Fault diagnosis method and device for turbine generator and readable storage medium
By collecting and fusing the electromechanical operating parameters of the turbine generator in real time, and using the electromechanical coupling correlation model to dynamically determine the reference range, the problem of misjudgment of high-speed turbine generators under complex operating conditions is solved, and high-precision fault diagnosis and system stability are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-03
- Publication Date
- 2026-03-10
AI Technical Summary
Existing technologies for condition monitoring and fault diagnosis of high-speed turbine generators, especially under complex operating conditions, have a high misjudgment rate, leading to frequent false alarms, affecting system reliability, and potentially causing unnecessary downtime and economic losses.
By collecting the electromechanical operating parameters of the turbine generator in real time, including the operating condition definition parameters and the parameters to be diagnosed, the expected reference range is dynamically determined using the electromechanical coupling correlation model. Through the fusion diagnosis of multi-dimensional electrical and mechanical parameters, abnormal indication signals are generated, and finally, the fault diagnosis results are output.
It significantly improves the accuracy and reliability of diagnosis, reduces false alarms and missed alarms, adapts to complex operating conditions, and enhances the accuracy of fault identification and the stability of the system.
Smart Images
Figure CN121633830A_ABST
Abstract
Description
Technical Field
[0001] This specification relates to the field of turbine generator technology, and in particular to a fault diagnosis method, device and readable storage medium for a turbine generator. Background Technology
[0002] As a key energy conversion device, the operating status of high-speed turbine generators directly affects system stability and equipment lifespan.
[0003] In the field of condition monitoring and fault diagnosis of turbine generators, especially high-speed turbine generators, a widely used technique is to synchronously sample the phase of the stator current and analyze specific excitation signals in the spectrum to detect rotor or gear faults. However, the actual operating conditions of high-speed turbines are complex and variable, especially those involving speed variations. The current method, which relies solely on electrical signal spectrum analysis, lacks adaptability and robustness, easily leading to misdiagnosis or missed diagnosis. Frequent false alarms not only reduce the reliability of the monitoring system and interfere with the judgment of maintenance personnel, but more seriously, they can cause unnecessary equipment downtime, resulting in significant production and economic losses. Summary of the Invention
[0004] To address the aforementioned technical problems, this specification provides the following technical solutions: Firstly, a fault diagnosis method for a turbine generator is provided, the method comprising: The electromechanical operating parameters of the turbine generator are collected in real time, including at least one operating condition definition parameter and one or more parameters to be diagnosed. Based on the current value of the operating condition definition parameter, the expected reference range of the parameter to be diagnosed corresponding to the current operating condition is dynamically determined; The actual measured value of the parameter to be diagnosed is compared with the expected reference range, and one or more abnormal indication signals are generated based on the comparison results; Based on the combination of one or more abnormal indication signals, a fault diagnosis result for the turbine generator is output.
[0005] In some embodiments, dynamically determining the expected reference range of the parameter to be diagnosed corresponding to the current operating condition based on the current value of the operating condition definition parameter includes: The operating condition definition parameters are input into a pre-established electromechanical coupling correlation model, and the model outputs the expected reference range of the parameters to be diagnosed corresponding to the current operating condition. The electromechanical coupling correlation model encapsulates the dynamic correlation between at least one thermal state type operating condition definition, at least one dynamic state type operating condition definition parameter, and at least one parameter to be diagnosed for the turbine generator.
[0006] In some embodiments, the electromechanical coupling correlation model is implemented in the form of a two-dimensional lookup table, which is pre-calibrated based on multi-condition operating data of the turbine generator under healthy conditions; and / or, The thermal state condition definition parameter is the heater power, and the dynamic state parameter is the rotational speed of the turbine generator.
[0007] In some embodiments, before the real-time acquisition of the electromechanical operating parameters of the turbine generator, the method further includes: Determine whether the turbine generator is in a stable operating condition; Under stable operating conditions, the electromechanical operating parameters of the turbine generator are collected in real time.
[0008] In some embodiments, outputting fault diagnosis results for the turbine generator based on a combination of the one or more anomaly indication signals includes: The combination includes performing a logical AND operation on at least two of the aforementioned anomaly indication signals; Based on the result of the logical AND operation, output the fault diagnosis result for the turbine generator.
