A 3D Visualization Early Warning and Construction Method for Generator Faults

Abstract

The present invention discloses a three-dimensional visualization warning and construction method for generator faults. The present invention relates to the field of digital twin technology. Generator equipment parameters, operation data, and environmental data are obtained through sensors, and a digital twin model of the generator is constructed by combining digital twin technology and three-dimensional visualization technology; and the operation data of the generator is continuously collected to correct the constructed digital twin model of the generator until the constructed digital twin model of the generator can fit the actual generator; the operation data simulated by the corrected digital twin model of the generator is analyzed to identify the generator fault situation, and the identified generator fault situation is mapped in real time with the digital twin model of the generator, and the equipment components with fault situations are displayed to the staff in the form of three-dimensional visualization, and a warning reminder is sent to the staff to inform the staff to perform maintenance in time.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital twins, and specifically relates to a three-dimensional visualization warning and construction method for generator faults. Background Technique

[0002] With the transformation of the global energy structure and the enhancement of environmental protection awareness, the widespread use of electric energy has gradually replaced the traditional energy structure. Whether it is wind power generation, thermal power generation, or nuclear power plants, the most important one is the generator. The operating state of the generator directly affects the power generation efficiency and reliability. Therefore, it is of great significance to study the state monitoring and fault diagnosis technology of generators.

[0003] As a key research object in the field of new energy in current society, the generator state detection and fault diagnosis technology has received much attention at home and abroad. Existing generator fault diagnosis and operating state detection methods have certain limitations. On the one hand, traditional methods mainly focus on the real-time operating state of the generator; on the other hand, some detection means rely on the daily inspection of generator components, or indirectly judge the operating condition of the generator by monitoring the power generation, working voltage, and working current of the generator. These methods cannot directly monitor and warn the generator itself and its equipment components, and it is difficult to meet the requirements of accurate and efficient fault diagnosis and warning. To solve the above problems, the present invention provides a three-dimensional visualization warning and construction method for generator faults. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention provides a three-dimensional visualization warning and construction method for generator faults, which solves the problem that it is difficult to monitor and early warn generator faults in the existing technology.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A three-dimensional visualization warning method for generator faults, characterized in that the method includes the following steps:

[0007] S1. Obtain generator equipment parameters, operation data, and environmental data, and use digital twin technology to construct a generator digital twin model;

[0008] S2. Continuously collect the actual generator operation data to correct the constructed generator digital twin model until the constructed generator digital twin model fits the actual generator;

[0009] S3. Obtain and analyze the operation data of the generator digital twin model during simulated operation, identify the generator fault conditions, map the identified generator fault conditions to the generator digital twin model in real time, and issue a warning reminder to the staff.

[0010] As a further solution of the present invention, the specific method for continuously collecting the generator operation data to correct the constructed generator digital twin model is as follows:

[0011] S21. Based on the constructed generator digital twin model, starting from the current moment as the start moment, simulate running a simulation cycle, the duration of the simulation cycle is set by the staff, and a simulation cycle includes j moments;

[0012] S22. During a simulation cycle, obtain the operation data obtained from the simulation of the generator digital twin model, and on a two-dimensional coordinate system, with time as the horizontal axis and the values of various operation data as the vertical axis, plot the scatter diagrams of the changes of each operation data over time, forming a set of scatter diagram feature vectors A;

[0013] S23. Obtain the operation data of the actual generator when running a simulation cycle starting from the current moment as the start moment, and repeat the method described in S32 to obtain a set of scatter diagram feature vectors B;

[0014] S24. Take the scatter diagram feature vector set A and the scatter diagram feature vector set B as the same group, and denote it as a double-sample scatter diagram feature vector;

[0015] S25. Based on the obtained double-sample scatter diagram feature vector, take one moment in two voltage scatter diagrams, and the two voltage values corresponding to it on the vertical axis ;

[0016] Take and the straight-line distance between the voltage values corresponding to the previous n consecutive moments ; take and the straight-line distance between the voltage values corresponding to the next n consecutive moments . Take as the radius length to draw a circle, obtain the sum of all voltage values within the circle and average it to get the voltage average value ;

[0017] Similarly, obtain the voltage average value ;

[0018] If and the difference rate exceeds the difference rate preset by the staff, it is considered that at this moment The two scatter plots of voltage change do not match. The voltage parameters of the actual generator within this circle are used to overwrite the voltage parameters of the simulated operation of the generator digital twin model, where n is a value preset by the staff, and n is less than i, and i is less than j;

[0019] S26. Transform the two scatter plots of voltage change after the overwriting process into two line graphs of voltage change, and fit them into the same line graph of voltage change for further analysis.

