Fault-tolerant control method and device for synchronous motor controllable fault library

Abstract

This invention provides a fault-tolerant control method and apparatus for a controllable fault library of a synchronous motor, belonging to the field of motor equipment fault diagnosis technology. The method includes: multi-domain feature extraction and standardization processing. A weighted distance model is used to calculate the matching distance between the standardized feature vector and various fault templates in the controllable fault library. Feature weights reflect the differences in importance of different features for fault identification, giving features with higher fault sensitivity a higher weight in the matching calculation. The current fault type is determined based on the fault matching result, and the associated control strategy in the controllable fault library is called according to the fault type identification result. This achieves a direct mapping between fault diagnosis results and control strategies, solving the technical problem of the disconnect between fault diagnosis and control strategies in traditional methods, and improving the operational stability and reliability of synchronous motors under complex operating conditions.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology for motor equipment, and in particular to a fault-tolerant control method and device for a controllable fault library of synchronous motors. Background Technology

[0002] Synchronous motors are prone to various electromagnetic faults, such as excitation flux imbalance, stator negative sequence current, torque pulsation, local magnetic saturation, abnormal temperature rise, and harmonic distortion. These faults are often coupled with each other and exhibit complex manifestations, making it difficult for traditional diagnostic methods that rely on single-feature judgments or fixed thresholds to accurately identify multiple complex fault types simultaneously.

[0003] Existing technologies primarily rely on fixed control strategies, failing to implement differentiated and adaptive suppression control based on the characteristics of different faults and changes in operating conditions. This means that once a fault occurs, the system cannot flexibly adjust control parameters and strategies to achieve the best suppression effect, thus limiting the improvement of system performance.

[0004] Traditional fault-tolerant control processes in motor controllable fault libraries are typically independent, and diagnostic results cannot directly and effectively guide the selection and optimization of control strategies. This disconnect prevents the system from achieving coordinated optimization of diagnosis and control when facing dynamically changing faults and operating conditions, thereby exacerbating problems such as enhanced electromagnetic force waves, increased vibration, and decreased efficiency. Summary of the Invention

[0005] This invention provides a fault-tolerant control method and apparatus for a controllable fault library of a synchronous motor, which solves the shortcomings of existing fault diagnosis methods, such as limited diagnostic capabilities, fixed control strategies, and inability to adaptively optimize with changes in operating conditions, thereby improving the operating stability and reliability of the motor under complex operating conditions.

[0006] In a first aspect, the present invention provides a fault-tolerant control method for a controllable fault library of a synchronous motor, comprising: Multi-domain feature extraction and standardization processing are performed on multi-source operating data during the operation of synchronous motors to obtain standardized feature vectors. The standardized feature vector is input into the controllable fault database, and the matching distance between the standardized feature vector and various fault templates in the controllable fault database is calculated using a weighted distance model to obtain the fault matching result. The current fault type is determined based on the fault matching results, and a fault type discrimination result is obtained. Based on the fault type identification result, the control strategy associated with the fault type in the controllable fault library is invoked to obtain the fault suppression control instruction.

[0007] Furthermore, after obtaining the fault suppression control command, the method further includes: The fault suppression operation is executed according to the fault suppression control command, and the vibration index, torque fluctuation index and magnetic flux deviation index after suppression are collected to obtain the suppression effect feedback data. The suppression effect feedback data is evaluated based on the comprehensive error evaluation function to obtain the suppression effect evaluation value. The comprehensive error evaluation function is a weighted combination of the vibration index, torque fluctuation index and magnetic flux deviation index. If the suppression effect evaluation value exceeds a preset threshold, the feature weight parameters in the controllable fault database are updated by gradient based on the suppression effect evaluation value to obtain updated feature weight parameters. The updated feature weight parameters are then stored to achieve online self-learning optimization of the controllable fault database. If the threshold is not exceeded, the control process ends.