[0009] In some embodiments, the parameter to be diagnosed includes the actual rotational speed of the turbine generator, and the method further includes: Within a predefined time window, the difference between the actual speed of the turbine generator and the expected reference speed is sampled to form a time series; Determine whether the difference in the time series continuously exceeds a preset threshold; When the state is determined to be persistent within the time window, a corresponding abnormality indication signal is generated.
[0010] In some embodiments, the method further includes: Real-time monitoring of the actual rotational speed of the turbine generator; When the actual rotational speed exceeds the set overspeed protection threshold, an overspeed protection abnormal indication signal is generated; The overspeed protection triggering logic is independent of the current value of the operating condition definition parameter, dynamically determines the expected reference range of the parameter to be diagnosed corresponding to the current operating condition, and compares the actual measured value of the parameter to be diagnosed with the expected reference range, and generates one or more abnormal indication signals based on the comparison result.
[0011] In some embodiments, the overspeed protection flag has the highest priority among the one or more abnormal indication signals; And / or, The parameters to be diagnosed include at least one of motor current, motor power, and motor vibration.
[0012] In a second aspect, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements a fault diagnosis method for a turbine generator as described in any one of the first aspects.
[0013] Thirdly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the fault diagnosis method for the turbine generator described in the first aspect.
[0014] This application provides a fault diagnosis method for turbine generators, which, compared with the current method that relies solely on electrical signals and has a high misjudgment rate under complex operating conditions, has the following advantages: The electromechanical operating parameters of the turbine generator are acquired in real time. These parameters include at least one operating condition definition parameter and one or more parameters to be diagnosed. By fusing multi-dimensional electrical and mechanical parameters, a comprehensive and multi-dimensional perception of the turbine generator's operating status is achieved, laying a data foundation for fusion diagnosis. Based on the current value of the operating condition definition parameter, the expected reference range of the parameter to be diagnosed corresponding to the current operating condition is dynamically determined. The actual measured value of the parameter to be diagnosed is compared with the expected reference range, and one or more abnormal indication signals are generated based on the comparison results. This allows the diagnostic process to adapt to the real-time operating conditions of the equipment, overcoming the problem of poor adaptability of fixed thresholds in changing operating conditions. This significantly improves the accuracy and reliability of the diagnosis and reduces false alarms and missed alarms caused by changes in operating conditions. Subsequently, through the fusion and correlation analysis of multi-source information, the fault diagnosis results of the turbine generator are comprehensively output, significantly improving the accuracy of fault identification compared to traditional single-parameter analysis methods.
[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings.
[0017] Figure 1 This is a flowchart illustrating a fault diagnosis method for a turbine generator provided in this manual; Figure 2This is a schematic diagram of a computer-readable storage medium provided in this disclosure; Figure 3 This is a schematic diagram of the structure of a computing device provided in this disclosure. Detailed Implementation
[0018] This specification describes several technical solutions with different concepts. Each concept has one or more embodiments, and different concepts can be combined to form more embodiments. Those skilled in the art, after reading this specification, can combine different concepts to obtain new technical solutions, and these new technical solutions should also fall within the scope of this specification.
[0019] The technical solutions of these different concepts will be introduced in turn below. Some concepts may appear in multiple technical solutions of different concepts. For these concepts, this article will explain them when they first appear and will not repeat them in the following text.
[0020] As a key energy conversion device, the operating status of high-speed turbine generators directly affects system stability and equipment lifespan.
[0021] Currently, the main method for condition monitoring and fault diagnosis of such equipment is to use phase-synchronous sampling of the motor stator current and analyze specific excitation signals in the spectrum to detect rotor or gear faults. The advantages of this technology are that it is non-invasive and highly adaptable, but its disadvantage is that it relies solely on electrical signals and has a high false alarm rate in complex operating conditions.
[0022] To address the aforementioned technical problems, this specification provides a fault diagnosis method, device, and readable storage medium for a turbine generator.
[0023] The system aims to collect real-time electromechanical operating parameters of turbine generators, including at least electrical and mechanical performance parameters. This enhances the dimensionality and coverage of generator diagnostics, using the interconnectedness of electromechanical parameters during real-time operation as a criterion to improve diagnostic accuracy. Furthermore, by establishing dynamic rules between operating conditions and the parameters to be diagnosed, expected reference values are dynamically determined during the diagnostic process, making the diagnostic process applicable to scenarios with frequent changes in speed and load, thus improving the robustness of the diagnosis.
