A method for monitoring the temperature of a generator rotor

Abstract

The present invention relates to the technical field of generator temperature monitoring, and in particular to a method for monitoring the temperature of a generator rotor, comprising: setting a sampling frequency one, an infrared temperature sensor located at a position one collects temperature data according to the sampling frequency one, and preprocesses the collected temperature data; setting a sampling frequency two, an infrared imaging device located at a position two collects infrared imaging data according to the sampling frequency two, and preprocesses the collected infrared imaging data; extracting a plurality of feature data one from the preprocessed temperature data to form a monitoring data set one; extracting a plurality of feature data two from the preprocessed infrared imaging data to form a monitoring data set two; a temperature monitoring model predicts the probability of overheating of a generator rotor based on the monitoring data set one and the monitoring data set two, and outputs a corresponding early warning signal according to the analysis result; and adjusting the sampling frequency one and the sampling frequency two to monitor the temperature of different measuring points of the generator rotor.

Description

Technical Field

[0001] The invention relates to the technical field of generator temperature monitoring, and in particular to a method for monitoring the temperature of a generator rotor. Background Art

[0002] There are two methods for monitoring the temperature of the generator rotor: contact and non-contact. The contact measurement method is to measure the temperature of the generator rotor by contacting the engine rotor through a thermistor, etc. The non-contact method is to obtain the temperature data of the generator rotor by measuring thermal radiation. For example: 1. Obtain infrared images of heating equipment through infrared imaging equipment (infrared cameras, etc.), which can be used to analyze temperature distribution; 2. Measure the temperature by measuring the infrared intensity through infrared temperature sensors. The basic principle is to use the infrared radiation characteristics of an object, and according to Planck's law and Stefan-Boltzmann's law, determine the temperature of an object by measuring the intensity of infrared radiation emitted by the object.

[0003] The advantages of non-contact temperature measurement are: the upper limit of measurement is not limited by the temperature resistance of the temperature sensing element, so there is no limit on the maximum measurable temperature in principle. For high temperatures above 1800°C, non-contact temperature measurement methods are mainly used. Based on this, we propose a temperature monitoring method suitable for generator rotors to improve the efficiency and accuracy of generator rotor temperature monitoring. Summary of the invention

[0004] The present invention predicts the probability of high temperature of the generator rotor by analyzing the temperature data of the generator rotor and the data such as the motor input current and input voltage, and integrates multiple monitoring data to improve the accuracy of predicting the probability of high temperature of the generator rotor through machine learning algorithms. By regulating the sampling frequency, the coordination between multiple temperature measuring devices, as well as the selection and adaptive adjustment of temperature measuring points are achieved.

[0005] The technical solution proposed by the present invention is: a method for monitoring the temperature of a generator rotor, the method comprising:

[0006] The sampling frequency is set to one, and the infrared temperature sensor located at position one collects temperature data according to the sampling frequency one, and pre-processes the collected temperature data;

[0007] Sampling frequency 2 is set, and the infrared imaging device located at position 2 collects infrared imaging data according to sampling frequency 2, and pre-processes the collected infrared imaging data;

[0008] Extracting a plurality of feature data 1 from the preprocessed temperature data to form a monitoring data set 1;

[0009] Extracting a plurality of feature data 2 from the preprocessed infrared imaging data to form a monitoring data set 2, wherein the infrared imaging data includes a plurality of infrared images;

[0010] The temperature monitoring model predicts the probability of overheating of the generator rotor based on monitoring data set 1 and monitoring data set 2, and then outputs the corresponding early warning signal according to the analysis results of the probability;

[0011] The sampling frequency 1 and the sampling frequency 2 are adjusted to monitor the temperature of different measuring points of the generator rotor.

[0012] Preferably, the method further comprises the following steps: acquiring physical characteristic data and historical maintenance status data of the generator rotor from a database, and constructing a digital twin model of the rotor of the rotor generator according to the physical characteristic data and historical maintenance status data of the generator rotor;

[0013] Obtain the generator rotor speed, match the sampling frequency 1 with the generator rotor speed, and set multiple sampling points according to the matching result;

[0014] Map multiple sampling points into the digital twin model of the generator rotor, and add a display function to each sampling point in the digital twin model to display the temperature information of each sampling point;

[0015] The method of obtaining the generator rotor speed, matching the sampling frequency 1 with the generator rotor speed, and setting a plurality of sampling points according to the matching result comprises the following steps:

