Generator set operation and maintenance data analysis system and method based on three-dimensional modeling

Abstract

The application discloses a generator set operation and maintenance data analysis system and method based on three-dimensional modeling, and belongs to the technical field of data processing. The system obtains generator set data, obtains the structure, working principle and operation parameters of the generator set, constructs a three-dimensional model of the generator set, fuses a hydropower field three-dimensional model, the three-dimensional model of the generator set and an electromagnetic field simulation environment into an overall digital twin model, constructs a stator electromagnetic characteristic extraction and loss evaluation model, extracts features from the obtained electromagnetic parameters, performs electromagnetic loss evaluation on the generator set, constructs a generator set electromagnetic diagnosis and early warning model, establishes a normal working benchmark and a fault database, compares the model prediction situation with the actual situation, and triggers early warning when an anomaly is detected. The system realizes comprehensive quantification and fault diagnosis on the internal electromagnetism of the stator of the generator set through fault feature extraction, electromagnetic calculation, loss evaluation and intelligent early warning functions, and improves the operation safety and maintenance efficiency of the equipment.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, specifically a generator set operation and maintenance data analysis system and method based on three-dimensional modeling. Background Technology

[0002] With the continuous development of power systems and the increasing demands for reliable power supply, the operation and maintenance of generator sets have become crucial. As one of the core pieces of equipment in a power system, the operating status of generator sets directly affects the stable supply of power and the safe operation of the system. Effective operation and maintenance can promptly detect potential faults, prevent equipment accidents, extend equipment lifespan, reduce maintenance costs, improve power generation efficiency and power quality, and ensure the reliability and economy of the power system. Existing monitoring methods mainly rely on single or a few sensors to collect data such as temperature, vibration, current, and voltage in real time. However, these data often lack comprehensiveness and are insufficient to fully reflect the operating status of the equipment. Data from different monitoring systems suffers from silo effects, failing to form a systematic and continuous basis for fault diagnosis. During generator operation, electromagnetic forces cause electromagnetic vibrations in components such as the stator. These vibrations not only affect the operational stability of the generator set but can also lead to mechanical damage and insulation aging. Electromagnetic losses result in reduced generator efficiency and significant energy waste. Furthermore, electromagnetic losses cause the equipment to heat up, affecting its insulation performance and lifespan. Current technologies lack fault detection and energy consumption assessment capabilities for stator electromagnetic vibration.

[0003] This invention aims to improve equipment operation safety and maintenance efficiency by constructing a generator set fault diagnosis system based on three-dimensional modeling and multi-field coupling simulation, integrating data acquisition, real-time monitoring, fault feature extraction, electromagnetic force calculation, loss assessment, and intelligent early warning functions. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention proposes a generator set operation and maintenance data analysis system and method based on three-dimensional modeling.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] Acquire generator set data, including the generator set's structure, working principle, and operating parameters;

[0007] Construct a 3D model of the generator set, and integrate the 3D model of the hydroelectric field, the 3D model of the generator set, and the electromagnetic field simulation environment into a unified digital twin model;

[0008] A model for extracting stator electromagnetic characteristics and assessing losses was constructed. The acquired electromagnetic parameters were feature extracted, and the electromagnetic losses of the generator set were assessed.

[0009] An electromagnetic diagnostic and early warning model for generator sets is constructed. By establishing normal operating benchmarks and a fault database, the model's predictions are compared with the actual situation, and an early warning is triggered when an anomaly is detected.

[0010] The generator set operation and maintenance data analysis method based on 3D modeling includes the following specific steps:

[0011] Preferably, the step of acquiring generator set data, including the generator set's structure, working principle, and operating parameters, includes the following specific steps:

[0012] S11. Obtain the structural data of the generator set equipment, and collect the operating data and environmental data of the generator set in real time through sensors and monitoring instruments, and store the acquired data in the generator set operation database.

[0013] S12. Obtain historical fault data and establish a generator set fault database;

[0014] S13. Obtain vibration conditions and electromagnetic parameters caused by electromagnetic factors through electromagnetic sensors.