[0024] Figure 1 This is a flowchart illustrating a fault diagnosis method for a turbine generator provided in this specification. The fault diagnosis method for the turbine generator includes: Step 102: Real-time acquisition of electromechanical operating parameters of the turbine generator, including at least one operating condition definition parameter and one or more parameters to be diagnosed.
[0025] In this embodiment, the fault diagnosis method is applied to the field of industrial control and equipment condition monitoring. The equipment can be, but is not limited to, high-value, high-speed rotating machinery such as turbine generators.
[0026] The following uses a turbine generator (also referred to as a generator, turbine generator or device in the following embodiments) as an example to illustrate the fault diagnosis method of a turbine generator.
[0027] In this embodiment, the electromechanical operating parameters of the turbine generator refer to the collective term that includes at least electrical performance parameters and mechanical performance parameters.
[0028] In this embodiment, one or more diagnostic parameters refer to parameters that are monitored and used to determine whether the device has malfunctioned or failed. Their actual measured values are compared with an expected reference value / expected reference range to generate an anomaly indication signal. For example, the diagnostic parameters include at least electrical performance parameters and mechanical performance parameters.
[0029] Electrical performance parameters include, but are not limited to, electrical signals such as current, voltage, and power. Mechanical performance parameters include, but are not limited to, mechanical signals such as motor vibration and speed.
[0030] In this embodiment, the parameters to be diagnosed include at least one of motor current, motor power, and motor vibration.
[0031] By using hardware such as sensors, data acquisition cards, and controllers (such as PLCs and DSPs), the above parameter data are continuously or periodically acquired at a sufficiently high frequency. By integrating the electrical and mechanical performance parameters of the turbine generator, real-time joint judgment is achieved, which improves the stability of the diagnostic mechanism when facing load fluctuations, speed changes, and temperature disturbances, and also provides accurate basic data for subsequent diagnosis.
[0032] In this embodiment, at least one operating condition definition parameter is used to describe the current operating state, load, or external conditions of the turbine generator. These parameters are the basis for determining the operating conditions of the equipment and also serve as inputs or bases for dynamically determining the expected reference values of the parameters to be diagnosed.
[0033] For example, operating condition definition parameters may include, but are not limited to, motor speed, output power, heater power (reflecting heat load), ambient temperature, etc.
[0034] During startup, the turbine generator experiences a surge in current and a rapid increase in speed, which is normal and not a sign of a fault. If the diagnostic logic in steps 104 to 108 below is active during this time, frequent alarms will inevitably occur. Therefore, to avoid the absence of alarms during transient processes, the diagnostic logic is disabled or controlled to remain unresponsive in these special scenarios. Measurements and judgments are then performed after the turbine generator reaches a steady state to detect any faults that manifest abnormally even in a steady state.
[0035] In some embodiments, before the real-time acquisition of the electromechanical operating parameters of the turbine generator, the method further includes: Determine whether the turbine generator is in a stable operating condition; Under stable operating conditions, the electromechanical operating parameters of the turbine generator are collected in real time.
[0036] The system determines whether it is in a diagnosable steady state by monitoring the rate of change of rotational speed (i.e., the dynamic behavior of the system). This ensures that the data used by the subsequent diagnostic logic is collected under a steady state that is diagnostically meaningful, thereby guaranteeing the reliability of the diagnostic basis.
[0037] Specifically, the speed change rate of the turbine generator is obtained. When the speed change rate is within a stable range and the error change rate is small, the turbine generator is determined to be in a stable operating condition. The diagnostic logic in steps 104 to 108 is then activated to effectively avoid misjudgments caused by short-term disturbances.
[0038] In this embodiment, the scenario of short-term disturbance can be: Start-up process: The turbine generator accelerates from a standstill to its rated speed, and the speed, current, and power rise sharply from zero, while the vibration characteristics also change.
[0039] Shutdown process: The opposite of startup, all parameters drop sharply.
[0040] Complex and large-scale switching: When the power grid dispatch requires the generator to rapidly increase / decrease the load, the control system will act quickly, resulting in large fluctuations and adjustments in parameters such as speed and power.
[0041] At the moment of grid connection: When the generator is synchronously connected to the grid, there will be a brief adjustment process of electrical and mechanical parameters.