[0020] As a further solution of the present invention, the specific method of transforming the two scatter plots of voltage change after the overwriting process into two line graphs of voltage change and fitting them into the same line graph of voltage change for further analysis in step S26 is as follows:

[0021] S31. Based on the two scatter plots of voltage change, connect any two adjacent points with the shortest line segments to obtain two line graphs of voltage change, and fit the two line graphs of voltage change into the same line graph of voltage change to obtain the first broken line and the second broken line , corresponding to the actual generator and the generator digital twin model respectively;

[0022] S32. Obtain the first moment after the start moment as the initial moment, construct an initial moment line passing through the initial moment and perpendicular to the horizontal axis, and calculate the area characteristics formed among the vertical axis, the first broken line and the second broken line ; ;

[0023] S33. Copy the initial moment line to the moment after the initial moment, denoted as the second moment line, and calculate the area characteristics formed among the initial moment line, the second moment line, the first broken line and the second broken line ; ;

[0024] S34. Repeat step S33 until the last moment of this simulation operation cycle, and a total of j area characteristics are obtained, denoted as , and compare the obtained j area characteristics with the area characteristic threshold preset by the staff. If any area characteristic , then it is considered that the voltage parameters of the simulated operation of the generator digital twin model between this moment and the previous moment do not match the voltage parameters of the actual generator, and the voltage parameters of the actual generator are used to overwrite the voltage parameters of the simulated operation of the generator digital twin model;

[0025] S35. Place the voltage parameters obtained from the simulation operation of the digital twin model of the generator after the covering operation into the digital twin model of the generator to run a simulation operation cycle for data calibration.

[0026] As a further solution of the present invention, place the voltage parameters obtained from the simulation operation of the digital twin model of the generator after the covering operation into the digital twin model of the generator to run a simulation operation cycle for data calibration, and process other operation data according to the method of processing voltage parameters to calibrate the data of the digital twin model of the generator.

[0027] As a further solution of the present invention, the specific method for determining whether the constructed digital twin model of the generator can fit the actual generator is as follows:

[0028] If the operation data obtained from the simulation operation of the digital twin model of the generator in C consecutive simulation operation cycles are all in line with the actual generator, it is regarded that the digital twin model of the generator fits the actual generator, and the value of C is set by the staff.

[0029] As a further solution of the present invention, the specific method for identifying the fault situation of the generator in step S3 is as follows:

[0030] Divide the digital twin model of the generator according to the total number of equipment components. After division, u equipment components are obtained, which are denoted as in turn, where u is a counting index representing the total number of equipment components, are u equipment components: is any one of them, and v is also a counting index. v starts from 1, and the maximum value of v is u;

[0031] Make the digital twin model of the generator simulate running for a simulation operation cycle;

[0032] Extract the time series operation data of the equipment component at any moment during the simulation operation cycle: , where is a data vector, represents the values of all operation data of the component at the moment , and there are q different operation data;

[0033] Based on j moments, obtain the j time series operation data of the equipment component . Taking as an example, obtain the associated data set , calculate the average value and the standard deviation of the data set through the normalization formula:

[0034]

[0035] Normalize all the data in the data set to the range of 0 to 1 to obtain a normalized data set ; similarly, obtain the normalized respective associated normalized data sets;

[0036] Place the normalized operating data into the time series operating data corresponding to their respective times to obtain the normalized time series operating data at time :

[0037]

[0038] Similarly, obtain j normalized time series operating data corresponding to j times, and fit each normalized time series operating data into the device state characteristics of the device component at that time, and draw a curve of the change in the operating state of the device component on a two-dimensional coordinate system and obtain the fluctuation degree of the curve;

[0039] Simulate running several simulation running cycles to obtain the fluctuation degrees of several curves;

[0040] Compare the fluctuation degrees of several curves with the fluctuation degree thresholds set by the staff respectively. If the fluctuation degree of any curve exceeds the fluctuation degree threshold set by the staff, it is determined that the device component has a fault situation during that simulation running cycle;

[0041] According to the above method, perform fault identification processing on all device components in the actual generator, identify the component devices with fault situations, and obtain the simulation running cycles in which the component devices have fault situations.

[0042] As a further solution of the present invention, the specific method for real-time mapping the identified generator fault situation to the generator digital twin model and sending a warning reminder to the staff is as follows:

[0043] For the device components with fault situations, the generator digital twin model uses a highlighted block with a different color from other device components to flash and mark, informing the staff when the device component will have a fault situation, and warning and reminding the staff to perform maintenance or replacement in time before the device component has a fault.

