Motor control method and device based on real-time monitoring, equipment and storage medium

Abstract

The application discloses a motor control method based on real-time monitoring and belongs to the technical field of double-fed motor control. The application obtains power generation data of a double-fed motor, controls an image acquisition device to shoot brush image data of the double-fed motor, determines temperature state information of the brush according to the brush image data and an image recognition algorithm, generates a motor monitoring result according to the temperature state information and the power generation data, and controls the double-fed motor according to the motor monitoring result, so that the detection efficiency of the brush is improved, and the beneficial effect of reducing the risk of double-fed motor operation is achieved.

Description

Technical Field

[0001] This invention relates to the field of doubly-fed motor control technology, and in particular to a motor control method, device, equipment and storage medium based on real-time monitoring. Background Technology

[0002] Doubly fed induction generators (DFIGs) are widely used variable-speed constant-frequency power generation devices in fields such as wind power generation and industrial drives. During long-term operation, the brushes are susceptible to problems such as localized overheating, carbon buildup, poor contact, abnormal wear, or spark discharge due to the combined effects of factors such as current density, contact pressure, speed variations, ambient temperature and humidity, and dust. Currently, condition monitoring of DFIG brush systems mainly relies on the following methods: one is periodic manual inspection, which involves visually inspecting the brush appearance and measuring brush grip pressure and contact resistance to determine the condition. However, this method is greatly affected by subjective factors, has low efficiency, and struggles to detect transient or early anomalies, thus increasing the risk. Summary of the Invention

[0003] The embodiments disclosed herein are intended to at least address one of the technical problems existing in the prior art, and to provide a motor control method, apparatus, device, and storage medium based on real-time monitoring.

[0004] On one hand, embodiments of this disclosure provide a motor control method based on real-time monitoring, the motor control method based on real-time monitoring including: Acquire the power generation data of the doubly-fed motor and control the image acquisition device to capture the brush image data of the doubly-fed motor; The temperature status information of the brush is determined based on the brush image data and the image recognition algorithm. Generating motor monitoring results based on the temperature status information and the power generation data; The doubly fed motor is controlled based on the motor monitoring results.

[0005] Optionally, the image recognition algorithm includes an image statistical analysis algorithm and an image morphology recognition algorithm, and the step of determining the temperature state information of the brush based on the brush image data and the image recognition algorithm includes: The brush image data is divided according to a preset division method to obtain multiple brush recognition regions; Based on the image statistical analysis algorithm, the corresponding temperature statistical features of each brush identification area are extracted to obtain multiple temperature statistical features; Based on the image morphology recognition algorithm, the corresponding image morphology features of each brush recognition area are extracted to obtain multiple image morphology features; The temperature state information is determined based on the multiple temperature statistical features and the multiple image morphological features.

[0006] Optionally, the image statistical analysis algorithm includes a grayscale statistical analysis algorithm, and the step of extracting the corresponding temperature statistical features of each brush identification area according to the image statistical analysis algorithm to obtain multiple temperature statistical features includes: The grayscale features are calculated for each of the brush recognition areas according to the grayscale statistical analysis algorithm, resulting in multiple grayscale features. The types of grayscale features include: grayscale mean, grayscale standard deviation, and peak position and peak height of the grayscale histogram. The plurality of temperature statistical features are determined based on the plurality of grayscale features and the first mapping relationship, wherein the first mapping relationship is the mapping relationship between grayscale features and temperature features.

[0007] Optionally, the step of extracting the corresponding image morphological features of each brush recognition region according to the image morphological recognition algorithm to obtain multiple image morphological features includes: An edge detection algorithm is used to extract the edges of each of the brush recognition regions to obtain edge extraction results, which include: edge intensity distribution and total edge length. Based on the edge extraction results, at least two of the following are calculated as image morphological features: the percentage of toner peeling area, the total length or number of cracks, and the unevenness of contact surface wear. These are used as image morphological features to obtain multiple image morphological features.