[0042] In this embodiment, the aforementioned precision diagnostic program will only be activated when the system determines that the generator is operating in a relatively stable state (e.g., with gradual speed changes). If the generator is in a "turbulent period" of starting, stopping, or undergoing drastic adjustments, this switch will be temporarily turned off to prevent temporary, drastic fluctuations from triggering a large number of meaningless alarms, greatly improving the availability and reliability of the entire diagnostic system.
[0043] Step 104: Based on the current value of the defined operating condition parameter, dynamically determine the expected reference range of the parameter to be diagnosed corresponding to the current operating condition.
[0044] The actual operating conditions of a turbine generator are dynamic, with frequent fluctuations in load, speed, and ambient temperature. Under different operating conditions, the normal baseline values of parameters such as current, power, and vibration will change significantly. Using fixed or finitely preset reference values has fundamental limitations.
[0045] Based on this, this application uses operating condition definition parameters (such as speed, power, etc.) to determine the current operating mode or load condition of the equipment. According to this determination, a value range considered normal under the current conditions is dynamically calculated for the parameter to be diagnosed (such as vibration, current, etc.) through pre-set rules. It can be a single value or a range with upper and lower limits.
[0046] In some embodiments, dynamically determining the expected reference range of the parameter to be diagnosed corresponding to the current operating condition based on the current value of the operating condition definition parameter includes: The operating condition definition parameters are input into a pre-established electromechanical coupling correlation model, and the model outputs the expected reference range of the parameters to be diagnosed corresponding to the current operating condition. The electromechanical coupling correlation model encapsulates the dynamic correlation between at least one thermal state type operating condition definition, at least one dynamic state type operating condition definition parameter, and at least one parameter to be diagnosed for the turbine generator.
[0047] The essence of turbine generator failure lies in abnormal energy conversion. Dynamic parameters directly reflect the mechanical energy conversion process, while thermal state parameters capture losses and efficiency during energy conversion. These two types of parameters together constitute a complete energy flow view. In other words, the actual operating state of a turbine generator is the result of the combined and coupled effects of its thermodynamic and dynamic processes. For example, bearing wear increases vibration (dynamics) and temperature due to friction (thermal state). Single-dimensional monitoring may not be able to comprehensively and accurately describe the equipment's operating condition, thus failing to provide a precise diagnosis. Therefore, an electromechanical coupling correlation model is established to establish the dynamic relationship between at least one thermal state-type operating condition definition, at least one dynamic state-type operating condition definition parameter, and at least one parameter to be diagnosed. This model can output the expected reference range of the parameter to be diagnosed based on the input thermal and dynamic state parameters.
[0048] In this embodiment, the thermal state condition definition parameters may include, but are not limited to, heater power, bearing temperature / lubricating oil temperature, stator / rotor winding temperature, cooling medium temperature / flow rate, ambient temperature, etc. The dynamic state parameters may include, but are not limited to, motor speed, load torque, output power, etc.
[0049] In this embodiment, the pre-established electromechanical coupling correlation model can be constructed using experimental data, physical modeling, or machine learning methods.
[0050] In some embodiments, the electromechanical coupling association model is implemented in the form of a two-dimensional lookup table, which is pre-calibrated based on the multi-condition operating data of the turbine generator under healthy conditions.
[0051] In this embodiment, the function of the two-dimensional lookup table is to dynamically output a normal reference value or expected reference range that should exist under the current real-time operating conditions. This reference value is pre-filled based on a large amount of experimental and theoretical data, so that the judgment criteria are no longer fixed, but intelligently change with the operating conditions.
[0052] In some embodiments, the thermal state condition definition parameter is the heater power, and the dynamic state parameter is the rotational speed of the turbine generator.
[0053] A dynamic correlation mechanism between heat load (such as heater power) and rotational speed is established through a 2-D Lookup Table, which records the normal state of the equipment under various combinations of rotational speed and heating power.
[0054] Therefore, by using heater power and motor speed as input variables, a 2-D Lookup Table is constructed to output reference values based on set breakpoints and interpolated data. These values reflect the correlation between thermal load and motor speed, serving as an auxiliary diagnostic criterion. This solves the problems of poor adaptability and high false alarm rate of traditional methods under varying operating conditions.
[0055] Step 106: Compare the actual measured value of the parameter to be diagnosed with the expected reference range, and generate one or more abnormal indication signals based on the comparison results.
[0056] The actual values of the parameters collected in real time are compared with the expected reference range determined by the dynamic working conditions, and a binary abnormality indication signal is generated according to the preset and fixed comparison rules. One or more abnormality indication signals provide a basis for subsequent fusion diagnosis.