[0015] Preferably, the construction of the generator set three-dimensional model, which integrates the hydroelectric field three-dimensional model, the generator set three-dimensional model, and the electromagnetic field simulation environment into a unified digital twin model, includes the following specific steps:

[0016] S21. Input the actual measured natural data as boundary conditions into the fluid dynamics software (CFD software) to perform three-dimensional modeling of the hydroelectric field and obtain the hydraulic information inside and around the hydroelectric field.

[0017] S22. Based on the structural data, working principle and operating parameters of the generator set, import them into modeling software (such as BIM, CAD and other software) to perform three-dimensional modeling of the generator set, and map the real-time collected data to the three-dimensional model;

[0018] S23. Construct an electromagnetic field simulation environment in the three-dimensional model of the generator set, set corresponding boundary conditions and physical parameters according to electromagnetic field theory and vibration field theory, simulate and analyze the electromagnetic field distribution inside the generator set, and associate the electromagnetic parameters with the various components of the three-dimensional model.

[0019] S24. Integrate the three-dimensional model of the hydroelectric field, the three-dimensional model of the generator set, and the electromagnetic field simulation environment to construct an overall digital twin model of the generator set.

[0020] Preferably, the construction of the stator electromagnetic characteristic extraction and loss assessment model, which involves feature extraction of the acquired electromagnetic parameters and assessment of the generator set electromagnetic losses, includes the following specific steps:

[0021] S31. Preprocess the collected electromagnetic data and extract electromagnetic vibration characteristic parameters using wavelet transform. The wavelet transform denoising function is: Where x(t) is the time-domain signal, W(a,b) is the wavelet transform denoising function, a is the scale parameter, b is the translation parameter, and ψ(t) is the mother wavelet function. The characteristic frequency, amplitude, and phase of the stator electromagnetic vibration are extracted through wavelet transform.

[0022] S32. Based on the electromagnetic simulation results, calculate the local electromagnetic forces on and inside the stator surface. The formula for calculating the electromagnetic force is: F=∫ S J×BdS, where S is the stator surface area, J is the local current density, and B is the magnetic induction intensity. The calculated electromagnetic force distribution is applied as an external load to the three-dimensional model of the stator, and subsequent static structural analysis is performed in the simulation software.

[0023] S33. Evaluate the energy efficiency of the generator set by calculating electromagnetic losses, wherein the formula for calculating total electromagnetic losses is: P = P e +P h +P c , where P e Eddy current loss is calculated using the following formula: P h Hysteresis loss is calculated using the formula: P h =ηB n f, P c For resistance loss, the formula for calculating resistance loss is: P c =I 2 R, where B is the magnetic flux density, d is the core thickness, f is the alternating magnetic field frequency, ρ is the resistivity of the core material, η is the hysteresis coefficient, n is the hysteresis exponent, I is the current, and R is the winding resistance.

[0024] Preferably, the construction of the generator set electromagnetic diagnostic and early warning model, by establishing a normal operating benchmark and a fault database, comparing the model's predictions with the actual situation, and triggering an early warning when an anomaly is detected, includes the following specific steps:

[0025] S41. Obtain normal operating parameters of the generator set, determine the natural frequency and mode shape of the stator, and establish a normal operating condition reference.

[0026] S42. Establish a generator set electromagnetic vibration fault mode database. Import historical generator fault types into the database. Use machine learning to compare the extracted feature values ​​with the fault types in the database to obtain the coupled simulation results in the 3D model. Locate the fault location using the 3D model. Compare the electromagnetic force distribution and electromagnetic loss simulation data obtained from the 3D model with the actual data. Correct the model parameters using historical fault cases. Measure the average deviation between the model's predicted values ​​and the actual measured values ​​using the root mean square error (RMSE). Compare the current generator set's electromagnetic loss data with the normal average data of similar generator sets to evaluate the current generator set's electromagnetic performance relative to other generator sets of the same type. The RMSE calculation formula is as follows: Where m is the number of predicted values, P i M represents the model's predicted value. i These are actual measured values;

[0027] S43. Set electromagnetic force distribution and electromagnetic loss thresholds. When the evaluated electromagnetic force distribution and electromagnetic loss values ​​exceed the set thresholds, an early warning is immediately triggered, and abnormal areas are marked on the digital twin platform. Based on the fault diagnosis results and over-mean square error calculation, maintenance suggestions are automatically generated, and collaborative optimization is achieved in conjunction with the cross-site data sharing platform.