[0008] Optionally, the step of generating motor monitoring results based on the temperature status information and the power generation data includes: The temperature status information is mapped into a quantitative temperature anomaly index, and the power generation data is preprocessed to extract key operating parameter sequences. The quantized temperature anomaly index and the key operating parameter sequence are jointly reduced in dimensionality using a deep embedding algorithm to obtain joint low-dimensional embedding features. Based on the joint low-dimensional embedding features and multiple base clusterers, several preliminary clustering results are obtained; Based on the consensus mechanism, the multiple preliminary clustering results are integrated to obtain the final operating condition classification and comprehensive monitoring score; The motor monitoring results are generated based on the final operating condition classification and comprehensive monitoring score.

[0009] Optionally, the step of generating the motor monitoring results based on the final operating condition classification and comprehensive monitoring score includes: When the comprehensive monitoring score is less than the first threshold, the motor monitoring result indicates that it is in normal operating condition. When the comprehensive monitoring score is greater than or equal to the first threshold and less than the second threshold, the motor monitoring result is in a state that requires attention, and it is suggested to optimize the operating parameters. When the comprehensive monitoring score is greater than or equal to the second threshold, the motor monitoring result is in an abnormal state and indicates a potential fault risk; When the final operating condition is classified as a transitional switching condition and the comprehensive monitoring score is greater than or equal to the first threshold, the motor monitoring result further includes a short-term risk warning indicator. When the final operating condition is classified as a high load fluctuation condition and the comprehensive monitoring score is greater than or equal to the second threshold, the motor monitoring result further includes an immediate load reduction or shutdown protection recommendation.

[0010] Optionally, the step of acquiring the power generation data of the doubly-fed motor and controlling the image acquisition device to capture the brush image data of the doubly-fed motor includes: When the operating state of the doubly fed motor meets the preset triggering conditions, the power generation data are the stator current, rotor current, output power and speed collected in real time. When the power generation data meets the acquisition conditions, an image trigger command is sent to the image acquisition device; The image acquisition device captures brush image data of the doubly fed motor according to the image trigger command.

[0011] On the other hand, embodiments of this disclosure also provide a motor control device based on real-time monitoring, the motor control device based on real-time monitoring comprising: The acquisition module is used to acquire the power generation data of the doubly fed motor and control the image acquisition device to capture the brush image data of the doubly fed motor. The analysis module is used to determine the temperature status information of the brush based on the brush image data and the image recognition algorithm; The identification module is used to generate motor monitoring results based on the temperature status information and the power generation data; The control module is used to control the doubly fed motor based on the motor monitoring results.

[0012] On the other hand, embodiments of this disclosure also provide a motor control device based on real-time monitoring, the motor control device based on real-time monitoring including: a memory, a processor, and a motor control program based on real-time monitoring stored in the memory and executable on the processor, the motor control program based on real-time monitoring being configured to implement the steps of the motor control method based on real-time monitoring described above.

[0013] On the other hand, embodiments of this disclosure also provide a storage medium storing a motor control program based on real-time monitoring, wherein the motor control program based on real-time monitoring, when executed by a processor, implements the steps of the motor control method based on real-time monitoring described above.

[0014] This invention proposes a motor control method, device, equipment, and storage medium based on real-time monitoring. The method acquires the power generation data of a doubly-fed induction generator (DFIG) and controls an image acquisition device to capture image data of the DFIG's brushes. Based on the brush image data and an image recognition algorithm, the temperature status information of the brushes is determined. The motor monitoring results are generated based on the temperature status information and the power generation data. Compared with traditional manual inspection, this method can effectively and accurately control the DFIG based on the motor monitoring results, thereby reducing the motor's operational risks. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of a motor control device based on real-time monitoring in the hardware operating environment of the embodiment of the present invention; Figure 2 This is a flowchart illustrating a motor control method based on real-time monitoring according to an embodiment of the present invention. Figure 3 This is a flowchart illustrating another embodiment of the motor control method based on real-time monitoring according to the present invention. Detailed Implementation

[0016] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0017] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a motor control device based on real-time monitoring, which is part of the hardware operating environment involved in the embodiments of the present invention.

