anomaly probability; The initial anomaly probability is corrected based on the fusion degree index; The anomaly detection result is generated based on the corrected preliminary anomaly probability.

7. The electromechanical actuator anomaly detection method based on cyber-physical fusion drive according to claim 1, characterized in that, It also includes the following steps: Monitor the detection process of the focal data source and predict the computing resources released due to the shortened detection time; Based on the dynamic priority list and the released computing resources, select high-priority data sources that have not been focused for supplementary inspection; Perform anomaly detection on the high-priority data source and update the anomaly detection results.

8. The electromechanical actuator anomaly detection method based on cyber-physical fusion drive according to claim 7, characterized in that, Monitoring the detection process of the focal data source and predicting the computing resources released due to the shortened detection time includes: Evaluate the stability of the integration index of the focal data source; When the stability is higher than the stability threshold, the detection time is shortened and the corresponding resource release amount is calculated. Based on the resource release amount, a resource idle prediction signal is generated.

9. The electromechanical actuator anomaly detection method based on cyber-physical fusion drive according to claim 7, characterized in that, Based on the dynamic priority list and the released computing resources, select high-priority data sources that have not been focused for supplementary inspection, including: Non-focus data sources with priority higher than the re-inspection eligibility threshold are selected from the dynamic priority list to form a candidate re-inspection list; The released computing resources are allocated to the data sources in the candidate supplementary inspection list; Parallel anomaly detection is performed on the data source that obtained the resources, and supplementary detection results are generated and integrated into the anomaly detection results.

10. The electromechanical actuator anomaly detection method based on cyber-physical fusion drive according to any one of claims 1-9, further comprising an electromechanical actuator anomaly detection system based on cyber-physical fusion drive, characterized in that, include: The data acquisition module is used to acquire the first feature data and the second feature data of the electromechanical actuator; The feature processing module is used to perform feature processing on the first feature data and the second feature data to generate a comprehensive feature vector; The consistency calculation module is used to obtain the mechanism model used to define the theoretical behavior of the electromechanical actuator, and calculate the degree of conformity between the operating state and the theoretical behavior based on the comprehensive feature vector and the mechanism model, and generate a fusion index. A sequence generation module is used to generate a first sequence and a second sequence, wherein the first sequence is a random perturbation sequence and the second sequence is determined according to the changing trend of the fusion index. The list generation module is used to fuse the first sequence and the second sequence through a dynamic weighting function to generate a dynamic priority list; The anomaly detection module is used to select a focus data source according to the dynamic priority list, perform anomaly detection on the focus data source, and generate anomaly detection results.

Images