[0016] Get the generator rotor at the corresponding power The speed under , calculate the corresponding angular velocity ;

[0017] Get the sampling frequency , matching the angular velocity of the generator rotor and the sampling frequency, so that the generator rotor rotates The infrared temperature sensor collects the temperature of the generator rotor surface;

[0018] set up , represents the matching coefficient;

[0019] The generator rotor rotates one circle, and the infrared temperature sensor collects the number of , that is, the number of sampling points is ;

[0020] The method of mapping multiple sampling points into the digital twin model of the generator rotor and adding a display function to each sampling point in the digital twin model to display the temperature information of each sampling point includes the following steps:

[0021] In the digital twin model, each sampling point is assigned a unique identifier and associated with an infrared temperature sensor actually installed on the side of the generator stator ventilation groove close to the air gap;

[0022] After obtaining the data from the infrared temperature sensor, the temperature information of each sampling point is displayed in the digital twin model to intuitively display the temperature distribution information on the generator rotor surface.

[0023] Preferably, the setting of sampling frequency one, the infrared temperature sensor located at position one collects temperature data according to sampling frequency one, and preprocesses the collected temperature data, including the following steps:

[0024] Initialize the infrared temperature sensor and set the sampling frequency of the infrared temperature sensor to sampling frequency 1. ;

[0025] Acquiring generator rotor state information, wherein the generator rotor state information includes generator rotor input current and input voltage;

[0026] The infrared temperature sensor collects the generator rotor surface temperature data at sampling frequency one, and adds a timestamp one to each temperature data;

[0027] The collected surface temperature data is preprocessed, and the preprocessing includes one or more of data cleaning, deduplication and missing value processing.

[0028] Preferably, extracting a plurality of feature data 1 from the preprocessed temperature data to form a monitoring data set 1 comprises the following steps:

[0029] Use the preprocessed temperature data to construct a temperature data time series 1;

[0030] Set sliding window one;

[0031] By moving the sliding window one multiple times, multiple temperature data are extracted from the temperature data time series one in turn to form a temperature data set one ,in Indicates the acquisition frequency is The A temperature dataset, Indicates the number of temperature data. = ;

[0032] Extract multiple feature data from each temperature data set to form a monitoring data set. ,in Indicates The characteristic data 1 of the temperature data set 1 includes one or more of a maximum value, a minimum value, and an average value.

[0033] Preferably, the setting of sampling frequency 2, the infrared imaging device located at position 2 collecting infrared imaging data according to sampling frequency 2, and preprocessing the collected infrared imaging data, comprises the following steps:

[0034] Set sampling frequency 2 ,in, Represents the matching parameters of sampling frequency 1 and sampling frequency 2, ;

[0035] Take the location of the infrared temperature sensor as the reference point , let the angle between position 2 and position 1 on the circumferential direction of the generator rotor be ,in, Indicates the time difference, ;

[0036] Assume that the distance between position 2 and position 1 on the generator rotor axis is , ,in, Indicates the viewing angle range of the infrared imaging device, Indicates the distance between the infrared imaging device and the surface of the generator rotor;

[0037] Initialize the infrared imaging device and set the frame rate of the infrared imaging device to acquisition frequency 2 ;

[0038] The infrared imaging device collects infrared image data of the generator rotor surface according to sampling frequency two, and adds a timestamp two to each infrared image data;

[0039] The collected infrared image data is subjected to noise reduction and normalization processing to form an infrared image sequence.

[0040] Preferably, the step of extracting a plurality of feature data 2 from the preprocessed infrared imaging data to form a monitoring data set 2, wherein the infrared imaging data includes an infrared image, comprises the following steps:

[0041] Use the Sobel operator to detect edges in infrared images and calculate the gradient magnitude to divide the image into different regions;

[0042] Map pixel values ​​in different regions to temperature values;

[0043] Obtain the temperature value corresponding to the central area of ​​the infrared image to form the second temperature data time series;

[0044] Get the distance from the center area of ​​the infrared image The temperature value of the area constitutes the temperature data time series three;

[0045] Set sliding window 2;

[0046] By moving sliding window 2 multiple times, multiple temperature data are extracted from temperature data time series 2 in sequence to form temperature data set 2 ;in Indicates the acquisition frequency is The Temperature dataset 2;

[0047] Extract multi-feature data 2 from each temperature data set 2 to form monitoring data subset 1 ,in, Indicates Feature data 2 of temperature data set 2;

[0048] By moving the sliding window 2 multiple times, multiple temperature data are extracted from each temperature data time series 3 in turn to form a temperature data set 3 ;in Indicates the acquisition frequency is The Three temperature data sets;

[0049] Extract multi-feature data 3 from each temperature data set 3 to form monitoring data subset 2 ,in, Indicates Feature data three of temperature data set three;

[0050] Monitoring data subset 1 and monitoring data subset 2 constitute monitoring data set 2 .