[0018] like Figure 1As shown, the real-time monitoring-based motor control device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The interactive device 1003 may include a display screen or an input unit such as a keyboard. Optionally, the interactive device 1003 may also be connected to the communication bus via standard wired or wireless interfaces. The network interface 1004 may optionally include standard wired or wireless interfaces (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0019] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on motor control devices based on real-time monitoring, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0020] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a motor control program based on real-time monitoring.

[0021] exist Figure 1 In the real-time monitoring-based motor control device shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the real-time monitoring-based motor control device of the present invention can be set in the real-time monitoring-based motor control device, and the real-time monitoring-based motor control device calls the real-time monitoring-based motor control program stored in the memory 1005 through the processor 1001 and executes the real-time monitoring-based motor control method provided in the embodiment of the present invention.

[0022] This invention provides a motor control method based on real-time monitoring, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a motor control method based on real-time monitoring according to the present invention.

[0023] In this embodiment, the motor control method based on real-time monitoring includes: Step S1: Obtain the power generation data of the doubly fed motor and control the image acquisition device to capture the brush image data of the doubly fed motor; In this embodiment, the doubly-fed induction motor refers to an AC induction motor whose rotor winding is directly connected to the power grid, and whose rotor winding is connected to the power grid via a bidirectional converter through slip rings. It is typically equipped with brushes and slip rings for the electrical connection between the rotor winding and the external bidirectional converter. The power generation data here can be voltage, current, and power data. Specifically, an infrared image of the brush area is acquired using a synchronous control image acquisition device as the brush image data. This infrared image can be used to analyze the wear degree of the brushes. Optionally, the brush usage can be analyzed using the power generation data and the infrared image.

[0024] Step S2: Determine the temperature status information of the brush based on the brush image data and the image recognition algorithm; Preferably, since the brush image data is infrared image data, the temperature status information of the brush can be determined by the brush image data and the image recognition algorithm. It should be noted that since the image of a conventional brush also includes the distribution of debris generated by brush wear, the wear status of the brush can be determined.

[0025] Step S3: Generate motor monitoring results based on the temperature status information and the power generation data; It should be noted that due to varying motor operating conditions, brush temperature will fluctuate accordingly. Therefore, a single temperature status information is insufficient to determine whether a temperature is abnormal. Optionally, temperature status information can be spatiotemporally aligned and correlated with power generation data to analyze the coupling relationship between brush temperature rise and electrical load and operating conditions. This allows for a comprehensive assessment of the motor's health level and fault risk, generating motor monitoring results that include the type and severity of the anomaly.

[0026] Step S4: Control the doubly fed motor based on the motor monitoring results.

[0027] The excitation current, speed, or power settings of the doubly fed motor are dynamically adjusted based on motor monitoring results. When the risk of brush overheating is detected, the load reduction operation or protection shutdown is automatically triggered, realizing closed-loop control based on real-time feedback to ensure the safe and stable operation of the unit.

[0028] In this embodiment, by acquiring the power generation data of the doubly fed motor and controlling the image acquisition device to capture the brush image data of the doubly fed motor, the temperature status information of the brush is determined based on the brush image data and the image recognition algorithm, and the motor monitoring result is generated based on the temperature status information and the power generation data. Compared with traditional manual inspection, the doubly fed motor can be effectively and accurately controlled based on the motor monitoring result, thereby reducing the operating risk of the motor.

[0029] Furthermore, based on the first embodiment, a second embodiment of the motor control method based on real-time monitoring of the present invention is proposed. In this embodiment, reference is made to... Figure 3 The image recognition algorithm includes: an image statistical analysis algorithm and an image morphology recognition algorithm. The step of determining the temperature state information of the brush based on the brush image data and the image recognition algorithm includes: Step S21: Divide the brush image data according to a preset division method to obtain multiple brush recognition regions; Specifically, the brush image data is divided according to a preset division method to obtain multiple independent brush recognition regions. Optionally, this division can be based on the boundaries of the brush structure, commonly the outline of a single brush. Alternatively, a grid-like division can be performed to obtain standard regions.