[0008] Furthermore, the multi-domain feature extraction and standardization processing of multi-source operating data during the synchronous motor operation to obtain a standardized feature vector includes: Multi-source operating data during the operation of the synchronous motor are collected and preprocessed by synchronization, filtering and normalization to obtain the preprocessed multi-source signal. The time-domain statistical features, frequency-domain energy distribution features, harmonic component features, and current and flux linkage space vector features in the dq coordinate system are extracted from the preprocessed multi-source signal to obtain the multi-domain feature vector. The multi-domain feature vectors are standardized to obtain standardized feature vectors.

[0009] Furthermore, the controllable fault library includes fault templates for excitation flux imbalance, stator negative sequence current, torque pulsation, local magnetic saturation, abnormal temperature rise, and harmonic distortion. Each fault template includes a feature template vector unit, a control strategy unit, and an adaptive weight update unit.

[0010] Furthermore, the current fault type is determined from the fault matching results based on the principle of minimum feature distance or maximum similarity, thus obtaining the fault type discrimination result.

[0011] Furthermore, based on the fault type determination result, the step of invoking the controllable fault database for a controllable fault type associated with that fault type to obtain a fault suppression control instruction includes: Determine the fault type of the fault type identification result. If the fault type is excitation flux imbalance, local magnetic saturation, or magnetomotive force fluctuation, then invoke the excitation side control strategy to adjust the amplitude and phase of the excitation current according to the flux deviation characteristics and generate a compensating magnetic field opposite to the flux deviation caused by the fault. If the fault type is stator negative sequence current type or harmonic distortion type, the stator side sub-current control strategy is invoked, and the stator sub-current reference value is adjusted through dual-channel compensation to generate a compensation current that is opposite to the negative sequence current component or harmonic component. If the fault type is a torque pulsation type or a multi-source coupling fault, the joint coordinated control strategy is invoked to synchronously execute the excitation side control strategy and the stator side sub-current control strategy, and the adjustment weights of the excitation side and the stator side are dynamically allocated according to the fault deviation, so that the flux distribution and current vector are coordinated in space and time, and the electromagnetic force wave and flux imbalance are synchronously suppressed.

[0012] Furthermore, the stator current reference value is adjusted through a dual-channel compensation method, specifically using the following formula: ; Among them, i s ( t () represents the actual stator current vector. i ref This is the reference template current in the controllable fault database. K c This is the vector correction coefficient.

[0013] Furthermore, the inhibition effect evaluation value is assessed using an error evaluation function, the specific formula of which is: ; in, Evaluation value of inhibition effect M v For vibration index, T g For torque ripple indicators, H d This is an index of magnetic flux deviation. α , β , γ These are the weighting coefficients; like If the value exceeds the preset threshold, the gradient is updated using the following formula: ; in, η For learning rate, For the updated feature weight parameters, These are the current feature weight parameters; When the control effect meets the target, the parameters are updated and the control is terminated to achieve closed-loop optimization.

[0014] Secondly, the present invention also provides a fault-tolerant control device for a controllable fault library of a synchronous motor, comprising: The data processing module is used to perform multi-domain feature extraction and standardization on multi-source operating data during the operation of synchronous motors to obtain standardized feature vectors. The fault matching module is used to input the standardized feature vector into the controllable fault database, and use a weighted distance model to calculate the matching distance between the standardized feature vector and various fault templates in the controllable fault database to obtain the fault matching result. The fault identification module is used to determine the current fault type based on the fault matching result and obtain the fault type discrimination result; The control strategy generation module is used to call the control strategy associated with the fault type in the controllable fault library based on the fault type discrimination result to obtain the fault suppression control instruction.

[0015] Thirdly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the fault-tolerant control method of the synchronous motor controllable fault library as described above.