[0051] Preferably, the temperature monitoring model predicts the probability of overheating of the generator rotor based on the monitoring data set 1 and the monitoring data set 2, comprising the following steps:

[0052] Importing a pre-trained temperature monitoring model ,in, They represent regression coefficient one, regression coefficient two and regression coefficient three respectively. They represent error term 1, error term 2, and error term 3 respectively. Indicates the number of input items. and Represent regression coefficients 4 and 5 respectively. Indicates First-class input items, Indicates The second type of input, and Indicates third and fourth category input items.

[0053] Preferably, outputting a corresponding warning signal according to the analysis result of the probability value comprises the following steps:

[0054] The elements in the monitoring data set 1 are input into the temperature monitoring model as the first type of input items, and the probability value of the generator rotor overheating is output. ;

[0055] The elements in the monitoring data subset 1 in the monitoring data set 2 are input into the temperature monitoring model as the second type of input items, and the generator rotor overheating probability value 2 is output. ;

[0056] The elements in the monitoring data subset 2 in the monitoring data set 2 are input into the temperature monitoring model as the first type of input items, and the probability value 3 of the generator rotor overheating is output. ;

[0057] Set the warning threshold and warning threshold 2 ,if and ;or, and , then the warning signal is output to the host computer and displayed in the preset area of ​​the generator digital twin model;

[0058] The step of adjusting the sampling frequency 1 and the sampling frequency 2 to monitor the temperature of different measuring points of the generator rotor comprises the following steps:

[0059] Adjust the sampling frequency to adjust the number of times the infrared temperature sensor collects data;

[0060] Increase or decrease the number of sampling points by adjusting the number of acquisitions by the infrared temperature sensor;

[0061] Adjustment , to select different measurement points and monitor the temperature of different measurement points of the generator rotor.

[0062] The present invention also provides an electronic device, which is used to execute the generator rotor temperature monitoring method.

[0063] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the generator rotor temperature monitoring method.

[0064] Beneficial effects of the present invention:

[0065] 1. The present invention is based on non-contact temperature measurement technology. It collects temperature data of different temperature measurement points through the set infrared temperature measurement sensor and infrared imaging device, monitors the temperature data through the sampling temperature monitoring model, predicts the probability of overheating of the generator rotor, and makes corresponding early warnings. Combined with the digital twin technology, the visualization of the temperature measurement and early warning process is realized.

[0066] 2. The present invention sets the positions of the infrared temperature sensor and the infrared imaging device according to the common rotation speed of the generator rotor, that is, the angle between the two devices in the circumferential direction; the spacing between the two devices can be adjusted according to actual needs. The sampling frequency 1 and the sampling frequency 2 are set, and the selection of the temperature measurement point is realized by matching with the rotor rotation speed. The temperature measurement points of the two devices can be the same or different, realizing the adaptive adjustment and matching of the temperature measurement points and expanding the temperature measurement range.

[0067] 3. In the present invention, the infrared image obtained by the infrared imaging device can be analyzed to obtain the temperature data of the temperature measuring point corresponding to the infrared imaging device, and the temperature data of the temperature measuring point corresponding to the infrared temperature sensor can also be obtained. The three sets of data obtained from the infrared temperature sensor and the infrared imaging device are all used as the data source of the temperature monitoring model, which greatly improves the accuracy of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 The present invention is a flow chart of a method for monitoring the temperature of a generator rotor. DETAILED DESCRIPTION

[0069] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0070] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0071] refer to Figure 1 The technical solution provided by the present invention is: a method for monitoring the temperature of a generator rotor, comprising the following steps:

[0072] 1. Obtain the physical characteristic data and historical maintenance status data of the generator rotor from the database, and build a digital twin model of the rotor generator based on the physical characteristic data and historical maintenance status data of the generator rotor. Obtain the generator rotor speed, match the sampling frequency one and the generator rotor speed, and set multiple sampling points according to the matching results. Map multiple sampling points to the digital twin model of the generator rotor, and add a display function to each sampling point in the digital twin model to display the temperature information of each sampling point, specifically: assign a unique identifier to each sampling point in the digital twin model, and associate it with the infrared temperature sensor actually installed on the side of the generator stator ventilation groove close to the air gap; after obtaining the data of the infrared temperature sensor, display the temperature information of each sampling point in the digital twin model to intuitively display the surface temperature distribution information of the generator rotor.