[0044] As a further solution of the present invention, a method for constructing a three-dimensional visualization of generator faults, the method includes the following:

[0045] Obtain the parameters of the generator equipment. The equipment parameters include equipment components and the three-dimensional shape and positional relationship between the equipment components, and construct a digital twin model of the generator based on the three-dimensional modeling software combined with the collected equipment parameters;

[0046] Obtain the operating data of the generator. The operating data includes voltage, current, speed, vibration, stator temperature, and rotor temperature, and is real-time mapped to the digital twin model of the generator through digital twin technology to achieve simulated operation;

[0047] Obtain the environmental parameters. The environmental parameters include environmental temperature, environmental humidity, environmental air pressure, and environmental electric field strength, and are real-time fitted into the operating environment of the simulated operation of the digital twin model of the generator through digital twin technology.

[0048] Advantages of the present invention:

[0049] (1) The present invention provides a method for constructing a three-dimensional visualization warning and construction method of generator faults by combining an actual generator and digital twin technology. A digital twin model of the generator is constructed through digital twin technology, and a method for correcting the digital twin model of the generator based on the actual generator operating data is provided until the digital twin model of the generator highly coincides with the actual generator. This precise modeling and mapping method can ensure a comprehensive and accurate understanding of the generator, providing solid and reliable basic data and model references for subsequent fault diagnosis and warning;

[0050] (2) The present invention provides a method for identifying fault situations based on analyzing the operating data simulated by the corrected digital twin model of the generator, and maps the fault information to the digital twin model of the generator in real time, and timely issues a warning reminder to the staff. Different from the previous indirect monitoring or only being able to detect the occurred faults, this method realizes the early warning of potential faults, enabling the staff to take measures in time, greatly improving the reliability and safety of the generator operation, and reducing the downtime, equipment damage risk and maintenance cost caused by faults;

[0051] (3) The present invention constructs a three-dimensional visualization generator model through digital twin technology and uses a three-dimensional visualization method to warn of faults, enabling the staff to more intuitively understand the fault location and faulty equipment components of the generator. Compared with traditional complex data reports or indicator light alarms, etc., it improves the readability and understandability of fault information, facilitating the staff to quickly make accurate judgments and decisions based on the faulty equipment components, and improving work efficiency and response speed. Description of the Drawings

[0052] The present invention will be further described below with reference to the accompanying drawings.

[0053] Figure 1It is a schematic flowchart of the method described in Embodiment 1 of the present invention;

[0054] Figure 2 It is a schematic flowchart of the method described in Embodiment 2 of the present invention;

[0055] Figure 3 It is a schematic flowchart of the method described in Embodiment 3 of the present invention. Detailed implementation manners

[0056] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0057] Embodiment 1

[0058] A three-dimensional visualization early warning method for generator faults, as Figure 1 shown, specifically includes the following:

[0059] Step 1: Obtain generator equipment parameters, operation data, and environmental data; among them, the equipment parameters of the generator include (including but not limited to) the three-dimensional shapes and positional relationships of the generator housing, rotor, stator, bearings, and the relationships between them, which are obtained through the generator's ex-factory instructions and 3D point cloud measurement technology. The purpose of obtaining the equipment parameters is to use , and other three-dimensional composition technologies to create an accurate geometric model according to the actual size and equipment components of the corresponding generator, and use the digital twin technology to further construct a generator digital twin model on the constructed three-dimensional model;

[0060] The operation data is collected by various sensors assembled on the actual generator during the normal operation of the actual generator, including: voltage, current, speed, vibration, stator temperature, rotor temperature. The data collected from the actual generator is mapped to the corresponding generator digital twin model through the digital twin technology to achieve simulated operation;

[0061] The environmental data is the working environment where the current actual generator is located, which is collected by sensors in the current working environment, including environmental temperature, environmental humidity, environmental air pressure, and environmental electric field strength, and the measured environmental data is fitted into the working environment of the generator digital twin model through the digital twin technology;

[0062] It should be explained here that the environmental data has certain patterns through periodic data and can be summarized. The summarized environmental data is applied to the digital twin model of the generator to simulate the environmental data for a period of time in the future. Before the simulation, calibration processing is required. The calibration processing of the environmental data is regarded as prior art and will not be elaborated in this article.