[0016] The fault-tolerant control method and apparatus for a controllable fault library of synchronous motors provided by this invention eliminates the differences in the dimensions of different features through multi-domain feature extraction and standardization processing. This transforms multi-source operating data such as voltage, current, excitation current, speed, temperature, and vibration into a unified scale, improving the accuracy and stability of feature matching. A weighted distance model is used to calculate the matching distance between the standardized feature vector and various fault templates in the controllable fault library. Feature weights reflect the differences in the importance of different features to fault identification, giving features with higher fault sensitivity a higher weight in the matching calculation. The current fault type is determined based on the fault matching result, and the associated control strategy in the controllable fault library is invoked according to the fault type identification result. This achieves a direct mapping between fault diagnosis results and control strategies, solving the technical problem of the disconnect between fault diagnosis and control strategies in traditional methods. The system can automatically select and execute corresponding excitation-side control strategies, stator-side sub-current control strategies, or joint collaborative control strategies for different fault types. This realizes adaptive collaboration in the fault-tolerant control of the controllable fault library of the motor, improving the operational stability and reliability of the synchronous motor under complex operating conditions. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1This is a flowchart illustrating an optional fault-tolerant control method for a controllable fault library of a synchronous motor provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of a fault-tolerant control system for an optional controllable fault library of a synchronous motor, provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of an optional controllable fault database operation provided by an embodiment of the present invention; Figure 4 This is a schematic diagram of a process for selecting and executing control strategies for multiple types of faults, provided by an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0020] It should be noted that, in the description of the embodiments of the present invention, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0021] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more.

[0022] Figure 1 This is a flowchart illustrating the fault-tolerant control method for a controllable fault library of synchronous motors provided by the present invention, as shown below. Figure 1 As shown, including but not limited to the following steps: Step 102: Perform multi-domain feature extraction and standardization on the multi-source operating data during the synchronous motor operation process to obtain standardized feature vectors.

[0023] Synchronous motors are widely used in new energy power generation, large-scale transmission and power equipment fields due to their adjustable excitation and high operating stability.

[0024] However, in actual operation, it is susceptible to multi-source coupled disturbances such as magnetic flux imbalance, negative sequence current, torque pulsation, local magnetic saturation and abnormal temperature rise, which lead to enhanced electromagnetic force waves, increased vibration and decreased efficiency.

[0025] In this embodiment, sensors are used to collect multi-source operating signals such as voltage, current, excitation current, speed, temperature, and vibration during the operation of the synchronous motor.

[0026] Multi-source operating data undergoes synchronization, filtering, and normalization preprocessing to obtain preprocessed multi-source signals. Time-domain statistical features, frequency-domain energy distribution features, harmonic component features, and current and flux linkage space vector features in the dq coordinate system are extracted from the preprocessed multi-source signals to obtain multi-domain feature vectors. This invention enhances the separability between different types of electromagnetic faults by constructing multi-dimensional feature vectors to comprehensively characterize the operating state of the motor at the electromagnetic, mechanical, and thermal levels.

[0027] To eliminate differences in the dimensions, numerical ranges, and distribution patterns of different features and improve the stability and robustness of subsequent feature matching calculations, the extracted multidimensional feature vectors are standardized to obtain standardized feature vectors. Standardization is used to eliminate differences in the dimensions of different features.

[0028] Optional, for the first i Eigenvalues ​​of each feature channel x i ( t Perform the standardization transformation as follows:

[0029] in, x i ( t ) is the first i The original feature values ​​of the channel, x i This is the mean value of this characteristic under normal operating conditions. σ i This represents the standard deviation of the corresponding feature. Through the above standardization process, features from different sources and at different scales are made to participate in matching calculations at a unified scale.

[0030] Step 104: Input the standardized feature vector into the controllable fault database, and use a weighted distance model to calculate the matching distance between the standardized feature vector and various fault templates in the controllable fault database to obtain the fault matching result.

[0031] To achieve unified modeling, controllable description, and subsequent diagnosis and suppression of various types of electromagnetic faults in synchronous motors, a controllable fault library is first constructed. The fault-tolerant control method of the controllable fault library for synchronous motors provided in this implementation can be applied to a fault-tolerant control system based on the controllable fault library of the motor. Figure 2 This is a schematic diagram of the structure of a fault-tolerant control system for an optional synchronous motor controllable fault library provided in an embodiment of the present invention.

[0032] like Figure 2 As shown, the fault-tolerant control system of the controllable fault library of the motor described in this invention includes a signal acquisition layer, a feature analysis layer, a control execution layer, and a synchronous motor body. The controllable fault library is located inside the feature analysis layer and between the feature extraction and standardization module and the fault discrimination and control strategy selection module, for the purpose of realizing centralized management of fault features and mapping of control strategies.