[0073] 2. Set sampling frequency 1. The infrared temperature sensor located at position 1 collects temperature data according to sampling frequency 1, and pre-processes the collected temperature data, including the following steps:

[0074] Initialize the infrared temperature sensor and set the sampling frequency of the infrared temperature sensor to sampling frequency 1. , obtain the generator rotor status information, the generator rotor status information includes the generator rotor input current and input voltage; the infrared temperature sensor collects the generator rotor surface temperature data according to the sampling frequency one, and adds a timestamp one to each temperature data; the collected surface temperature data is preprocessed, and the preprocessing includes one or more of data cleaning, deduplication and missing value processing.

[0075] 3. Setting sampling frequency 2, the infrared imaging device at position 2 collects infrared imaging data according to sampling frequency 2, and preprocesses the collected infrared imaging data, including the following steps:

[0076] Set sampling frequency 2 ,in, Represents the matching parameters of sampling frequency 1 and sampling frequency 2, ;

[0077] Take the location of the infrared temperature sensor as the reference point , let the angle between position 2 and position 1 on the circumferential direction of the generator rotor be ,in, Indicates the time difference, ;

[0078] Assume that the distance between position 2 and position 1 on the generator rotor axis is , ,in, Indicates the viewing angle range of the infrared imaging device, Indicates the distance between the infrared imaging device and the surface of the generator rotor;

[0079] Initialize the infrared imaging device and set the frame rate of the infrared imaging device to acquisition frequency 2 ;

[0080] The infrared imaging device collects infrared image data of the generator rotor surface according to sampling frequency two, and adds timestamp two to each infrared image data; the collected infrared image data is subjected to noise reduction and normalization processing to form an infrared image sequence.

[0081] 4. Extracting multiple feature data 1 from the preprocessed temperature data to form a monitoring data set 1 includes the following steps:

[0082] Use the preprocessed temperature data to construct a temperature data time series 1;

[0083] Set sliding window 1, and extract multiple temperature data from temperature data time series 1 by moving sliding window 1 multiple times to form temperature data set 1 ,in Indicates the acquisition frequency is The A temperature dataset, Indicates the number of temperature data. = ;

[0084] Extract multiple feature data from each temperature data set to form a monitoring data set. ,in Indicates The characteristic data 1 of the temperature data set 1 includes one or more of a maximum value, a minimum value, and an average value.

[0085] For example, extract each temperature dataset The maximum value of the temperature in the monitoring data set ,in, Indicates The maximum value in a temperature data set.

[0086] 5. Extracting a plurality of feature data 2 from the preprocessed infrared imaging data to form a monitoring data set 2, wherein the infrared imaging data includes a plurality of infrared images, comprising the following steps:

[0087] Acquire multiple infrared images, use the Sobel operator to detect edges in the infrared images, calculate the gradient amplitude, and divide the images into different areas according to temperature differences;

[0088] The pixel values ​​in different areas are mapped to temperature values, and the temperature value corresponding to the central area of ​​the infrared image is obtained to form the second temperature data time series; the central area of ​​the infrared image here is the part of the generator rotor that the infrared imaging device is aimed at, that is, a temperature measurement point of the generator rotor;

[0089] Get the distance from the center area of ​​the infrared image The temperature values ​​of the area constitute the temperature data time series 3; here the distance Indicates the distance between the infrared imaging device and the infrared temperature sensor. By obtaining the temperature value of this area, the temperature data of the measuring point of the infrared temperature sensor can be indirectly obtained.