[0028] The generator set operation and maintenance data analysis system based on 3D modeling is implemented based on the aforementioned 3D modeling-based generator set operation and maintenance data analysis method, and specifically includes:

[0029] The data acquisition module is used to acquire the structure, working principle, and operating parameters of the generator set;

[0030] The 3D model building module is used to integrate the 3D model of the hydroelectric field, the 3D model of the generator set, and the electromagnetic field simulation environment into a unified digital twin model;

[0031] The stator electromagnetic characteristic extraction and loss assessment module is used to extract features from the acquired electromagnetic parameters and assess the electromagnetic loss of the generator set.

[0032] The electromagnetic diagnostic and early warning module is used to establish normal working benchmarks and fault databases, compare model predictions with actual conditions, and trigger early warnings when an anomaly is detected.

[0033] An electronic device includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0034] The processor executes the above-described generator set operation and maintenance data analysis method based on three-dimensional modeling by calling the computer program stored in the memory.

[0035] A computer-readable storage medium is characterized by storing instructions that, when executed on a computer, cause the computer to perform the aforementioned generator set operation and maintenance data analysis method based on three-dimensional modeling.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] This invention acquires generator set data, including the generator set's structure, working principle, and operating parameters. It constructs a 3D model of the generator set, integrates the 3D model of the hydroelectric field, the 3D model of the generator set, and the electromagnetic field simulation environment into a unified digital twin model, and builds a stator electromagnetic characteristic extraction and loss assessment model. The acquired electromagnetic parameters are feature-extracted, and the electromagnetic loss of the generator set is assessed. An electromagnetic diagnosis and early warning model for the generator set is constructed, and a normal operating benchmark and fault database are established. The model's predictions are compared with actual conditions, and an early warning is triggered when an anomaly is detected. Through fault feature extraction, electromagnetic calculation, loss assessment, and intelligent early warning functions, this invention achieves comprehensive quantification and fault diagnosis of the electromagnetic components inside the generator set stator, improving equipment operating safety and maintenance efficiency. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the overall process of the generator set operation and maintenance data analysis method based on three-dimensional modeling according to the present invention;

[0039] Figure 2 This is a schematic diagram of a 3D modeling method for generator set operation and maintenance data analysis based on 3D modeling, as described in this invention.

[0040] Figure 3 This is a schematic diagram of the overall framework of the generator set operation and maintenance data analysis system based on three-dimensional modeling according to the present invention. Detailed Implementation

[0041] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0042] Example 1

[0043] Please see Figure 1-2 The present invention provides an embodiment of a generator set operation and maintenance data analysis method based on three-dimensional modeling, which includes the following specific steps:

[0044] Acquire generator set data, including the generator set's structure, working principle, and operating parameters;

[0045] Construct a 3D model of the generator set, and integrate the 3D model of the hydroelectric field, the 3D model of the generator set, and the electromagnetic field simulation environment into a unified digital twin model;

[0046] A model for extracting stator electromagnetic characteristics and assessing losses was constructed. The acquired electromagnetic parameters were feature extracted, and the electromagnetic losses of the generator set were assessed.

[0047] An electromagnetic diagnostic and early warning model for generator sets is constructed. By establishing normal operating benchmarks and a fault database, the model's predictions are compared with the actual situation, and an early warning is triggered when an anomaly is detected.

[0048] In this embodiment, it should be specifically explained that obtaining generator set data, including the generator set's structure, working principle, and operating parameters, includes the following specific steps:

[0049] S11. Obtain generator set equipment structure data. Collect generator set operation data and environmental data in real time through sensors and monitoring instruments, and store the acquired data in the generator set operation database. Among them, generator set equipment structure data includes generator set structure, working principle and operating parameters. Operation data includes vibration, current, voltage, etc., and environmental data includes humidity, air pressure, temperature, etc.