[0033] The controllable fault database takes typical abnormal states of motors under different operating conditions and electromagnetic disturbances as its objects, and describes various electromagnetic faults in a templated, parameterized and structured manner, so that it can serve both fault identification and control strategy generation. Figure 3 This is a schematic diagram of an optional motor controllable fault database operation provided by an embodiment of the present invention, such as... Figure 3 As shown, the controllable fault database can adopt a modular structure design, which includes feature template vector unit, template weight unit, fault matching and discrimination logic unit, control strategy unit, and weight self-learning update unit. The units are associated with each other through feature vectors and parameters to achieve unified management and dynamic evolution of multiple types of faults.

[0034] Optionally, the controllable fault library includes at least several fault templates, such as those for excitation flux imbalance, stator negative sequence current, torque pulsation, local magnetic saturation, abnormal temperature rise, and harmonic distortion. Each fault template corresponds to a set of standard characteristic descriptions and control correlation parameters, used to characterize the typical manifestations of this type of fault at the electromagnetic, mechanical, and thermal levels. By modularizing the characteristic structures of different faults, unified management, expansion, and reuse of multiple types of faults can be achieved.

[0035] During the fault database construction process, for each type of controllable fault, a corresponding feature template vector is established to describe the standard form of that type of fault in the multi-domain feature space. The fault feature template vector can be represented as:

[0036] Among them, T k For the first k Feature template vector of the fault class, x i,k This indicates that this type of fault occurred in the [number]th [year]. iTypical eigenvalues ​​across several characteristic dimensions. These dimensions include, but are not limited to, current imbalance, flux deviation, torque ripple components, harmonic energy indices, and vibration characteristics. This approach enables different types of faults to have comparable and distinguishable representations within the same characteristic space, providing a foundation for subsequent fault diagnosis based on characteristic distance.

[0037] To enhance the correlation between fault templates and control strategies, a set of controllable parameters is further introduced into each type of fault template to describe the sensitivity of that type of fault to the adjustment of the excitation-side control quantity or the stator-side sub-current control quantity. The set of controllable parameters can be uniformly represented as:

[0038] in, θ k This represents the equivalent action direction parameter associated with this type of fault. λ k Parameters indicating fault intensity or deviation amplitude. ρ k This represents the control channel association weight corresponding to this type of fault. By binding the feature template vector with the set of controllable parameters, each type of fault not only becomes identifiable but also adjustable, thus providing a direct basis for the rapid invocation of subsequent control strategies and parameter generation.

[0039] Furthermore, to adapt to changes in the amplitude and distribution of fault characteristics under different operating conditions, parameter update interfaces are reserved for various fault templates in the controllable fault database. This allows the parameter values ​​to be adjusted online based on the operating status and control effect while maintaining the template structure unchanged. For example... Figure 3 As shown, the template weighting unit and the weight self-learning update unit are used to implement the above functions, thereby providing basic support for subsequent online diagnosis and adaptive optimization. The controllable fault library constructed in the above manner does not rely on fixed thresholds or single criteria, but uses structured templates and parameterized descriptions as its core to achieve unified modeling of multiple types of electromagnetic faults.

[0040] The resulting controllable fault database organically integrates fault feature descriptions, control correlation parameters, and template structures, transforming the fault database from a traditional static fault set into a functional module with scalability and control orientation. This provides a complete and reliable foundation for subsequent fault diagnosis methods and active suppression strategies based on the controllable fault database.

[0041] In this embodiment, the standardized feature vector is input into a controllable fault database. A weighted distance model is used to calculate the matching distance between the current real-time feature vector and various fault templates in the database, where the feature weights reflect the importance of different features for fault identification.

[0042] Alternatively, a weighted distance model may be used, for example: ; in, ω i For feature weights, x' i,k For the first k The characteristic quantities of a fault template.

[0043] Step 106: Determine the current fault type based on the fault matching result to obtain the fault type discrimination result.