[0063] Step 2: Continuously collect the operation data of the actual generator to calibrate the constructed digital twin model of the generator. The calibration method is as follows: Use the digital twin model of the generator to simulate the operation for a simulation operation cycle starting from the current time, and obtain the operation data obtained by the simulation operation of the digital twin model of the generator within this simulation operation cycle time. Then, also obtain the operation data of the actual generator within this simulation operation cycle time. Compare the two sets of data and analyze the differences between the two operation data. If the differences are large, the digital twin model of the generator needs to be calibrated. If the operation data of several consecutive simulation operations can match the operation data of the actual generator, it is considered that the calibration is successful. At this time, it is considered that the operation data of the simulation operation of the digital twin model of the generator is equivalent to the operation data of the actual generator.

[0064] Step 3: Analyze the operation data of the simulation operation of the calibrated digital twin model of the generator, identify the generator fault conditions, and map the identified generator fault conditions to the digital twin model of the generator in real time, and display the fault location to the staff in the form of three-dimensional visualization, and issue a warning reminder to the staff.

[0065] Embodiment 2

[0066] This embodiment further elaborates on Step 2 in Embodiment 1. On the basis of Step 2, a method for calibrating the digital twin model of the generator based on the operation data of the actual generator is disclosed, as Figure 2 shown, and specifically includes the following:

[0067] Based on Step 1 in Embodiment 1, a preliminarily constructed digital twin model of the generator can be obtained. In this embodiment, calibration processing will be performed on this digital twin model of the generator with the aim of making the constructed digital twin model of the generator match the actual generator.

[0068] Obtain the current time point, that is, the current moment , and As the starting moment, extend a period of time into the future. The duration of this period is set by the staff and is named the simulation operation cycle. A simulation operation cycle contains j moments (it should be explained that the time interval between two adjacent moments is not one second and should be determined by the staff according to the actual situation. If a higher-precision generator digital twin model is required, the time between adjacent moments can be appropriately shortened, and vice versa; in addition, the j moments refer to the moments except the starting moment, that is, the moment after the starting moment is used as the first moment (the first moment is also called the initial moment, which is different from the starting moment), until the jth moment of a simulation operation cycle. However, the various measured data still include the operation data and environmental data during the period from the starting moment to the first moment).

[0069] Using the initially constructed generator digital twin model with the current moment as the starting moment, simulate running a simulation operation cycle and record in real time the operation data of the generator digital twin model during this simulation operation cycle. For the voltage, current, rotational speed, vibration, stator temperature, and rotor temperature in the operation data, use a two-dimensional coordinate system to map the change scatter plots respectively. The construction method of the two-dimensional coordinate system is as follows: Use time (this simulation operation cycle, with the scale being one moment) as the horizontal axis and the values of various operation data (such as voltage value, current value, etc.) as the vertical axis to plot the change scatter plots of each operation data over time;

[0070] Respectively obtain the voltage change scatter plot, current change scatter plot, rotational speed change scatter plot, vibration change scatter plot, stator temperature change scatter plot, and rotor temperature change scatter plot, and take the scatter plots of the above generator digital twin model as a group, which is called the change scatter plot set A.

[0071] Then make the actual generator start running for a time of a simulation operation cycle with the same initial moment as that of the generator digital twin model. The time of the simulation operation cycle of this actual generator is the same as that of the generator digital twin model.

[0072] Record in real time the operation data during the operation of the actual generator and obtain the corresponding voltage change scatter plot, current change scatter plot, rotational speed change scatter plot, vibration change scatter plot, stator temperature change scatter plot, and rotor temperature change scatter plot according to the processing method of the generator digital twin model, and take the scatter plots of the above actual generator as a group, which is called the change scatter plot set B.

[0073] A set of change scatter plots A drawn from the operating data obtained by simulating the operation of the digital twin model of the generator within the same simulation operation cycle and a set of change scatter plots B drawn from the operating data obtained by the actual operation of the generator are treated as the same set of data and recorded as the double-sample scatter plot feature vector.

[0074] Based on the obtained double sample scatter plot feature vector, take two change scatter plots of any of the same parameters. Here, take the voltage change scatter plot as an example. Since the horizontal axes are all time units and the scales are the same, they both correspond to the time of the same simulation operation cycle. Therefore, take any moment in this simulation operation cycle. , the two voltage values corresponding to the vertical axis on the two voltage change scatter plots and ;

[0075] For voltage value , get The voltage value corresponding to the previous n consecutive moments The straight-line distance between ,as well as The voltage value corresponding to the next n consecutive moments The straight-line distance between , and then As the radius length , draw a circle and get the voltage value Neighborhood radius The sum of all voltage values within the range (i.e. all voltage values within this circular area) is averaged to obtain the average voltage value. ;

[0076] Similarly, get the voltage value Neighborhood radius The voltage average of all voltage values within the range ;