[0050] S12. Obtain historical fault data and establish a generator set fault database;

[0051] S13. Obtain vibration conditions and electromagnetic parameters caused by electromagnetic factors through electromagnetic sensors.

[0052] In this embodiment, it is necessary to specifically explain that constructing a three-dimensional model of the generator set and integrating the three-dimensional model of the hydroelectric field, the three-dimensional model of the generator set, and the electromagnetic field simulation environment into a unified digital twin model includes the following specific steps:

[0053] S21. Input the actual measured natural data as boundary conditions into the fluid dynamics software (CFD software) to perform three-dimensional modeling of the hydroelectric field and obtain the hydraulic information inside and around the hydroelectric field.

[0054] S22. Based on the structural data, working principle and operating parameters of the generator set, import them into modeling software (such as BIM, CAD and other software) to perform three-dimensional modeling of the generator set, and map the real-time collected data to the three-dimensional model;

[0055] S23. Construct an electromagnetic field simulation environment in the three-dimensional model of the generator set. Set the corresponding boundary conditions and physical parameters according to electromagnetic field theory and vibration field theory. Among them, the formula for calculating the relationship between magnetic field and magnetic induction intensity is: B=μH, and the formula for calculating magnetic flux is: φ=∫ S B·dS, where μ is the permeability of the medium, H is the magnetic field strength, B is the magnetic induction intensity, and dS is the differential area vector, is used to simulate and analyze the electromagnetic field distribution inside the generator set, and to associate the electromagnetic parameters with the various components of the three-dimensional model.

[0056] S24. Integrate the three-dimensional model of the hydroelectric field, the three-dimensional model of the generator set, and the electromagnetic field simulation environment to construct an overall digital twin model of the generator set.

[0057] In this embodiment, it is necessary to specifically explain that the construction of the stator electromagnetic characteristic extraction and loss assessment model, the feature extraction of the acquired electromagnetic parameters, and the assessment of generator set electromagnetic losses include the following specific steps:

[0058] S31. Preprocess the collected electromagnetic data and extract electromagnetic vibration characteristic parameters using wavelet transform. The wavelet transform denoising function is: Where x(t) is the time-domain signal, W(a,b) is the wavelet transform denoising function, a is the scale parameter, b is the translation parameter, and ψ(t) is the mother wavelet function. The characteristic frequency, amplitude, and phase of the stator electromagnetic vibration are extracted by wavelet transform. Wavelet transform has denoising capability. By calculating the wavelet transform coefficients and selecting an appropriate threshold for denoising, noise components can be suppressed and useful information in the signal can be enhanced.

[0059] S32. Based on the electromagnetic simulation results, calculate the local electromagnetic forces on and inside the stator surface. The formula for calculating the electromagnetic force is: F=∫ S J×BdS, where S is the stator surface area, J is the local current density, and B is the magnetic induction intensity. The calculated electromagnetic force distribution is applied as an external load to the three-dimensional model of the stator, and subsequent static structural analysis is performed in the simulation software. This formula is derived from the Lorentz force law, which quantifies the magnitude and direction of the electromagnetic force. During the calculation, the total electromagnetic force borne by each region is obtained by integration, and the direction of force is determined according to the current direction and magnetic field distribution. Through calculation, regions bearing high electromagnetic loads can be identified as locations of structural stress concentration. The electromagnetic force distribution is compared with actual measurement data to correct the parameters of the three-dimensional model, thereby providing reliable data support for the real-time early warning system. Once the electromagnetic force in a certain region exceeds the normal range, the system can trigger an early warning.

[0060] S33. Evaluate the energy efficiency of the generator set by calculating electromagnetic losses, wherein the formula for calculating total electromagnetic losses is: P = P e +P h +P c , where P e Eddy current loss is calculated using the following formula: P h Hysteresis loss is calculated using the formula: P h =ηB n f, P c For resistance loss, the formula for calculating resistance loss is: P c =I2 R, where B is the magnetic flux density, d is the core thickness, f is the alternating magnetic field frequency, ρ is the resistivity of the core material, η is the hysteresis coefficient, n is the hysteresis exponent, I is the current, and R is the winding resistance.