[0044] After calculating the matching distances for various fault templates, the fault type under the current motor operating state is determined based on the minimum distance decision principle or the maximum similarity principle. For example, the fault category corresponding to the fault template with the smallest matching distance is determined as the current fault type. It is worth noting that in the process of determining the current fault type using the minimum distance principle, Euclidean distance, cosine similarity, and fuzzy clustering distance can be combined when necessary to cope with feature drift caused by complex operating conditions and improve recognition stability. Figure 4 This is a schematic diagram illustrating an optional control strategy selection and execution method for multiple types of faults provided in an embodiment of the present invention, such as... Figure 4 As shown, the fault type discrimination results can be classified into various types such as excitation flux imbalance, stator negative sequence current, torque pulsation, local magnetic saturation, and harmonic distortion.

[0045] Step 108: Based on the fault type identification result, call the control strategy associated with the fault type in the controllable fault library to obtain the fault suppression control instruction.

[0046] After identifying the fault type, differentiated suppression control is executed according to the corresponding template strategy based on the fault type discrimination result, automatically selecting and calling the appropriate control strategy. For example, the excitation-side control strategy, for flux-related faults such as flux imbalance and local magnetic saturation, compensates for flux deviation by correcting the excitation current. The stator-side sub-current control strategy, for current-related faults such as negative sequence current, torque pulsation, and harmonic distortion, adjusts the stator sub-current through dual-channel compensation to offset negative sequence current and weaken harmonic effects. The joint and coordinated control strategy, for torque pulsation or multi-source coupling faults, synchronously adjusts the excitation current and stator sub-current, and dynamically allocates adjustment weights to balance suppression effect and system operational stability.

[0047] In this embodiment, for flux-related faults such as flux imbalance, magnetomotive force distortion, and local magnetic saturation, an excitation current compensation law is used for adjustment:

[0048] in, Where ξ is the rated excitation current and ξ is the equivalent correction factor. This is the characteristic deviation. The excitation compensation signal is superimposed in opposite phase with the actual deviation, thereby reducing flux linkage fluctuations.

[0049] Furthermore, for current-related faults such as stator negative sequence current, torque ripple, or harmonic distortion, a dual-channel sub-current compensation strategy is adopted:

[0050] in, This is the actual stator current vector. This is the reference template current in the controllable fault database. This is the vector correction coefficient. This strategy can quickly offset negative sequence current, weaken harmonic effects, and form a synergistic suppression effect with excitation compensation.

[0051] Furthermore, to evaluate the suppression effect, this invention constructs a comprehensive error evaluation function:

[0052] in, For vibration index, For torque ripple indicators, This is an index of magnetic flux deviation. α , β , γ These are the weighting coefficients.

[0053] Furthermore, when the evaluation value E When the values ​​exceed a set threshold, the weights of each feature in the fault database are adjusted using a gradient update mechanism.

[0054] in, η For learning rate, For the updated feature weight parameters, These are the current feature weight parameters; This invention achieves unified identification of different electromagnetic fault types through the matching and decision mechanism based on the controllable fault database, and provides clear criteria for subsequent invocation of corresponding excitation-side control, stator-side current control or joint coordinated control strategies for different fault types.

[0055] Furthermore, in the fault-tolerant control method for a controllable fault library of a synchronous motor provided in this embodiment of the invention, after obtaining the fault suppression control command, the method further includes: Step 110: Execute the fault suppression operation according to the fault suppression control command, and collect the vibration index, torque fluctuation index and magnetic flux deviation index after suppression to obtain the suppression effect feedback data; Step 112: Evaluate the suppression effect feedback data according to the comprehensive error evaluation function to obtain the suppression effect evaluation value. The comprehensive error evaluation function is a weighted combination of the vibration index, torque fluctuation index and magnetic flux deviation index. Step 114: Determine whether the suppression effect evaluation value exceeds a preset threshold. If it does, perform gradient updates on the feature weight parameters in the controllable fault database based on the suppression effect evaluation value to obtain updated feature weight parameters, and store the updated feature weight parameters to achieve online self-learning optimization of the controllable fault database. If it does not exceed the threshold, end the control process.