[0077] What needs to be explained here is that by calculating the average voltage within the neighborhood radius, it is possible to quickly and effectively identify whether abnormal data occurs. If the digital twin model of the generator is consistent with the actual generator, then the average voltage values within the neighborhood radius of their voltage values at a certain moment should be smaller. If the difference is larger, it means that there is abnormal data within the neighborhood radius of the voltage value at that moment simulated by the digital twin model of the generator. If the abnormal data is missing data, then the average voltage value within the neighborhood radius of the voltage value at that moment simulated by the digital twin model of the generator will be smaller. If the abnormal data is redundant data, then the average voltage value within the neighborhood radius of the voltage value at that moment simulated by the digital twin model of the generator will be larger, so as to detect whether abnormal data occurs.

[0078] by the staff for the average voltage and set a preset difference rate , if the average voltage and the difference rate between exceeds the preset difference rate , then it is regarded as that at this moment the two voltage change scatter plots do not match (that is, the voltage parameters in the operation data simulated by the generator digital twin model at this moment do not match the voltage parameters in the actual generator operation data). Take the actual generator here as as the radius length to preliminarily cover the voltage parameters of the generator digital twin model simulated operation within the range of the circle made. Where n is the value preset by the staff, and n is less than i, and i is less than j.

[0079] Preliminarily cover the voltage parameters at each moment of the digital twin model simulated operation, and connect any two adjacent points in the voltage change scatter plot obtained from the digital twin model simulated operation after the preliminary coverage processing and the voltage change scatter plot obtained from the actual generator operation with the shortest line segment. Finally, two voltage change line charts are obtained;

[0080] Because the horizontal and vertical axes of the two voltage change line charts are the same, the two voltage change line charts can be fitted into the same voltage change line chart through image processing technology, that is, there are two line segments in one voltage change line chart, which are recorded as the first line segment and the second line segment , corresponding to the voltage parameters of the actual generator and the generator digital twin model respectively;

[0081] Obtain the moment after the start moment of this simulation operation cycle as the initial moment (the first moment), and construct a straight line passing through the first moment and perpendicular to the horizontal axis on the voltage change line chart with two line segments. This straight line passes through the first line segment and the second line segment , recorded as the initial moment line (the first moment line);

[0082] The initial moment line, the vertical axis, the first line segment and the second line segment form a closed area. Calculate the area of the closed area and record it as the area feature ;

[0083] It should be explained here that the larger the area of the closed area, the greater the difference rate between the voltage parameters of the actual generator and the generator digital twin model corresponding to this area. On the contrary, the smaller. It should be noted here that the first line segment and the second broken line will cross, resulting in multiple closed regions within adjacent moments. For example, between the initial moment line and the vertical axis, the first broken line and the second broken line intersect multiple times, resulting in multiple closed regions. Then calculate the sum of the areas of the multiple closed regions, and denote the result after summation as the area feature .

[0084] Copy the initial moment line to the moment after the first moment (i.e., the second moment), mark the line passing through the second moment as the second moment line, and calculate the area of the closed region formed between the initial moment line, the second moment line, the first broken line and the second broken line and denote it as the area feature ;

[0085] Continue to copy the initial moment line backward to the moment after the second moment (the third moment), and calculate the area of the closed region formed between the third moment line, the second moment line, the first broken line and the second broken line and denote it as the area feature ;

[0086] Until the initial moment line is copied to the last moment (the jth moment) of this simulation operation cycle, and denote the j area features obtained from the calculation as , take any one of the area features and compare it with the area feature threshold preset by the staff . If this area feature is greater than the preset area feature threshold , then it is determined that the voltage parameters of the generator digital twin model simulated between this moment and the previous moment do not match the voltage parameters of the actual generator. Use the voltage parameters of the actual generator between the moment and the previous moment to overwrite the voltage parameters of the generator digital twin model simulated operation;

[0087] Fit the voltage data of the generator digital twin model simulated operation after two overwrite operations into the generator digital twin model and repeat a simulation operation cycle for data correction.

[0088] It should be explained here that the reason for fitting the voltage data obtained from the simulated operation of the generator digital twin model after two covering operations into the generator digital twin model and repeating a simulated operation cycle for data correction, rather than directly using the actual generator operation data for fitting into the digital twin model for simulation and data correction, is as follows: Since the operation data of the actual generator is directly measured by sensors, the data contains noise, errors, or outliers. If these data are directly used for the simulated operation of the digital twin model, it will cause the digital twin model to learn incorrect patterns or deviate from the actual operation law, thus affecting the accuracy and reliability of the digital twin model. By first performing anomaly detection on the simulated operation data of the digital twin model and covering some abnormal data with actual data, it can ensure that the data used for correcting the simulated operation is more accurate and reliable. Through several corrections, finally, a generator digital twin model that can relatively accurately approximate the actual operation state of the actual generator can be obtained.