[0061] In this embodiment, it is necessary to specifically explain that the construction of the generator set electromagnetic diagnostic and early warning model, by establishing a normal working benchmark and fault database, comparing the model's predictions with the actual situation, and triggering an early warning when an anomaly is detected, includes the following specific steps:

[0062] S41. Obtain normal operating parameters of the generator set, determine the natural frequency and mode shape of the stator, and establish a normal operating condition reference.

[0063] S42. Establish a generator set electromagnetic vibration fault mode database. Import historical generator fault types into the database. Use machine learning (such as convolutional neural networks or random forests) to compare the extracted feature values ​​with the fault types in the database, obtain the coupled simulation results in the 3D model, locate the fault location using the 3D model, compare the electromagnetic force distribution and electromagnetic loss simulation data obtained from the 3D model with the actual data, and correct the model parameters using historical fault cases. Use the root mean square error (RMSE) to measure the average deviation between the model's predicted values ​​and the actual measured values. Compare the current generator set's electromagnetic loss data with the normal average data of similar generator sets to evaluate the current generator set's electromagnetic performance at the same level as other generator sets. The RMSE calculation formula is: Where m is the number of predicted values, P i M represents the model's predicted value. i These are actual measured values;

[0064] S421. Compare the current electromagnetic loss data with historical data, analyze the trend of electromagnetic loss, and determine whether there are signs of aging, wear or failure in the generator set. If the electromagnetic loss of the current generator set is significantly higher than that of the same type of generator set, analyze the electromagnetic loss of the generator set under different operating conditions (such as different loads, different speeds, different cooling conditions, etc.) and find the fault type through the fault database.

[0065] S422. Use offline historical data for cross-validation to evaluate the stability of the model on different datasets, perform parameter sensitivity analysis, test preset faults in actual operating environment, and record the timing and amplitude errors between model predictions and actual faults.

[0066] S43. Set electromagnetic force distribution and electromagnetic loss thresholds. When the evaluated electromagnetic force distribution and electromagnetic loss values ​​exceed the set thresholds, an early warning is immediately triggered, and abnormal areas are marked on the digital twin platform. Based on the fault diagnosis results and over-mean square error calculation, maintenance suggestions (such as local insulation detection, winding replacement, or structural optimization) are automatically generated, and collaborative optimization is achieved in conjunction with the cross-site data sharing platform.

[0067] In this embodiment, it is necessary to specifically explain the method for determining the electromagnetic force distribution and electromagnetic loss threshold: obtain representative electromagnetic force distribution and electromagnetic loss data of generator sets, and evaluate whether the fault assessment requirements are met through three-dimensional model, machine learning, and expert manual assessment. At the same time, substitute the obtained historical data of the generator set related to electromagnetic factors into the calculation results and judgment results of each step in this embodiment, and then substitute them into the fitting software to output the threshold that meets the highest judgment accuracy.

[0068] The advantages of this embodiment compared to the prior art are:

[0069] This invention acquires generator set data, including the generator set's structure, working principle, and operating parameters. It constructs a 3D model of the generator set, integrates the 3D model of the hydroelectric field, the 3D model of the generator set, and the electromagnetic field simulation environment into a unified digital twin model, and builds a stator electromagnetic characteristic extraction and loss assessment model. The acquired electromagnetic parameters are feature-extracted, and the electromagnetic loss of the generator set is assessed. An electromagnetic diagnosis and early warning model for the generator set is constructed, and a normal operating benchmark and fault database are established. The model's predictions are compared with actual conditions, and an early warning is triggered when an anomaly is detected. Through fault feature extraction, electromagnetic calculation, loss assessment, and intelligent early warning functions, this invention achieves comprehensive quantification and fault diagnosis of the electromagnetic components inside the generator set stator, improving equipment operating safety and maintenance efficiency.