[0057] In this embodiment, its execution is achieved through the comparison logic unit of the controller: if the actual value exceeds the reference range, the exception flag is immediately set (e.g., set to logic 1); if it is within the range, the flag bit is cleared (logic 0).
[0058] In this embodiment, multiple operating parameters such as motor current, motor power, motor vibration, heater power, and motor speed are analyzed collaboratively to extract characteristic abnormal indicators and enhance the accuracy of fault identification.
[0059] For example, when the absolute value of the change in motor current is greater than 2A (expected reference range), an abnormal current judgment signal is output.
[0060] For example, when the motor power is greater than 1000W, an abnormal power output signal is generated.
[0061] For example, when the motor amplitude is greater than 140μm, an abnormal vibration signal is output.
[0062] In this embodiment, the form of the abnormal indication signal may be, but is not limited to, a Boolean value (binary signal), an integer value or an enumeration type, a string message, etc., and is selected according to actual usage requirements. No specific limitation is made here.
[0063] For example, it generates corresponding error flags such as "Motor Current Error Flag" and "Motor Power Error Flag".
[0064] In some embodiments, when comparing the actual values of parameters acquired in real time with the expected reference range dynamically determined by the operating conditions, if an out-of-range condition is found, a status persistence judgment is initiated. Only after the abnormal state persists for more than a preset time window (e.g., 0.5 seconds) is a standardized abnormal indication signal finally generated, effectively distinguishing between real faults and transient interference, and significantly improving diagnostic reliability. This execution process is achieved through the coordinated use of comparators, timers, and logic gates embedded in the controller.
[0065] In some embodiments, the parameter to be diagnosed includes the actual rotational speed of the turbine generator, and the method further includes: Within a predefined time window, the difference between the actual speed of the turbine generator and the expected reference speed is sampled to form a time series; Determine whether the difference in the time series continuously exceeds a preset threshold; When the state is determined to be persistent within the time window, a corresponding abnormality indication signal is generated.
[0066] The speed of the turbine generator is monitored, and the deviation between the actual speed and the expected reference speed is determined to identify any abnormalities in this parameter. A dynamic threshold mechanism is employed during the determination process to adapt to scenarios with frequent changes in speed and load, thereby improving diagnostic accuracy.
[0067] Specifically, a dynamic threshold mechanism is introduced: such as an error mutation threshold of 150 rpm and a change duration of 0.5 s.
[0068] First, calculate the difference between the expected reference speed and the actual speed, and take its absolute value.
[0069] Next, the absolute value of the difference is compared with the threshold (150 rpm), and it is determined whether the error continues to exceed the preset threshold (0.5 seconds).
[0070] If both of the above conditions are met, the "Speed Error Flag" error indication signal will be output through the "Bitwise AND" logic gate.
[0071] In this embodiment, a dynamic diagnostic mechanism based on rotational speed error and its duration is established to identify rotor operation anomalies (such as imbalance, control lag, etc.) in real time, enabling rapid detection of abnormal states and ensuring the system's real-time response capability. Furthermore, by introducing judgment logic based on error duration and change trend, transient interference and false triggering are effectively filtered out, ensuring the stability and reliability of the system in complex environments.
[0072] The most critical factor in ensuring the safe operation of a turbine generator is the rotor speed. Therefore, during the diagnostic process, it is essential to prevent mechanical failures or even disintegration caused by overspeed.
[0073] In some embodiments, the method further includes: Real-time monitoring of the actual rotational speed of the turbine generator; When the actual rotational speed exceeds the set overspeed protection threshold, an overspeed protection abnormal indication signal is generated; The overspeed protection triggering logic is independent of the current value of the operating condition definition parameter, dynamically determines the expected reference range of the parameter to be diagnosed corresponding to the current operating condition, and compares the actual measured value of the parameter to be diagnosed with the expected reference range, and generates one or more abnormal indication signals based on the comparison result.
[0074] In this embodiment, overspeed protection is an independent safety mechanism that does not depend on the main diagnostic logic.
[0075] In this embodiment, the overspeed protection flag has the highest priority among the one or more abnormal indication signals.
[0076] This means that overspeed protection can be triggered independently regardless of whether the main diagnostic system is running or malfunctioning. This ensures that even when the main diagnostic system cannot correctly diagnose due to complex logic failures, software bugs, or sensor malfunctions, there is still a reliable dedicated channel to protect the equipment.