[0030] Step S22: Extract the corresponding temperature statistical features of each brush identification area according to the image statistical analysis algorithm to obtain multiple temperature statistical features; For infrared thermal images, statistical measures such as the mean, variance, extreme values, and quantiles of grayscale or radiance values ​​can be directly obtained. Optionally, these temperature statistical features can objectively reflect the overall thermal level and temperature distribution uniformity of the area. For example, a high mean indicates a high temperature state, and a high variance indicates that there are large local temperature variations in the corresponding area, thus yielding multiple temperature statistical features.

[0031] Step S23: Extract the corresponding image morphology features of each brush recognition area according to the image morphology recognition algorithm to obtain multiple image morphology features; In this embodiment, it should be noted that the brush is a consumable component, and its appearance will change during use. Image morphology recognition algorithms are used to extract the structural features of the brush's recognition area. This process uses edge detection, contour extraction, and morphological opening and closing operations to identify the brush's geometry, surface texture, ablation marks, crack morphology, and carbon powder accumulation morphology. These morphological features are closely related to temperature conditions: a normal brush surface is smooth and flat, while overheating is often accompanied by material ablation, deformation, or cracking, manifesting as irregular edges, increased surface roughness, or the appearance of holes. By quantifying this morphological information, the physical deformation caused by abnormal temperature can be captured, enhancing the ability to identify severe overheating faults.

[0032] Step S24: Determine the temperature state information based on the multiple temperature statistical features and the multiple image morphological features.

[0033] In this embodiment, temperature statistical features and image morphological features are jointly analyzed to determine the temperature state information. Optionally, the reliability of the temperature statistical features is determined based on the image morphological features. Alternatively, the multiple temperature statistical features and the multiple image morphological features are used as a vector of temperature state information.

[0034] In this embodiment, multiple brush recognition regions are obtained by dividing the brush image data according to a preset division method. The corresponding temperature statistical features of each brush recognition region are extracted according to the image statistical analysis algorithm to obtain multiple temperature statistical features. The corresponding image morphological features of each brush recognition region are extracted according to the image morphological recognition algorithm to obtain multiple image morphological features. The temperature state information is determined according to the multiple temperature statistical features and the multiple image morphological features, thereby improving the accuracy and completeness of the temperature state information.

[0035] Furthermore, based on the first or second embodiment, a third embodiment of the motor control method based on real-time monitoring of the present invention is proposed. In this embodiment, the image statistical analysis algorithm includes a grayscale statistical analysis algorithm. The step of extracting the corresponding temperature statistical features of each brush identification area according to the image statistical analysis algorithm to obtain multiple temperature statistical features includes: The grayscale features are calculated for each of the brush recognition areas according to the grayscale statistical analysis algorithm, resulting in multiple grayscale features. The types of grayscale features include: grayscale mean, grayscale standard deviation, and peak position and peak height of the grayscale histogram. The plurality of temperature statistical features are determined based on the plurality of grayscale features and the first mapping relationship, wherein the first mapping relationship is the mapping relationship between grayscale features and temperature features.

[0036] In this embodiment, grayscale features generally refer to the grayscale values ​​of pixels in an infrared image. When the image acquisition device simultaneously acquires visible and infrared light, the grayscale here refers to the data of the infrared light channel, not the data of the red, green, and blue channels. Furthermore, for each region, a mean grayscale value is determined to characterize the average thermal radiation level of that region. This first mapping reflects the overall temperature level. The grayscale standard deviation is calculated to quantify the dispersion of grayscale values ​​between pixels, thereby assessing the uniformity of temperature distribution. Simultaneously, a grayscale histogram is constructed, its peak positions are extracted to identify the dominant temperature range, and the peak height is extracted to reflect the pixel concentration within that temperature range. These grayscale features accurately characterize the thermal distribution properties of the brush surface from a statistical perspective.