[0056] In this embodiment, after completing fault diagnosis based on a controllable fault database and determining the current fault type, this embodiment further provides an active suppression and self-learning update method for multiple types of electromagnetic faults. The overall control logic and execution structure of this method are as follows: Figure 1 and Figure 4 As shown, the fault diagnosis results serve as the input to the control strategy selection module. The module automatically matches the corresponding control strategy according to different fault types and updates the weight parameters in the controllable fault database online through a closed-loop feedback mechanism, thereby achieving continuous improvement in fault suppression effect and system performance.

[0057] like Figure 4 As shown, in the control strategy execution layer, the system first classifies the current fault based on the fault type discrimination result.

[0058] When the fault is identified as an unbalanced excitation flux linkage, a local magnetic saturation fault, or a fault related to abnormal magnetic field distribution, the control strategy selection module invokes the excitation-side control strategy to specifically adjust the excitation current. The excitation-side control primarily adjusts the excitation current, using the corresponding flux linkage deviation characteristics in the fault template as the control input. Through dynamic correction of the excitation current amplitude and phase, a compensating magnetic field opposite to the direction of the fault is generated. Its control law can be expressed as:

[0059] in, Where ξ is the rated excitation current and ξ is the equivalent correction factor. The characteristic deviation is... θ For rotor electrical angle, θ 0 represents the equivalent action direction angle corresponding to the fault characteristic. Through the above control method, the flux deviation caused by the fault is actively compensated, thereby reducing the asymmetry of the air gap magnetic field and the electromagnetic vibration it induces.

[0060] When the fault type is determined to be a stator negative sequence current fault, a harmonic distortion fault, or an electromagnetic fault related to current imbalance, such as Figure 4The stator-side sub-current control strategy is invoked. The sub-current is a control current component obtained through stator three-phase current coordinate transformation or sequence component decomposition, used for targeted compensation of negative sequence components and harmonic components. Its control law can be expressed as:

[0061] Among them, i s ( t () represents the actual stator current vector. This is the reference template current in the controllable fault database. K c This is the vector correction coefficient.

[0062] By dynamically compensating for the stator-side current, effective suppression of negative sequence current, asymmetrical current, and harmonic components can be achieved.

[0063] When the fault type is determined to be a torque pulsation fault or a multi-source coupling fault, further... Figure 4 The diagram illustrates a joint and coordinated regulation strategy that enables excitation-side control and stator-side sub-current control. This joint control strategy synchronizes the excitation current and stator sub-current to maintain spatial and temporal coordination between the flux linkage distribution and the current vector, thereby reducing torque pulsation and the resulting mechanical vibrations and additional losses as a whole. During the execution of the joint control, the regulation weights of the excitation and stator sides are dynamically allocated based on the fault deviation to balance suppression effectiveness with system operational stability.

[0064] After the control strategy is executed, such as Figure 2 The diagram illustrates real-time monitoring of key performance indicators such as vibration amplitude, torque fluctuation, and flux deviation via a closed-loop feedback channel, along with a comprehensive evaluation of the fault suppression effect. To quantify the improvement in system operating status before and after control, this embodiment constructs a comprehensive error evaluation function:

[0065] in M v For vibration index, T g For torque ripple indicators, H d This is an index of magnetic flux deviation. α , β , γ These are the weighting coefficients. Through the evaluation function... E The calculation results are compared with the preset threshold to determine whether the current control effect meets the design requirements.

[0066] When the evaluation result fails to achieve the expected suppression effect, the weight self-learning update mechanism of the controllable fault library is triggered. This update process structurally corresponds to... Figure 3The "weight self-learning update unit" in the model uses the comprehensive error evaluation function as the optimization objective to correct the weight parameters of each feature in the fault template online. Its update rule can be expressed as:

[0067] in, ωold i and ωnew i These represent the feature weights before and after the update, respectively. η The learning rate is used. Through the self-learning update method described above, the feature weights that contribute more to the suppression effect are gradually strengthened, while the feature weights that contribute less to the suppression effect are correspondingly weakened, thereby improving the accuracy of subsequent fault matching and control strategy selection.