[0077] In terms of execution, it monitors the rotational speed in real time and compares it directly with the set overspeed protection threshold. Once the limit is exceeded, a signal is triggered immediately without the need for dynamic model or time verification. This avoids the time delay caused by complex algorithm calculations and data fusion, and achieves the fastest safety response.
[0078] For example, if the overspeed protection threshold is set to 35,000 rpm, when the actual speed exceeds 35,000 rpm, a "MotorOverspeed Error Flag" is output to identify high-speed overload conditions. This logic can be embedded in the control system or run as an independent diagnostic module, exhibiting high real-time performance and robustness.
[0079] In this embodiment, by introducing an overspeed protection mechanism, an overspeed protection flag is triggered when the actual speed of the motor exceeds the set upper limit, providing a safety protection mechanism for high-speed operating equipment.
[0080] Step 108: Based on the combination of the one or more abnormal indication signals, output the fault diagnosis result for the turbine generator.
[0081] Traditional diagnostic methods cannot distinguish between transient disturbances and genuine faults, and will trigger an alarm for any transient abnormality in a single parameter. Furthermore, an abnormality may be caused by multiple factors; for example, increased vibration could be due to rotor imbalance (mechanical fault) or a winding short circuit (electrical fault). A single vibration signal is insufficient to determine the root cause.
[0082] Based on this, a joint judgment mechanism—that is, by designing different signal combination rules—can tolerate normal fluctuations in individual parameters, preventing alerts due to transient disturbances unless the anomaly is accompanied by other anomalies. This effectively filters out most transient interferences, such as current anomalies accompanied by power anomalies. Furthermore, it enhances the robustness of the diagnostic program under complex operating conditions. More importantly, by combining and analyzing weak but persistently correlated early abnormal signals, the system can identify potential fault modes in the early stages of a fault, before it deteriorates significantly. This is something that single-parameter diagnostics cannot achieve.
[0083] In this embodiment, the combination rules for one or more abnormal indication signals may be, but are not limited to, logical AND structure combination, logical OR structure combination, weighted or voting combination, etc.
[0084] Among these, the logical and structural combination diagnostic approach is used to confirm a fault that requires the simultaneous presence of multiple pieces of evidence. The logical or structural combination diagnostic approach is used to diagnose a fault that may be triggered by one of several different causes. The weighted or voting combination diagnostic approach is used for more complex systems where different pieces of evidence contribute differently to the final diagnostic result. These diagnostic approaches should be selected appropriately based on actual needs, such as requirements for real-time performance, accuracy, and equipment performance; no specific limitations are imposed here.
[0085] In some embodiments, outputting fault diagnosis results for the turbine generator based on a combination of the one or more anomaly indication signals includes: The combination includes performing a logical AND operation on at least two of the aforementioned anomaly indication signals; Based on the result of the logical AND operation, output the fault diagnosis result for the turbine generator.
[0086] The above criteria are combined through "Bitwise AND" logic to form a more robust multi-signal joint diagnostic mechanism, which can more accurately locate the root cause of the fault and generate corresponding abnormal signs.
[0087] For example, if the anomaly indication signal is represented by a Boolean signal, such as True / 1 or False / 0, then an example would be as follows: Scenario A: Speed Error Flag and Vibration Error Flag are both true.
[0088] Diagnostic conclusion: It is highly likely to be a mechanical failure, such as rotor imbalance or bearing damage. The simultaneous occurrence of uncontrolled speed and severe vibration strongly points to a problem with the rotating mechanical components themselves.
[0089] Scenario B: Speed Error Flag is true, and Motor Current Error Flag is true, but Vibration Error Flag is false.
[0090] Diagnostic conclusion: It is more likely an electrical or load fault. For example, a sudden change in the electromagnetic torque inside the motor (causing abnormal current) prevents the rotor from keeping up with the predetermined speed, but the mechanical body does not produce abnormal vibrations.
[0091] Scenario C: Only the Speed Error Flag is true, while all other flags are normal.
[0092] Diagnostic conclusion: It may be a problem with the speed control system itself (such as sensor drift or poor controller parameters), or a very minor, initial mechanical problem.