[0037] In this embodiment, grayscale features are calculated for each brush identification area using the grayscale statistical analysis algorithm to obtain multiple grayscale features. The multiple temperature statistical features are then determined based on the multiple grayscale features and a first mapping relationship, where the first mapping relationship is the mapping relationship between grayscale features and temperature features.

[0038] Furthermore, based on any of the above embodiments, a fourth embodiment of the motor control method based on real-time monitoring of the present invention is proposed, wherein the step of extracting the corresponding image morphological features of each brush recognition area according to the image morphological recognition algorithm to obtain multiple image morphological features includes: An edge detection algorithm is used to extract the edges of each of the brush recognition regions to obtain edge extraction results, which include: edge intensity distribution and total edge length. Based on the edge extraction results, at least two of the following are calculated as image morphological features: the percentage of toner peeling area, the total length or number of cracks, and the unevenness of contact surface wear. These are used as image morphological features to obtain multiple image morphological features.

[0039] In this embodiment, by calculating the amplitude and direction of grayscale changes, the abrupt boundary between the brush surface and the background, and between the intact area and the damaged area, is identified, and the extraction results including edge intensity distribution and total edge length are obtained. This provides data from different dimensions for subsequent analysis of the brush condition, increases the amount of data, and thus improves the accuracy of subsequent analysis.

[0040] Furthermore, based on any of the above embodiments, a fifth embodiment of the motor control method based on real-time monitoring of the present invention is proposed, wherein the step of generating motor monitoring results based on the temperature status information and the power generation data includes: The temperature status information is mapped into a quantitative temperature anomaly index, and the power generation data is preprocessed to extract key operating parameter sequences. The quantized temperature anomaly index and the key operating parameter sequence are jointly reduced in dimensionality using a deep embedding algorithm to obtain joint low-dimensional embedding features. Based on the joint low-dimensional embedding features and multiple base clusterers, several preliminary clustering results are obtained; Based on the consensus mechanism, the multiple preliminary clustering results are integrated to obtain the final operating condition classification and comprehensive monitoring score; The motor monitoring results are generated based on the final operating condition classification and comprehensive monitoring score.

[0041] In this embodiment, each base clusterer partitions the joint low-dimensional features based on different assumptions, forming differentiated preliminary clustering results. The consensus mechanism constructs a sample co-occurrence matrix and statistically analyzes the voting results of each base clusterer on whether sample pairs belong to the same class. When a majority of base clusterers believe that two samples belong to the same class, they are forcibly merged into the same cluster; otherwise, they are separated. This reduces the bias caused by a single algorithm, resulting in a final condition classification with clearer boundaries and stronger robustness. The base clusterers here can be classifiers such as K-means, AGNES, DIANA, and DBSCAN.

[0042] Furthermore, based on any of the above embodiments, a sixth embodiment of the motor control method based on real-time monitoring of the present invention is proposed, wherein the step of generating the motor monitoring result according to the final operating condition classification and comprehensive monitoring score includes: When the comprehensive monitoring score is less than the first threshold, the motor monitoring result indicates that it is in normal operating condition. When the comprehensive monitoring score is greater than or equal to the first threshold and less than the second threshold, the motor monitoring result is in a state that requires attention, and it is suggested to optimize the operating parameters. When the comprehensive monitoring score is greater than or equal to the second threshold, the motor monitoring result is in an abnormal state and indicates a potential fault risk; When the final operating condition is classified as a transitional switching condition and the comprehensive monitoring score is greater than or equal to the first threshold, the motor monitoring result further includes a short-term risk warning indicator. When the final operating condition is classified as a high load fluctuation condition and the comprehensive monitoring score is greater than or equal to the second threshold, the motor monitoring result further includes an immediate load reduction or shutdown protection recommendation.

[0043] In this embodiment, a hierarchical early warning system is constructed by setting multi-level thresholds. The comprehensive monitoring score and the final operating condition classification are cross-judged: low scores correspond to normal operation and only routine recording is performed; medium scores trigger a state of concern, prompting optimization of operating parameters to prevent degradation; high scores are judged as abnormal, and a fault risk assessment is initiated. For transitional switching conditions, even if the score just reaches the medium threshold, a short-term risk warning is added to prevent sudden changes in state from causing loss of control; for high load fluctuation conditions, if the score reaches the high-risk threshold, it is directly recommended to immediately reduce the load or shut down the machine to avoid serious damage.

