Comprehensive method and system for health condition evaluation and fault early warning of turbine generator

Abstract

The present invention relates to the technical field of power system equipment and control. The method of the present invention comprises: installing sensors to acquire data for online real-time monitoring, and constructing a comprehensive condition online monitoring model for comprehensive data analysis; comprehensively evaluating the health condition of a generator on the basis of a comprehensive analysis result, and identifying fault causes; and constructing a generator comprehensive data intelligent monitoring and dynamic early warning model to perform insulation degradation trend analysis and prediction on the generator. In the present invention, by comprehensively monitoring the condition of a turbine generator, various key indicators of the generator are captured in real time, and trends and patterns underlying the data are revealed, providing technical support for accurately evaluating the health condition of the generator; and continuous monitoring for the insulation condition of the generator allows for proactive identification of potential risks, thereby providing decision-making support for preventive maintenance, helping operators take measures promptly, preventing faults, improving the reliability and safety of the generator.

Description

A steam turbine generator health condition evaluation and fault early warning comprehensive method and system TECHNICAL FIELD

[0001] The present application belongs to the field of power system equipment and control technology, and particularly relates to a steam turbine generator health condition evaluation and fault early warning comprehensive method and system. BACKGROUND

[0002] The generator is one of the most important main devices in the power system, and its importance is self-evident. Due to the design and manufacturing quality of the generator and many other reasons, accidents and failures occur from time to time, and the safe operation of the generator is related to the stable and reliable operation of the power plant and even the entire power grid. The maintenance of the generator cannot be arbitrarily interrupted, so it is necessary to make full prediction before the accident occurs - solve the fault before the accident occurs; the overall structure of the generator is complex, mainly including stator and rotor two components, and the cause of most of the faults and accidents of the generator is due to insulation aging and insulation failure, therefore, if the overall insulation condition of the generator can be accurately known before the accident, the operation condition thereof is also mastered.

[0003] Due to the lack of effective monitoring technology for the health state insulation fault of the generator, the conventional maintenance cycle is power-off maintenance, and there are disadvantages of "small repair, no repair", which wastes a lot of manpower and financial resources. With the exploration and research of the generator health state comprehensive monitoring platform in-depth research project, the technical foundation of the equipment state maintenance in the power generation industry is greatly strengthened, which can effectively guide the generator rotor maintenance strategy, avoid more than 50% of the "no repair" phenomenon, save more than 50% of the maintenance cost; compared with the traditional test, the maintenance is guided according to the online monitoring result, the maintenance cycle is shortened, and the operation time of the generator set is improved.

[0004] There is no such technology application at home and abroad for the health state comprehensive monitoring and diagnosis of the generator, therefore, by researching the generator health comprehensive state monitoring platform, accurate judgment basis is provided, equipment hidden dangers can be found in advance, equipment maintenance time is effectively reduced, the online monitoring system has a pre-judgment function, greatly relieves the manpower and material resources investment of production management and maintenance, and has more significant economic benefits. Through the present application, the equipment perception ability, defect discovery ability, state control ability, active early warning ability and emergency disposal ability of the operation and maintenance personnel are comprehensively improved, and the standardization, lean and intelligent level of operation and maintenance is continuously improved.

[0005] SUMMARY

[0006] In view of the above existing problems, the present application is proposed. The present application establishes a steam turbine generator fault diagnosis and health condition evaluation system. On the basis of in-depth research and analysis of the stator winding insulation, rotor inter-turn short circuit, end vibration and bearing failure mechanism, an online monitoring and comprehensive diagnosis platform for generator insulation state is established. Combined with the Internet of Things information technology and the cloud data platform, online monitoring of the overall health condition of the generator is realized, and comprehensive evaluation is made. The fault waveform is dynamically identified, and the data is comprehensively analyzed. The dynamic early warning and diagnosis of the stator and rotor insulation faults of the generator are realized.

[0007] To solve the above technical problems, a steam turbine generator health condition evaluation and fault early warning comprehensive method is proposed, comprising,

[0008] The sensor is installed to collect data for online real-time detection, and a comprehensive state online monitoring model is constructed for comprehensive data analysis. According to the comprehensive analysis result, the health condition of the generator is comprehensively evaluated, and the fault reason is identified. A generator comprehensive data intelligent monitoring and dynamic early warning model is constructed to analyze and predict the insulation deterioration trend of the generator.

[0009] As a preferred scheme of the steam turbine generator health condition evaluation and fault early warning comprehensive method, the collected data includes electrical parameters, mechanical parameters and environmental parameters.

[0010] The electrical parameters include voltage and current, insulation resistance and partial discharge data.

[0011] The mechanical parameters include speed, displacement, expansion and vibration data.

[0012] The environmental parameters include humidity, temperature, dust and particles.

[0013] The installed sensor includes a 80pF coupling capacitor installed at the high-voltage inlet end of the generator to monitor the partial discharge data. The partial discharge data includes discharge amount, discharge frequency, discharge phase and discharge spectrum. A magnetic flux probe is used to monitor the rotor magnetic flux data. A vibration sensor is installed at the stator end to collect end vibration data. A shaft voltage and current sensor is installed on the bearing to collect shaft voltage and current information for online real-time monitoring. After data collection, noise filtering and normalization are performed to make the data reach the same scale.

[0014] As a preferred scheme of the steam turbine generator health condition evaluation and fault early warning comprehensive method, the comprehensive state online monitoring model includes data analysis based on the collected data, fusion of partial discharge data, rotor magnetic flux data, end vibration data and shaft voltage and current information collected by the sensor, and time series analysis of the partial discharge data.