[0093] This design enables multi-criteria linkage: multiple fault indicators are judged in parallel through logical combination, and a fault flag is output only when multiple abnormal conditions are met. This greatly improves the accuracy and robustness of diagnosis and avoids misjudgments caused by single-parameter fluctuations. Furthermore, it can distinguish fault types, guiding maintenance personnel to quickly locate problems.
[0094] In some embodiments, overspeed protection is independent and prioritized, ensuring device safety.
[0095] In this embodiment, the above-mentioned abnormal indication signals are combined and output as fault diagnosis results for the turbine generator according to the set judgment rules.
[0096] The fault diagnosis result can be a structured set of fault flags: Speed Error Flag: responsible for diagnosing problems at the "control and follow" level. Motor Current / Power / Vibration Error Flag: responsible for diagnosing performance problems of specific subsystems (electrical and mechanical). Motor Overspeed Error Flag: responsible for the highest level of safety protection.
[0097] It can also be a diagnostic conclusion or a diagnostic report.
[0098] In this embodiment, multiple operating parameters such as motor current, motor power, motor vibration, heater power, and motor speed are analyzed collaboratively to extract characteristic abnormal indicators for fusion judgment, thereby enhancing the accuracy of fault identification.
[0099] This application provides a fault diagnosis method for turbine generators, which, compared with the current method that relies solely on electrical signals and has a high misjudgment rate under complex operating conditions, has the following advantages: On one hand, the electromechanical operating parameters of the turbine generator are collected in real time. These parameters include at least one operating condition definition parameter and one or more parameters to be diagnosed. By fusing multi-dimensional electrical and mechanical parameters, a comprehensive and multi-dimensional perception of the turbine generator's operating status is achieved, laying a data foundation for fusion diagnosis. Based on the current value of the operating condition definition parameter, the expected reference range of the parameter to be diagnosed corresponding to the current operating condition is dynamically determined. The actual measured value of the parameter to be diagnosed is compared with the expected reference range, and one or more abnormal indication signals are generated based on the comparison results. This allows the diagnostic process to adapt to the real-time operating conditions of the equipment, overcoming the problem of poor adaptability of fixed thresholds in changing operating conditions, thereby significantly improving the accuracy and reliability of the diagnosis and reducing false alarms and missed alarms caused by changes in operating conditions. Subsequently, through the fusion and correlation analysis of multi-source information, the fault diagnosis results of the turbine generator are comprehensively output, significantly improving the accuracy of fault identification compared to traditional single-parameter analysis methods.
[0100] On the other hand, the fault diagnosis algorithm has a simple structure and modular logic, making it suitable for modular structures in embedded control environments (such as microcontrollers (MCUs), DSPs, programmable logic controllers (PLCs), and other industrial platforms / controllers), enabling local fault diagnosis or remote monitoring and linkage control.
[0101] This application provides a fault diagnosis system for a turbine generator, the system including a parameter acquisition and preprocessing module and a multi-parameter joint diagnosis module.
[0102] The parameter acquisition and preprocessing module is used to acquire the electromechanical operating parameters of the turbine generator in real time. The parameters include at least one operating condition definition parameter and one or more parameters to be diagnosed.
[0103] The multi-parameter joint diagnostic module also includes a two-dimensional lookup table submodule, a current judgment submodule, a power judgment submodule, and a vibration judgment submodule.
[0104] The system is used to dynamically determine the expected reference range of the parameter to be diagnosed corresponding to the current operating condition based on the current value of the parameter defined by the operating condition; compare the actual measured value of the parameter to be diagnosed with the expected reference range, and generate one or more abnormal indication signals based on the comparison result; and output the fault diagnosis result of the turbine generator based on the combination of the one or more abnormal indication signals.
[0105] The system further includes a dynamic speed error judgment module. This module samples the difference between the actual speed of the turbine generator and the expected reference speed within a predefined time window to form a time series; determines whether the difference in the time series continuously exceeds a preset threshold; and generates a corresponding abnormal indication signal when the exceedance is determined to be continuous within the time window.
[0106] The system further includes a diagnostic enable module, used to determine whether the turbine generator is in a stable operating condition; if it is determined to be in a stable operating condition, the module executes the real-time acquisition of the turbine generator's electromechanical operating parameters.