[0044] Furthermore, the step of acquiring the power generation data of the doubly-fed motor and controlling the image acquisition device to capture the brush image data of the doubly-fed motor includes: When the operating state of the doubly fed motor meets the preset triggering conditions, the power generation data are the stator current, rotor current, output power and speed collected in real time. When the power generation data meets the acquisition conditions, an image trigger command is sent to the image acquisition device; The image acquisition device captures brush image data of the doubly fed motor according to the image trigger command.

[0045] In this embodiment, a conditional triggering mechanism is used instead of continuous data acquisition. High-speed sampling of power generation data is initiated only when the doubly-fed motor's operating state meets preset triggering conditions, acquiring the stator and rotor electrical quantities and mechanical speeds. When these electrical data exhibit abnormal fluctuations or reach specific acquisition conditions, a trigger command is sent to the image acquisition device to initiate visual monitoring. This hierarchical triggering strategy effectively reduces invalid data transmission and storage overhead, ensures precise alignment between image acquisition and electrical anomalies, establishes a strong correlation between brush temperature status and power generation conditions, and improves the timeliness and relevance of monitoring.

[0046] Furthermore, embodiments of the present invention also propose a motor control device based on real-time monitoring, the motor control device based on real-time monitoring comprising: The acquisition module is used to acquire the power generation data of the doubly fed motor and control the image acquisition device to capture the brush image data of the doubly fed motor. The analysis module is used to determine the temperature status information of the brush based on the brush image data and the image recognition algorithm; The identification module is used to generate motor monitoring results based on the temperature status information and the power generation data; The control module is used to control the doubly fed motor based on the motor monitoring results.

[0047] Furthermore, this embodiment of the invention also proposes a motor control device based on real-time monitoring. The motor control device based on real-time monitoring includes: a memory, a processor, and a motor control program based on real-time monitoring stored in the memory and executable on the processor. The motor control program based on real-time monitoring is configured to implement the steps of the motor control method based on real-time monitoring described in any of the above embodiments.

[0048] Furthermore, embodiments of the present invention also propose a storage medium storing a motor control program based on real-time monitoring, wherein the motor control program based on real-time monitoring, when executed by a processor, implements the steps of the motor control method based on real-time monitoring described above.

[0049] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system 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 system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0050] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0051] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0052] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A motor control method based on real-time monitoring, characterized in that, The motor control method based on real-time monitoring includes: Acquire the power generation data of the doubly-fed motor and control the image acquisition device to capture the brush image data of the doubly-fed motor; The temperature status information of the brush is determined based on the brush image data and the image recognition algorithm. Generating motor monitoring results based on the temperature status information and the power generation data; The doubly fed motor is controlled based on the motor monitoring results.

2. The motor control method based on real-time monitoring as described in claim 1, characterized in that, The image recognition algorithm includes an image statistical analysis algorithm and an image morphology recognition algorithm. The step of determining the temperature state information of the brush based on the brush image data and the image recognition algorithm includes: The brush image data is divided according to a preset division method to obtain multiple brush recognition regions; Based on the image statistical analysis algorithm, the corresponding temperature statistical features of each brush identification area are extracted to obtain multiple temperature statistical features; Based on the image morphology recognition algorithm, the corresponding image morphology features of each brush recognition area are extracted to obtain multiple image morphology features; The temperature state information is determined based on the multiple temperature statistical features and the multiple image morphological features.

3. The motor control method based on real-time monitoring as described in claim 2, characterized in that, The image statistical analysis algorithm includes a grayscale statistical analysis algorithm. The step of extracting the corresponding temperature statistical features of each brush identification region according to the image statistical analysis algorithm to obtain multiple temperature statistical features includes: The grayscale features are calculated for each of the brush recognition areas according to the grayscale statistical analysis algorithm, resulting in multiple grayscale features. The types of grayscale features include: grayscale mean, grayscale standard deviation, and peak position and peak height of the grayscale histogram. The plurality of temperature statistical features are determined based on the plurality of grayscale features and the first mapping relationship, wherein the first mapping relationship is the mapping relationship between grayscale features and temperature features.