[0090] Set sliding window 2, and extract multiple temperature data from temperature data time series 2 by moving sliding window 2 multiple times to form temperature data set 2 ;in Indicates the acquisition frequency is The Temperature data set 2. Extract multi-feature data 2 from each temperature data set 2 to form monitoring data subset 1 ,in, Indicates Feature data 2 of temperature data set 2;

[0091] By moving the sliding window 2 multiple times, multiple temperature data are extracted from each temperature data time series 3 in turn to form a temperature data set 3 ;in Indicates the acquisition frequency is The Temperature data set 3. Extract multi-feature data 3 from each temperature data set 3 to form monitoring data subset 2 ,in, Indicates The characteristic data 3 of the temperature data set 3; in this embodiment, the characteristic data 3 can be the highest value or the lowest value of the temperature. After combining the monitoring data subset 1 and the monitoring data subset 2, the monitoring data set 2 is formed. .

[0092] 6. The temperature monitoring model predicts the probability of overheating of the generator rotor based on monitoring data set 1 and monitoring data set 2, and then outputs the corresponding early warning signal according to the analysis results of the probability, which specifically includes the following steps:

[0093] Importing a pre-trained temperature monitoring model ,in, They represent intercept 1, intercept 2, intercept 3 and intercept 4 respectively. They represent error term 1, error term 2, error term 3 and error term 4 respectively. They represent regression coefficient one, regression coefficient two and regression coefficient three respectively. and Represent regression coefficients 4 and 5 respectively. Indicates the number of input items. Indicates First-class input items, Indicates The second type of input, and Indicates third and fourth category input items.

[0094] Temperature monitoring model , which is used to output the probability of overheating of the generator rotor temperature at a future moment according to the temperature data of the temperature measuring point collected by the infrared temperature sensor; the future moment here can be determined according to the step size of the sliding window. If the step size of the sliding window is 5 seconds, then the probability of overheating after 5 seconds is predicted.

[0095] , used to predict the probability of overheating of the generator rotor based on the temperature of the corresponding temperature measurement point obtained by infrared image analysis. The position of the temperature measurement point corresponds to the center position of the infrared imaging device lens. The infrared imaging device is separated from the infrared temperature sensor by The distance, in When it is not zero, the temperature at two different positions on the axial direction of the generator rotor can be measured.

[0096] exist When the temperature is zero, the distance between the infrared imaging device and the infrared temperature sensor on the generator axis is zero, and the two devices are in the same plane. By setting the angle between the two in the circumferential direction and coordinating the rotation speed of the generator rotor, the infrared imaging device and the infrared temperature sensor can measure the temperature of the same temperature measuring point on the generator rotor. The data obtained by the two devices can be cross-verified, which improves the reliability of the measurement.

[0097] , used to predict the probability of overheating based on the temperature data of the temperature measuring point corresponding to the infrared temperature sensor obtained by analyzing the infrared image, and The output of the two sensors is used together as the basis for judging whether the generator rotor is overheated.

[0098] , which is used to output the probability of generator rotor overheating according to the generator input voltage and input current data. Here, the input voltage and input current acquisition frequency is the same as the sampling frequency 1, and are obtained through the electric energy metering device. The processing process of the input voltage and input current is similar to the processing process of the infrared temperature sensor data, including data acquisition, preprocessing, construction of voltage time series and current time series, extraction of characteristic voltage values ​​and characteristic current values ​​to form characteristic voltage data sets and characteristic current data sets.

[0099] Outputting corresponding warning signals according to the analysis results of the probability value includes the following steps:

[0100] The elements in the monitoring data set 1 are input into the temperature monitoring model as the first type of input items, and the probability value of the generator rotor overheating is output. .

[0101] The elements in the monitoring data subset 1 in the monitoring data set 2 are input into the temperature monitoring model as the second type of input items, and the generator rotor overheating probability value 2 is output. .

[0102] The elements in the monitoring data subset 2 in the monitoring data set 2 are input into the temperature monitoring model as the first type of input items, and the probability value 3 of the generator rotor overheating is output. .

[0103] Set the warning threshold and warning threshold 2 ,if and ;or, and , then the warning signal is output to the host computer and displayed in the preset area of ​​the generator digital twin model.

[0104] 7. Adjusting sampling frequency 1 and sampling frequency 2 to monitor the temperature of different measuring points of the generator rotor includes the following steps:

[0105] Adjust the sampling frequency to adjust the number of times the infrared temperature sensor collects data;

[0106] Increase or decrease the number of sampling points by adjusting the number of acquisitions by the infrared temperature sensor;

[0107] Adjustment , to select different measurement points and monitor the temperature of different measurement points of the generator rotor.