[0089] Fit all the voltage parameters after two covering operations into the generator digital twin model, repeat a simulated operation cycle for data correction, and process other operation data according to the method of processing voltage parameters, and fit other operation data into the generator digital twin model and repeat a simulated operation cycle for data correction.

[0090] If all the parameters in the operation data obtained from the simulated operation of the generator digital twin model can match the actual generator within consecutive C simulated operation cycles, it is considered that the generator digital twin model can match the actual generator at this time, and the next operation can be carried out. The value of C described here is determined by the staff.

[0091] Embodiment 3

[0092] This embodiment further details Step 3 in Embodiment 1. Based on Step 3, a method for analyzing the operation data obtained from the simulated operation of the generator digital twin model, identifying fault situations, and notifying the staff is disclosed. As Figure 3 shown, it specifically includes the following:

[0093] Based on the generator digital twin model corrected in Embodiment 2, the staff divides the generator digital twin model according to equipment components in combination with the type of the actual generator and the equipment parameters of the actual generator, and sequentially records the divided equipment components as , where is the counting index, starting from 1, and the maximum value is , is the total number of equipment components divided by the generator digital twin model, is any equipment component in the generator digital twin model.

[0094] Based on the calibrated generator digital twin model, use the current time as the start time and simulate running for one simulation cycle.

[0095] For any device component in the generator digital twin model during this simulation cycle , extract the time series operation data of this device component at any moment: , where is a data vector, expressed as , represents the numerical values of all operation data of the device component at moment

[0096] For the device component , there are a total of q different operation data. The q operation data associated with each moment form a data vector, and together they constitute a time series operation data. The time series operation data at one moment can represent the operation state of this device component at this moment, and different time series operation data reflect the operation conditions of this device component at different moments;

[0097] It should be explained here that q is not a fixed value, but a variable counting index, which is determined according to the number of operation data associated with different device components.

[0098] Based on the j moments existing within one simulation cycle, a total of j time series operation data of the component at j different moments can be obtained. Obtain the numerical values of j same-type operation data from the j time series operation data. Taking as an example, we can get the associated data set , calculate the average value and the standard deviation of this data set, and through the normalization formula:

[0099]

[0100] Normalize all the data in the associated data set to the interval [0, 1], and obtain the normalized associated normalized data set . Similarly, according to the above method, the normalized data sets associated with can be obtained respectively;

[0101] Place the normalized operation data into the time-series operation data corresponding to their respective times to obtain the normalized time-series operation data at the time:

[0102]

[0103] Similarly, obtain j normalized time-series operation data corresponding to j times, and fit the normalized time-series operation data corresponding to each time of the equipment component into the equipment state characteristics of the equipment component at that time;

[0104] It should be explained here that all the operation parameter values in the normalized time-series operation data jointly determine the operation state of the equipment component. These operation parameter values are regarded as a data vector from a mathematical perspective at each time. The serialization of the data vector over time completely reflects the operation state of the equipment. Therefore, by analyzing these multi-dimensional data vectors, the characteristic information of the operation state of the equipment component can be extracted. After normalization, data with different dimensions and magnitudes are unified to the same scale, eliminating the dimensional and magnitude differences between the data, which enables direct fitting between different operation data.

[0105] Statistically analyze all the equipment state characteristics within the current simulation operation cycle. A total of j equipment state characteristics are obtained after fitting j normalized time-series operation data. Then, taking time as the horizontal axis of the two-dimensional coordinate system and the fitted equipment state characteristics as the vertical axis of the two-dimensional coordinate system, plot the obtained j equipment state characteristics on the two-dimensional coordinate system and fit them into the equipment component operation state change curve. The horizontal axis of the two-dimensional coordinate system is time, representing a simulation operation cycle of the current simulation operation, with the scale being each time, and the vertical axis is the equipment state characteristic, representing the operation state of the equipment component at the corresponding time.