[0070] Example 2

[0071] like Figure 3 As shown, the generator set operation and maintenance data analysis system based on 3D modeling is implemented based on the aforementioned 3D modeling-based generator set operation and maintenance data analysis method. Specifically, it includes a data acquisition module, a 3D model construction module, a stator electromagnetic characteristic extraction and loss assessment module, and an electromagnetic diagnosis and early warning module. The data acquisition module is used to acquire the generator set's structure, working principle, and operating parameters. The 3D model construction module is used to integrate the hydroelectric field 3D model, the generator set 3D model, and the electromagnetic field simulation environment into a unified digital twin model. The stator electromagnetic characteristic extraction and loss assessment module is used to extract features from the acquired electromagnetic parameters and assess the generator set's electromagnetic losses. The electromagnetic diagnosis and early warning module is used to establish normal operating benchmarks and a fault database, compare the model's predictions with the actual situation, and trigger an early warning when an anomaly is detected.

[0072] Example 3

[0073] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0074] The processor executes the aforementioned generator set operation and maintenance data analysis method based on 3D modeling by calling computer programs stored in memory.

[0075] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the generator set operation and maintenance data analysis method based on 3D modeling provided in the above-described embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Further details are omitted in this embodiment.

[0076] Example 4

[0077] This embodiment proposes a computer-readable storage medium on which an erasable and rewritable computer program is stored.

[0078] When the computer program runs on the computer device, it causes the computer device to execute the above-mentioned generator set operation and maintenance data analysis method based on 3D modeling.

[0079] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage devices.

[0080] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives.

Claims

1. A method for analyzing generator set operation and maintenance data based on 3D modeling, characterized in that, It includes the following specific steps: Acquire generator set data, including the generator set's structure, working principle, and operating parameters; Construct a 3D model of the generator set, and integrate the 3D model of the hydroelectric field, the 3D model of the generator set, and the electromagnetic field simulation environment into a unified digital twin model; A model for extracting stator electromagnetic characteristics and assessing losses was constructed. The acquired electromagnetic parameters were feature extracted, and the electromagnetic losses of the generator set were assessed. S31. Preprocess the collected electromagnetic data and extract electromagnetic vibration characteristic parameters using wavelet transform. The wavelet transform denoising function is: ,in, For time-domain signals, Let be the wavelet transform denoising function, where 'a' is the scaling parameter and 'b' is the translation parameter. For the mother wavelet function; S32. Based on the electromagnetic simulation results, calculate the local electromagnetic forces on and inside the stator surface. The formula for calculating the electromagnetic force is as follows: Where S is the stator surface area, J is the local current density, and B is the magnetic induction intensity, the calculated electromagnetic force distribution is applied as an external load to the three-dimensional model of the stator, and subsequent static structural analysis is performed in the simulation software. During the calculation process, the total electromagnetic force borne by each region is obtained by integration, and the direction of force is determined according to the current direction and magnetic field distribution. The region bearing high electromagnetic load is identified by calculation, which becomes the location of structural stress concentration. The electromagnetic force distribution is compared with the actual measurement data to correct the parameters of the three-dimensional model. S33. Evaluate the energy efficiency of the generator set through the calculation of electromagnetic losses, wherein the formula for calculating the total electromagnetic losses is: ,in, Eddy current loss is calculated using the following formula: , Hysteresis loss is calculated using the following formula: , For resistance loss, the formula for calculating resistance loss is: Where B is the magnetic flux density, d is the core thickness, and f is the frequency of the alternating magnetic field. The resistivity of the iron core material. Where is the hysteresis coefficient, n is the hysteresis exponent, I is the current, and R is the winding resistance; An electromagnetic diagnostic and early warning model for generator sets is constructed. By establishing normal operating benchmarks and a fault database, the model's predictions are compared with the actual situation, and an early warning is triggered when an anomaly is detected. The specific steps include the following: S41. Obtain normal operating parameters of the generator set, determine the natural frequency and mode shape of the stator, and establish a normal operating condition reference. S42. Establish a generator set electromagnetic vibration fault mode database, import historical generator fault types into the generator set electromagnetic vibration fault mode database, compare the extracted feature values ​​with the fault types in the database through machine learning, obtain the coupling simulation results in the three-dimensional model, locate the fault location through the three-dimensional model, compare the electromagnetic force distribution and electromagnetic loss simulation data obtained from the three-dimensional model with the actual data, and correct the model parameters through historical fault cases. Measure the average deviation between the model prediction value and the actual measurement value through root mean square error, compare the electromagnetic loss data of the current generator set with the normal average data of the same type of generator set, and evaluate the electromagnetic performance of the current generator set at the level of the same generator set. S421. Compare the current electromagnetic loss data with historical data, analyze the trend of electromagnetic loss, determine whether there are signs of aging, wear or failure in the generator set, analyze the electromagnetic loss of the generator set under different operating conditions, and find the fault type through the fault database. S422. Use offline historical data for cross-validation to evaluate the stability of the model on different datasets, perform parameter sensitivity analysis, test the preset faults in the actual operating environment, and record the timing and amplitude errors between the model prediction and the actual faults. S43. Set electromagnetic force distribution and electromagnetic loss thresholds. When the evaluated electromagnetic force distribution and electromagnetic loss values ​​exceed the set thresholds, an early warning is immediately triggered, and abnormal areas are marked on the digital twin platform. Based on the fault diagnosis results and over-mean square error calculation, maintenance suggestions are automatically generated.