[0108] The change of sampling frequency 2 follows the change of sampling frequency 1. After adjusting sampling frequency 1, sampling frequency 2 changes synchronously.

[0109] The present invention also provides an electronic device, including a processor, a memory and a communication module, wherein the electronic device is used to execute the generator rotor temperature monitoring method.

[0110] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the generator rotor temperature monitoring method.

[0111] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0112] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0113] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A method for monitoring the temperature of a generator rotor, characterized in that: include: The sampling frequency is set to one, and the infrared temperature sensor located at the first position collects temperature data according to the sampling frequency, and pre-processes the collected temperature data; Sampling frequency 2 is set, and the infrared imaging device located at position 2 collects infrared imaging data according to sampling frequency 2, and pre-processes the collected infrared imaging data; Extracting a plurality of feature data 1 from the preprocessed temperature data to form a monitoring data set 1; Extracting a plurality of feature data 2 from the preprocessed infrared imaging data to form a monitoring data set 2, wherein the infrared imaging data includes a plurality of infrared images; The temperature monitoring model predicts the probability of overheating of the generator rotor based on monitoring data set 1 and monitoring data set 2, and then outputs the corresponding early warning signal according to the analysis results of the probability; Adjust sampling frequency one and sampling frequency two to monitor the temperature of different measuring points of the generator rotor; The temperature monitoring model predicts the probability of overheating of the generator rotor based on the monitoring data set 1 and the monitoring data set 2, including the following steps: Importing a pre-trained temperature monitoring model ,in, They represent intercept 1, intercept 2, intercept 3 and intercept 4 respectively. They represent error term 1, error term 2, error term 3 and error term 4 respectively. They represent regression coefficient one, regression coefficient two and regression coefficient three respectively. and Represent regression coefficients 4 and 5 respectively. Indicates the number of input items. Indicates First-class input items, Indicates The second type of input, and Indicates the third and fourth category input items; The method also includes the following steps: obtaining physical characteristic data and historical maintenance status data of the generator rotor from a database, and constructing a digital twin model of the generator rotor based on the physical characteristic data and historical maintenance status data of the generator rotor; Obtain the generator rotor speed, match the sampling frequency 1 with the generator rotor speed, and set multiple sampling points according to the matching result; Map multiple sampling points into the digital twin model of the generator rotor, and add a display function to each sampling point in the digital twin model to display the temperature information of each sampling point; The method of obtaining the generator rotor speed, matching the sampling frequency 1 with the generator rotor speed, and setting a plurality of sampling points according to the matching result comprises the following steps: Get the generator rotor at the corresponding power The speed under , calculate the corresponding angular velocity ; Get the sampling frequency , matching the angular velocity of the generator rotor and the sampling frequency, so that the generator rotor rotates The infrared temperature sensor collects the temperature of the generator rotor surface; set up , represents the matching coefficient; The generator rotor rotates one circle, and the infrared temperature sensor collects the number of , that is, the number of sampling points is ; The method of mapping multiple sampling points into the digital twin model of the generator rotor and adding a display function to each sampling point in the digital twin model to display the temperature information of each sampling point includes the following steps: In the digital twin model, each sampling point is assigned a unique identifier and associated with an infrared temperature sensor actually installed on the side of the generator stator ventilation groove close to the air gap; After obtaining the data from the infrared temperature sensor, the temperature information of each sampling point is displayed in the digital twin model to intuitively display the temperature distribution information on the generator rotor surface.

2. A method for monitoring the temperature of a generator rotor according to claim 1, characterized in that: The step of setting the sampling frequency to one, wherein the infrared temperature sensor located at the first position collects temperature data according to the sampling frequency to one, and preprocessing the collected temperature data comprises the following steps: Initialize the infrared temperature sensor and set the sampling frequency of the infrared temperature sensor to sampling frequency 1. ; Acquiring generator rotor state information, wherein the generator rotor state information includes generator rotor input current and input voltage; The infrared temperature sensor collects the generator rotor surface temperature data at sampling frequency one, and adds a timestamp one to each temperature data; The collected surface temperature data is preprocessed, and the preprocessing includes one or more of data cleaning, deduplication and missing value processing.