[0068] This invention combines fault suppression control with a weight self-learning update mechanism. In this embodiment, a closed-loop adaptive control system based on a controllable fault database is constructed. This system can continuously optimize the fault diagnosis results and control strategy execution effect during operation, so that the system can maintain good stability, adaptability and robustness under load changes, electromagnetic disturbances and long-term operation conditions.

[0069] This invention employs unified modeling and online identification of multiple typical faults. Through multi-domain feature fusion and template-based management, it improves diagnostic accuracy and significantly enhances the system's robustness to noise and operating condition fluctuations. It is particularly suitable for application scenarios with multiple coupled faults and complex electromagnetic disturbances. By adopting a differentiated joint control strategy for the excitation current and stator sub-current channels, it can automatically select the optimal suppression method for different faults, achieving comprehensive suppression of electromagnetic disturbances such as flux linkage deviation, negative sequence current, torque pulsation, and harmonic distortion.

[0070] This invention introduces an online fault database parameter update and self-learning mechanism, enabling the system to automatically optimize feature weights and control strategies based on the suppression effect. This improves the long-term adaptability and continuous optimization capability of the method, allowing the system to maintain efficient and reliable control performance under changing operating conditions, and possesses strong engineering application value. It achieves integrated diagnostic and suppression coordinated control of synchronous motors, thereby improving their operational reliability and intelligence level.

[0071] The present invention also provides a schematic diagram of a fault-tolerant control device for a controllable fault library of a synchronous motor, the device comprising: The data processing module is used to perform multi-domain feature extraction and standardization on multi-source operating data during the operation of synchronous motors to obtain standardized feature vectors. The fault matching module is used to input the standardized feature vector into the controllable fault database, and use a weighted distance model to calculate the matching distance between the standardized feature vector and various fault templates in the controllable fault database to obtain the fault matching result. The fault identification module is used to determine the current fault type based on the fault matching result and obtain the fault type discrimination result; The control strategy generation module is used to call the control strategy associated with the fault type in the controllable fault library based on the fault type discrimination result to obtain the fault suppression control instruction.

[0072] It should be noted that the fault-tolerant control device for the controllable fault library of synchronous motors provided in this embodiment of the invention can execute the fault-tolerant control method for the controllable fault library of synchronous motors described in any of the above embodiments during actual operation, which will not be elaborated in this embodiment.

[0073] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, and when the program instructions are executed by a computer, the computer is able to execute the fault-tolerant control method of the synchronous motor controllable fault library provided in the above embodiments.

[0074] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the fault-tolerant control method of the synchronous motor controllable fault library provided in the above embodiments.

[0075] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fault-tolerant control method for a controllable fault library of a synchronous motor, characterized in that, include: Multi-domain feature extraction and standardization processing are performed on multi-source operating data during the operation of synchronous motors to obtain standardized feature vectors. The standardized feature vector is input into the controllable fault database, and the matching distance between the standardized feature vector and various fault templates in the controllable fault database is calculated using a weighted distance model to obtain the fault matching result. The current fault type is determined based on the fault matching results, and a fault type discrimination result is obtained. Based on the fault type identification result, the control strategy associated with the fault type in the controllable fault library is invoked to obtain the fault suppression control instruction.

2. The fault-tolerant control method for a controllable fault library of a synchronous motor according to claim 1, characterized in that, After obtaining the fault suppression control command, the method further includes: The fault suppression operation is executed according to the fault suppression control command, and the vibration index, torque fluctuation index and magnetic flux deviation index after suppression are collected to obtain the suppression effect feedback data. The suppression effect feedback data is evaluated based on the comprehensive error evaluation function to obtain the suppression effect evaluation value. The comprehensive error evaluation function is a weighted combination of the vibration index, torque fluctuation index and magnetic flux deviation index. If the suppression effect evaluation value exceeds a preset threshold, the feature weight parameters in the controllable fault database are updated by gradient based on the suppression effect evaluation value to obtain updated feature weight parameters. The updated feature weight parameters are then stored to achieve online self-learning optimization of the controllable fault database. If the threshold is not exceeded, the control process ends.