[0106] Based on the equipment component operation state change curve of the equipment component determined within the current simulation operation cycle, obtain the fluctuation degree of the curve (the fluctuation degree of the curve can be analyzed by Fourier transform to analyze the frequency components of the curve, and the prior art will not be elaborated too much). The smaller the fluctuation degree, the more stable the current equipment component operation is considered; otherwise, it is more unstable. Based on this principle, continuously use the generator digital twin model to simulate and operate for several simulation operation cycles to obtain the equipment component operation state change curves of several components and obtain the fluctuation degrees of several curves;

[0107] The staff sets a fluctuation degree threshold for the fluctuation degree of the curve in combination with the actual generator in the actual working environment, which is used to distinguish the equipment components in the normal operation state from those in the abnormal operation state, and compares the fluctuation degrees of the obtained several curves with the fluctuation degree threshold set by the staff;

[0108] If the fluctuation degree of any curve exceeds the fluctuation degree threshold set by the staff, it is determined that the equipment component within the simulation operation cycle has a fault condition.

[0109] According to the above method, fault identification processing is performed on all equipment components divided by the actual generator, and the equipment components with fault conditions are recorded;

[0110] Continue to use the generator digital twin model to simulate and run several simulation operation cycles, and analyze the simulated operation data to identify the equipment components that will have fault conditions in a future simulation operation cycle.

[0111] Based on the determined equipment components that will have fault conditions, the generator digital twin model is rendered and marked with a highlighted block of a different color from other equipment components, and flashes to remind the staff when the equipment component will have a fault condition;

[0112] Exemplarily, there is a generator. When the generator digital twin model simulates and runs to the sixth simulation operation cycle, the rotor inside the generator fails. The preset duration of a simulation operation cycle by the staff is one week. Then the digital twin model renders the rotor with a color that is clearly divided from other equipment components and flashes to remind the staff. When the staff clicks to view the rotor, it will inform the staff that the rotor will fail in the sixth week after the current time, and the equipment component needs to be replaced or repaired before the sixth week.

[0113] Some of the data in the above formula are numerically calculated after removing their dimensions, and the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0114] The above content is only an example and explanation of the present invention. Those skilled in the art of this technology make various modifications or supplements to the described specific embodiments or use similar methods to replace them. As long as they do not deviate from the invention or exceed the scope defined by the claims of the present invention, they should fall within the protection scope of the present invention.

[0115] It should be stated that: all user data collected in this application are collected with the consent and authorization of the users. And the uses of user data are legal and compliant, and the use and processing of user data comply with the relevant laws, regulations and standards of the relevant regions.

Claims

1. A three-dimensional visualization warning method for generator faults, characterized in that, The method includes the following steps: S1. Obtain generator equipment parameters, operation data, and environmental data, and use digital twin technology to construct a digital twin model of the generator; S2. Continuously collect actual generator operation data to correct the constructed digital twin model of the generator until the constructed digital twin model of the generator fits the actual generator. The specific method of correction is as follows: S21. Based on the constructed digital twin model of the generator, taking the current moment as the starting moment, simulate running for a simulation running cycle. The duration of the simulation running cycle is set by the staff, and a simulation running cycle includes j moments; S22. During a simulated operation cycle, obtain the operation data obtained from the simulated operation of the digital twin model of the generator, and on a two-dimensional coordinate system, with time as the horizontal axis and the values of various operation data as the vertical axis, plot the scatter diagrams of the changes of each operation data over time to form a set of scatter diagram sets A of changes; S23. Obtain the operating data of the actual generator when running a simulation operation cycle with the current moment as the start moment, and repeat the method described in S32 to obtain a set of variation scatter plot sets B; S24. Take the scatter diagram set A of changes and the scatter diagram set B of changes as the same group, and denote it as a double-sample scatter diagram feature vector; S25. Based on the obtained two-sample scatter plot feature vectors, take the voltage values corresponding to a certain moment on the vertical axis of two of the voltage change scatter plots at two voltage values corresponding to the vertical axis and ; Take the straight-line distance between the voltage values corresponding to the previous n consecutive moments , take the straight-line distance between the voltage values corresponding to the next n consecutive moments , and use as the radius length to draw a circle, obtain the sum of all voltage values inside the circle and take the average to get the average voltage ; Similarly, obtain the average voltage ; If and the difference rate exceeds the difference rate preset by the staff , it is considered that the two voltage change scatter plots do not fit at this moment , and the voltage parameters of the actual generator within this circle are used to overwrite the voltage parameters of the simulated operation of the generator digital twin model, where n is the value preset by the staff, and n is less than i, and i is less than j; S26. Convert the two voltage change scatter diagrams after the covering process into two voltage change line diagrams, and fit them into the same voltage change line diagram for further analysis; S3. Obtain the operation data of the simulated operation of the digital twin model of the generator for analysis, identify the generator fault conditions, map the identified generator fault conditions to the digital twin model of the generator in real time, and issue a warning reminder to the staff.