4. The motor control method based on real-time monitoring as described in claim 2, characterized in that, The step of extracting the corresponding image morphology features of each brush recognition region according to the image morphology recognition algorithm to obtain multiple image morphology features includes: An edge detection algorithm is used to extract the edges of each of the brush recognition regions to obtain edge extraction results, which include: edge intensity distribution and total edge length. Based on the edge extraction results, at least two of the following are calculated as image morphological features: the percentage of toner peeling area, the total length or number of cracks, and the unevenness of contact surface wear. These are used as image morphological features to obtain multiple image morphological features.

5. The motor control method based on real-time monitoring as described in claim 1, characterized in that, The step of generating motor monitoring results based on the temperature status information and the power generation data includes: The temperature status information is mapped into a quantitative temperature anomaly index, and the power generation data is preprocessed to extract key operating parameter sequences. The quantized temperature anomaly index and the key operating parameter sequence are jointly reduced in dimensionality using a deep embedding algorithm to obtain joint low-dimensional embedding features. Based on the joint low-dimensional embedding features and multiple base clusterers, several preliminary clustering results are obtained; Based on the consensus mechanism, the multiple preliminary clustering results are integrated to obtain the final operating condition classification and comprehensive monitoring score; The motor monitoring results are generated based on the final operating condition classification and comprehensive monitoring score.

6. The motor control method based on real-time monitoring as described in claim 5, characterized in that, The step of generating the motor monitoring results based on the final operating condition classification and comprehensive monitoring score includes: When the comprehensive monitoring score is less than the first threshold, the motor monitoring result indicates that it is in normal operating condition. When the comprehensive monitoring score is greater than or equal to the first threshold and less than the second threshold, the motor monitoring result is in a state that requires attention, and it is suggested to optimize the operating parameters. When the comprehensive monitoring score is greater than or equal to the second threshold, the motor monitoring result is in an abnormal state and indicates a potential fault risk; When the final operating condition is classified as a transitional switching condition and the comprehensive monitoring score is greater than or equal to the first threshold, the motor monitoring result further includes a short-term risk warning indicator. When the final operating condition is classified as a high load fluctuation condition and the comprehensive monitoring score is greater than or equal to the second threshold, the motor monitoring result further includes an immediate load reduction or shutdown protection recommendation.

7. The motor control method based on real-time monitoring as described in any one of claims 1 to 6, characterized in that, The steps of acquiring the power generation data of the doubly-fed motor and controlling the image acquisition device to capture the brush image data of the doubly-fed motor include: When the operating state of the doubly fed motor meets the preset triggering conditions, the power generation data are the stator current, rotor current, output power and speed collected in real time. When the power generation data meets the acquisition conditions, an image trigger command is sent to the image acquisition device; The image acquisition device captures brush image data of the doubly fed motor according to the image trigger command.

8. A motor control device based on real-time monitoring, characterized in that, The motor control device based on real-time monitoring includes: The acquisition module is used to acquire the power generation data of the doubly fed motor and control the image acquisition device to capture the brush image data of the doubly fed motor. The analysis module is used to determine the temperature status information of the brush based on the brush image data and the image recognition algorithm; The identification module is used to generate motor monitoring results based on the temperature status information and the power generation data; The control module is used to control the doubly fed motor based on the motor monitoring results.

9. A motor control device based on real-time monitoring, characterized in that, The motor control device based on real-time monitoring includes: a memory, a processor, and a motor control program based on real-time monitoring stored in the memory and executable on the processor, the motor control program based on real-time monitoring being configured to implement the steps of the motor control method based on real-time monitoring as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a motor control program based on real-time monitoring, which, when executed by a processor, implements the steps of the motor control method based on real-time monitoring as described in any one of claims 1 to 7.

Images