2. The generator set operation and maintenance data analysis method based on three-dimensional modeling as described in claim 1, characterized in that, The construction of the generator set 3D model, which integrates the hydroelectric field 3D model, the generator set 3D model, and the electromagnetic field simulation environment into a unified digital twin model, includes the following specific steps: S21. Input the actual measured natural data as boundary conditions into the fluid dynamics software to perform three-dimensional modeling of the hydroelectric field and obtain the hydraulic information inside and around the hydroelectric field. S22. Based on the structural data, working principle and operating parameters of the generator set, import them into the modeling software to perform three-dimensional modeling of the generator set, and map the real-time collected data onto the three-dimensional model; S23. Construct an electromagnetic field simulation environment in the three-dimensional model of the generator set, set corresponding boundary conditions and physical parameters according to electromagnetic field theory and vibration field theory, simulate and analyze the electromagnetic field distribution inside the generator set, and associate the electromagnetic parameters with the various components of the three-dimensional model. S24. Integrate the three-dimensional model of the hydroelectric field, the three-dimensional model of the generator set, and the electromagnetic field simulation environment to construct an overall digital twin model of the generator set.

3. The generator set operation and maintenance data analysis method based on three-dimensional modeling as described in claim 2, characterized in that, The process of acquiring generator set data, including the generator set's structure, working principle, and operating parameters, includes the following specific steps: S11. Obtain the structural data of the generator set equipment, and collect the operating data and environmental data of the generator set in real time through sensors and monitoring instruments, and store the acquired data in the generator set operation database. S12. Obtain historical fault data and establish a generator set fault database; S13. Obtain vibration conditions and electromagnetic parameters caused by electromagnetic factors through electromagnetic sensors.

4. A generator set operation and maintenance data analysis system based on three-dimensional modeling, which is implemented based on the generator set operation and maintenance data analysis method based on three-dimensional modeling as described in any one of claims 1-3, characterized in that, Specifically, it includes: The data acquisition module is used to acquire the structure, working principle, and operating parameters of the generator set; The 3D model building module is used to integrate the 3D model of the hydroelectric field, the 3D model of the generator set, and the electromagnetic field simulation environment into a unified digital twin model; The stator electromagnetic characteristic extraction and loss assessment module is used to extract features from the acquired electromagnetic parameters and assess the electromagnetic loss of the generator set. The electromagnetic diagnostic and early warning module is used to establish normal working benchmarks and fault databases, compare model predictions with actual conditions, and trigger early warnings when an anomaly is detected.

5. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor is characterized in that it executes the generator set operation and maintenance data analysis method based on three-dimensional modeling as described in any one of claims 1-3 by calling a computer program stored in the memory.

6. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform a generator set operation and maintenance data analysis method based on three-dimensional modeling as described in any one of claims 1-3.

Images