[0107] The system further includes: an overspeed detection module, used to monitor the actual speed of the turbine generator in real time; when the actual speed exceeds a set overspeed protection threshold, generating an abnormal indication signal for overspeed protection; wherein the triggering logic of the overspeed protection is independent of the current value of the operating condition definition parameter, dynamically determining the expected reference range of the parameter to be diagnosed corresponding to the current operating condition; and a diagnostic logic that compares the actual measured value of the parameter to be diagnosed with the expected reference range, and generates one or more abnormal indication signals based on the comparison result.
[0108] The modular architecture of the system allows it to be flexibly integrated into embedded platforms (such as MCU, DSP, PLC) or host computer systems, supports local fault diagnosis and remote monitoring, and has good engineering adaptability and scalability.
[0109] The modules and sub-modules in the system are used to implement the fault diagnosis method for turbine generators as described above. Further details will not be elaborated here.
[0110] Figure 2 This is a schematic diagram of a computer-readable storage medium 140 provided in this disclosure, on which a computer program is stored, which, when executed by a processor, implements the method of any embodiment of this disclosure.
[0111] This disclosure also provides a computing device, including a memory and a processor; the memory is used to store computer instructions that can be executed on the processor, and the processor is used to implement the method of any embodiment of this disclosure when executing the computer instructions.
[0112] Figure 3 This is a schematic diagram of the structure of a computing device provided in this disclosure, such as... Figure 3 As shown, the computing device 15 may include, but is not limited to: a processor 151, a memory 152, and a bus 153 connecting different system components (including the memory 152 and the processor 151).
[0113] The memory 152 stores computer instructions that can be executed by the processor 151, enabling the processor 151 to perform the fault diagnosis method for the turbine generator according to any embodiment of this disclosure. The memory 152 may include a random access memory (RAM) 1521, a cache memory 1522, and / or a read-only memory (ROM) 1523. The memory 152 may also include a program tool 1525 having a set of program modules 1524, including but not limited to: an operating system, one or more application programs, other program modules, and program data. One or more combinations of these program modules may include an implementation of a network environment.
[0114] Bus 153 may include, for example, a data bus, an address bus, and a control bus. The computing device 15 can also communicate with external devices 155 via I / O interface 154, such as a keyboard or a Bluetooth device. The computing device 15 can also communicate with one or more networks via network adapter 156, such as a local area network (LAN), a wide area network (WAN), or a public network. As shown in the figure, the network adapter 156 can also communicate with other modules of the computing device 15 via bus 153.
[0115] Furthermore, although the operations of the methods disclosed herein are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.
[0116] While the spirit and principles of this disclosure have been described with reference to several specific embodiments, it should be understood that this disclosure is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for convenience of expression. This disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims
1. A method of diagnosing a fault of a turbo-generator, characterized by, The method comprises: Real-time acquisition of electromechanical operating parameters of the turbine generator, the parameters comprising at least one operating condition defining parameter and one or more parameters to be diagnosed; Based on the current value of the operating condition defining parameter, dynamically determining the expected reference range of the parameter to be diagnosed corresponding to the current operating condition; Comparing the actual measured value of the parameter to be diagnosed with the expected reference range, and generating one or more abnormal indication signals based on the comparison result; Based on the combination of the one or more abnormal indication signals, outputting the fault diagnosis result of the turbine generator.
2. The method of diagnosing a failure of a turbo-generator as claimed in claim 1, wherein The method comprises: The method comprises: The method comprises:
3. The method of diagnosing a fault of a turbo-generator as claimed in claim 2, wherein The method comprises: The method comprises:
4. The method of diagnosing a failure of a turbo-generator according to claim 1, wherein The method comprises: The method comprises: The method comprises:
5. The method of diagnosing a fault of a turbo-generator as claimed in claim 1, wherein The method comprises: The method comprises: The method comprises:
6. The method of diagnosing a fault of a turbine generator according to Claim 1, wherein The method comprises: The method comprises: The method comprises: The method comprises:
7. The method of diagnosing a fault of a turbo-generator as claimed in claim 6, wherein The method comprises: The method comprises: The method comprises: The method comprises:
8. The method of diagnosing a failure of a turbo-generator according to claim 7, wherein The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: and / or, The parameter to be diagnosed includes at least one of motor current, motor power and motor vibration. 9.An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, a fault diagnosis method of a turbogenerator according to any one of claims 1 to 8 is implemented.
10. A computer-readable storage medium, characterized in that, A computer readable storage medium stores a computer program, and when the computer program is executed, a fault diagnosis method of a turbogenerator according to any one of claims 1 to 8 is implemented.