3. A method for monitoring the temperature of a generator rotor according to claim 2, characterized in that: The method of extracting a plurality of feature data 1 from the preprocessed temperature data to form a monitoring data set 1 comprises the following steps: Use the preprocessed temperature data to construct a temperature data time series 1; Set sliding window one; By moving the sliding window one multiple times, multiple temperature data are extracted from the temperature data time series one in turn to form a temperature data set one ,in Indicates the acquisition frequency is The A temperature dataset, Indicates the number of temperature data. = ; Extract multiple feature data from each temperature data set to form a monitoring data set. ,in Indicates The characteristic data 1 of the temperature data set 1 includes one or more of a maximum value, a minimum value, and an average value.

4. A method for monitoring the temperature of a generator rotor according to claim 3, characterized in that: The second sampling frequency is set, the infrared imaging device at the second position collects infrared imaging data according to the second sampling frequency, and pre-processes the collected infrared imaging data, including the following steps: Set sampling frequency 2 ,in, Represents the matching parameters of sampling frequency 1 and sampling frequency 2, ; Take the location of the infrared temperature sensor as the reference point , let the angle between position 2 and position 1 on the circumferential direction of the generator rotor be ,in, Indicates the time difference, ; Assume that the distance between position 2 and position 1 on the generator rotor axis is , ,in, Indicates the viewing angle range of the infrared imaging device, Indicates the distance between the infrared imaging device and the surface of the generator rotor; Initialize the infrared imaging device and set the frame rate of the infrared imaging device to acquisition frequency 2 ; The infrared imaging device collects infrared image data of the generator rotor surface according to sampling frequency two, and adds a timestamp two to each infrared image data; The collected infrared image data is subjected to noise reduction and normalization processing to form an infrared image sequence.

5. A method for monitoring the temperature of a generator rotor according to claim 4, characterized in that: The method of extracting a plurality of feature data 2 from the pre-processed infrared imaging data to form a monitoring data set 2, wherein the infrared imaging data includes an infrared image, comprises the following steps: Use the Sobel operator to detect edges in infrared images and calculate the gradient magnitude to divide the image into different regions; Map pixel values ​​in different regions to temperature values; Obtain the temperature value corresponding to the central area of ​​the infrared image to form the second temperature data time series; Get the distance from the center area of ​​the infrared image The temperature value of the area constitutes the temperature data time series three; Set sliding window 2; By moving sliding window 2 multiple times, multiple temperature data are extracted from temperature data time series 2 in sequence to form temperature data set 2 ;in Indicates the acquisition frequency is The Temperature dataset 2; Extract multi-feature data 2 from each temperature data set 2 to form monitoring data subset 1 ,in, Indicates Feature data 2 of temperature data set 2; By moving the sliding window 2 multiple times, multiple temperature data are extracted from each temperature data time series 3 in turn to form a temperature data set 3 ;in Indicates the acquisition frequency is The Three temperature data sets; Extract multi-feature data 3 from each temperature data set 3 to form monitoring data subset 2 ,in, Indicates Feature data three of temperature data set three; Monitoring data subset 1 and monitoring data subset 2 constitute monitoring data set 2 .

6. A method for monitoring the temperature of a generator rotor according to claim 5, characterized in that: Outputting a corresponding warning signal according to the analysis result of the probability value comprises the following steps: The elements in the monitoring data set 1 are input into the temperature monitoring model as the first type of input items, and the probability value of the generator rotor overheating is output. ; The elements in the monitoring data subset 1 in the monitoring data set 2 are input into the temperature monitoring model as the second type of input items, and the generator rotor overheating probability value 2 is output. ; The elements in the monitoring data subset 2 in the monitoring data set 2 are input into the temperature monitoring model as the first type of input items, and the probability value 3 of the generator rotor overheating is output. ; Set the warning threshold and warning threshold 2 ,if and ;or, and , then the warning signal is output to the host computer and displayed in the preset area of ​​the generator digital twin model; The step of adjusting the sampling frequency 1 and the sampling frequency 2 to monitor the temperature of different measuring points of the generator rotor comprises the following steps: Adjust the sampling frequency to adjust the number of times the infrared temperature sensor collects data; Increase or decrease the number of sampling points by adjusting the number of acquisitions by the infrared temperature sensor; Adjustment , to select different measurement points and monitor the temperature of different measurement points of the generator rotor.

7. An electronic device, characterized in that: The electronic device is used to execute a generator rotor temperature monitoring method as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a generator rotor temperature monitoring method as described in any one of claims 1 to 6.

Images