2. The three-dimensional visualization warning method for generator faults according to claim 1, characterized in that, In step S26, the specific method of converting the two voltage change scatter diagrams after the covering process into two voltage change line diagrams and fitting them into the same voltage change line diagram for further analysis also includes the following: S261. Based on two scatter plots of voltage changes, connect any two adjacent points with the shortest line segments to obtain two line charts of voltage changes, and fit the two line charts of voltage changes into the same line chart of voltage changes to obtain the first line and the second line , corresponding to the actual generator and the digital twin model of the generator respectively; S262. Obtain the first moment after the start moment as the initial moment, construct an initial moment line passing through the initial moment and perpendicular to the horizontal axis, and calculate the area feature formed between the initial moment line, the vertical axis, the first polyline and the second polyline ; ; S263. Copy the initial time line to the next time after the initial time, denoted as the second time line, and calculate the area feature formed by the initial time line, the second time line, the first polyline and the second polyline ; ; S264. Repeat step S263 until the last moment of this simulation operation cycle, obtaining a total of j area features, denoted as , and respectively compare the obtained j area features with the area feature threshold preset by the staff. If any area feature , it is considered that the voltage parameters of the simulated operation of the generator digital twin model between this moment and the previous moment do not match the voltage parameters of the actual generator, and the voltage parameters of the simulated operation of the generator digital twin model are overwritten with the voltage parameters of the actual generator; S265. Place the voltage parameters of the simulated operation of the digital twin model of the generator after the covering operation in the digital twin model of the generator to run for a simulated operation cycle for data correction.

3. The three-dimensional visualization warning method for generator faults according to claim 2, wherein Place the voltage parameters of the simulated operation of the digital twin model of the generator after the covering operation in the digital twin model of the generator to run for a simulated operation cycle for data correction, and according to the method of processing voltage parameters, process other operation data to perform data correction on the digital twin model of the generator.

4. A three-dimensional visualization warning method for generator faults according to claim 3, characterized in that, The specific judgment method for the constructed digital twin model of the generator to fit the actual generator is as follows: If the operation data of the simulated operation of the digital twin model of the generator in continuous C simulated operation cycles are all in line with the actual generator, it is regarded that the digital twin model of the generator fits the actual generator, and the value of C is set by the staff.

5. A three-dimensional visualization warning method for generator faults according to claim 4, characterized in that, The specific method of identifying the generator fault conditions described in step S3 is as follows: Divide the digital twin model of the generator according to the total number of equipment components. After division, u equipment components are obtained and are denoted in sequence as , where u is a counting index representing the total number of equipment components, and are u equipment components: Any one of them, and v is also a counting index. v starts from 1, and the maximum value of v is u; Make the digital twin model of the generator simulate running for a simulated operation cycle; Extraction device components At any moment during the simulation operation cycle The time series operation data at that moment: , where is a data vector, representing the component at the moment The numerical values of all operation data at that time, with a total of q different operation data; Based on j moments, obtain the operating data of the device components in j moment sequences Take as an example, and obtain the associated data set , calculate the average value of the data set and the standard deviation , through the normalization formula: Normalize all the data in the dataset to the range of 0 to 1 to obtain a normalized dataset . Similarly, obtain the normalized associated normalized datasets respectively; Place the normalized operation data into the time-series operation data corresponding to their respective times, obtaining the normalized time-series operation data at time : Similarly, j normalized time series operation data corresponding to j moments are obtained, and each normalized time series operation data is fitted into the device state characteristics of the device component at this moment, and the curve of the operation state change of the device component is plotted on a two-dimensional coordinate system and the fluctuation degree of the curve is obtained; Simulate running for several simulated operation cycles to obtain the fluctuation degrees of several curves; Compare the fluctuation degrees of several curves with the fluctuation degree threshold set by the staff respectively. If the fluctuation degree of any curve exceeds the fluctuation degree threshold set by the staff, it is determined that the equipment component has a fault situation; According to the above method, perform fault identification processing on all equipment components in the actual generator, identify the component equipment with fault conditions, and obtain the simulated operation cycle in which the component equipment has fault conditions.

6. A three-dimensional visualization warning method for generator faults according to claim 5, characterized in that The specific method of mapping the identified generator fault conditions to the digital twin model of the generator in real time and issuing a warning reminder to the staff is as follows: For the equipment components that encounter failure situations, the generator digital twin model uses a highlighted block in a different color from other equipment components to flash and mark, informing the staff of when the equipment component will encounter a failure situation, and warning and reminding the staff to perform maintenance or replacement in a timely manner before the equipment component fails.

Images