3. The fault-tolerant control method for a controllable fault library of a synchronous motor according to claim 1, characterized in that, The process of extracting and standardizing multi-domain features from multi-source operating data during the operation of the synchronous motor to obtain a standardized feature vector includes: Multi-source operating data during the operation of the synchronous motor are collected and preprocessed by synchronization, filtering and normalization to obtain the preprocessed multi-source signal. The time-domain statistical features, frequency-domain energy distribution features, harmonic component features, and current and flux linkage space vector features in the dq coordinate system are extracted from the preprocessed multi-source signal to obtain the multi-domain feature vector. The multi-domain feature vectors are standardized to obtain standardized feature vectors.

4. The fault-tolerant control method for a controllable fault library of a synchronous motor according to claim 1, characterized in that, The controllable fault library includes fault templates for excitation flux imbalance, stator negative sequence current, torque pulsation, local magnetic saturation, abnormal temperature rise, and harmonic distortion. Each fault template includes a feature template vector unit, a control strategy unit, and an adaptive weight update unit.

5. The fault-tolerant control method for a controllable fault library of a synchronous motor according to claim 1, characterized in that, The current fault type is determined from the fault matching results based on the principle of minimum feature distance or maximum similarity, and the fault type discrimination result is obtained.

6. The fault-tolerant control method for a controllable fault library of a synchronous motor according to claim 4, characterized in that, The step of calling the control strategy associated with the fault type in the controllable fault database based on the fault type discrimination result to obtain the fault suppression control instruction includes: Determine the fault type of the fault type identification result. If the fault type is excitation flux imbalance, local magnetic saturation, or magnetomotive force fluctuation, then invoke the excitation side control strategy to adjust the amplitude and phase of the excitation current according to the flux deviation characteristics and generate a compensating magnetic field opposite to the flux deviation caused by the fault. If the fault type is stator negative sequence current type or harmonic distortion type, the stator side sub-current control strategy is invoked, and the stator sub-current reference value is adjusted through dual-channel compensation to generate a compensation current that is opposite to the negative sequence current component or harmonic component. If the fault type is a torque pulsation type or a multi-source coupling fault, the joint coordinated control strategy is invoked to synchronously execute the excitation side control strategy and the stator side sub-current control strategy, and the adjustment weights of the excitation side and the stator side are dynamically allocated according to the fault deviation, so that the flux distribution and current vector are coordinated in space and time, and the electromagnetic force wave and flux imbalance are synchronously suppressed.

7. The fault-tolerant control method for a controllable fault library of a synchronous motor according to claim 6, characterized in that, The stator current reference value is adjusted through a dual-channel compensation method, and the specific formula is as follows: ； Among them, i s ( t () represents the actual stator current vector. i ref This is the reference template current in the controllable fault database. K c This is the vector correction coefficient.

8. The fault-tolerant control method for a controllable fault library of a synchronous motor according to claim 2, characterized in that, The inhibition effect evaluation value is assessed using an error evaluation function, the specific formula of which is: ； in, Evaluation value of inhibition effect M v For vibration index, T g For torque ripple indicators, H d This is an index of magnetic flux deviation. α , β , γ These are the weighting coefficients; like If the value exceeds the preset threshold, the gradient is updated using the following formula: ； in, η For learning rate, For the updated feature weight parameters, These are the current feature weight parameters; When the control effect meets the target, the parameters are updated and the control is terminated to achieve closed-loop optimization.

9. A fault-tolerant control device for a controllable fault library of a synchronous motor, characterized in that, include: The data processing module is used to perform multi-domain feature extraction and standardization on multi-source operating data during the operation of synchronous motors to obtain standardized feature vectors. The fault matching module is used to input the standardized feature vector into the controllable fault database, and use a weighted distance model to calculate the matching distance between the standardized feature vector and various fault templates in the controllable fault database to obtain the fault matching result. The fault identification module is used to determine the current fault type based on the fault matching result and obtain the fault type discrimination result; The control strategy generation module is used to call the control strategy associated with the fault type in the controllable fault library based on the fault type discrimination result to obtain the fault suppression control instruction.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the fault-tolerant control method of the controllable fault library of synchronous motor as described in any one of claims 1 to 8.

Images