[0015] where g(y) is the local discharge data analysis function, K represents the number of local discharge data samples, y k represents the kth sample of local discharge data y, represents the average value of the kth sample of local discharge data, represents the standard deviation of the kth sample of local discharge data, y n is the amplitude of the local discharge signal.

[0016] Frequency domain analysis is performed on the rotor flux data:

[0017] where h(z) represents the rotor flux data analysis function, ζ represents the normalization constant, z m represents the time series data of rotor flux data z, μ z represents the average value of rotor flux data, σ z represents the standard deviation of rotor flux data, ω m represents the angular frequency of rotor flux data, t is the running time.

[0018] Time domain and frequency domain analysis are performed on the end vibration data and shaft voltage and current information to construct a comprehensive state online monitoring model:

[0019] where i(w) represents the analysis function of end vibration data and shaft voltage and current information, E represents the number of data points, w j represents the time series data of end vibration data and shaft voltage and current information, μ w represents the average value of end vibration data and shaft voltage and current information, σ w represents the standard deviation of end vibration data and shaft voltage and current information, λ j represents the filtering parameter of end vibration data and shaft voltage and current information.

[0020] The results of local discharge data analysis, rotor flux data analysis, and end vibration data analysis are integrated:

[0021] where f(g, h, i) represents the output result of the comprehensive state online monitoring model, x n represents the collected data of the nth sensor, μ y,z,w represents the average value of the data, σ y,z,w represents the standard deviation of the data.

[0022] As a preferred scheme of the health condition evaluation and fault early warning method of the steam turbine generator, the comprehensive data analysis includes output results according to f(g, h, i), when 0≤f(g, h, i)<20, it indicates that the collected data is in a normal state within the running time, if there is an abnormal data point at this time, the system considers that it does not affect the operation and allows to be ignored, the steam turbine generator remains the current operation mode unchanged, and the data collection and data analysis are maintained.

[0023] When 20≤f(g, h, i)<50, it indicates that the collected abnormal data points exceed the number x of abnormal data points set according to the current environment abnormal , the health of the steam turbine generator is immediately evaluated, and whether the performance of the generator is decreased is judged according to the evaluation result, if the performance is not decreased, whether the abnormal data causes insulation deterioration is judged according to the running time point, if the insulation is not deteriorated, the fault light flashes at the abnormal data point, quickly locates and informs the staff to repair, if the performance is decreased, the abnormal operation mode is switched, the power consumption and loss of the steam turbine generator are reduced, and the fault prediction is performed.

[0024] When f(g, h, i)≥50, it indicates that the number of normal data points collected is less than 3, and it is also considered that the steam turbine generator has existed a fault before the collected running time, the health of the steam turbine generator is evaluated, the damage degree and insulation deterioration degree of the steam turbine generator are judged and dynamic early warning is performed, and the emergency operation mode is switched, the work of the steam turbine generator is suspended, and the comprehensive maintenance preparation is made.

[0025] As a preferred scheme of the health condition evaluation and fault early warning method of the steam turbine generator, the comprehensive evaluation of the health state of the generator includes normal health evaluation H0 of the steam turbine generator according to partial discharge data, rotor flux data, end vibration data, shaft voltage and shaft current information, and H0 is expressed as:

[0026] When H0=1, it indicates that the generator is in the best health state, and when H0=0, it indicates that the generator is in a fault state, wherein t0 and t f respectively represent the starting and ending time points of the evaluation within the running time, n is the number of sensors, W i is the weight of the i-th sensor data, Y i is the complex information filtering function of the i-th sensor, y i (t) is the partial discharge data collected by the i-th sensor at time t, ε0 and ε f respectively represent the starting and ending positions of the rotor flux data measurement, H is the normalization function of the rotor flux data, z R (ε) is the rotor flux data measured at position ε, ω0 and ωf respectively represent the start and end angular frequency of the end vibration data measurement, U is the integral function of the end vibration data, w(x, ω) is the vibration data at position I and angular frequency ω, V0 and V f respectively represent the start and end voltage of the shaft voltage shaft current data measurement, F is the exponential function of the shaft voltage shaft current data, A(I) is the shaft current information measured at voltage I;

[0027] When H0=0, it is judged that the performance H s of the generator is falling:

[0028] wherein P(x) represents the performance index of the generator, S(x) represents the data collected by the sensor, n i represents the collected data of the nth sensor, β represents the normalization coefficient of the sensor data, γ represents the coefficient of the logarithmic function, η is the attenuation of the performance index of the generator with time, δ i and δ j represent the time attenuation coefficient of the measurement characteristics of the sensor i, p i and p j are parameters of the signal strength of the sensors i and j, which are adjusted according to the importance of the sensors or the reliability of the signals;

[0029] When H s =1, it indicates that the performance of the steam turbine generator is not falling, when 0≤H s <1, it indicates that the performance of the steam turbine generator is falling, and when H s is smaller, it indicates that the performance is falling more seriously.

[0030] When the number of normal data points is less than 3, the damage degree H2 of the generator is evaluated as: H2=H s ·(1-e-κ(3-G(x)))

[0031] When the value of H2 is smaller, it indicates that the damage degree is higher, wherein κ represents the coefficient of the normal data points, and G(x) represents the number of normal data points.

[0032] As a preferred scheme of the steam turbine generator health condition evaluation and fault early warning comprehensive method, wherein: the identification of the fault reason comprises judging according to the comprehensive health evaluation of the steam turbine generator, when the performance H s of the steam turbine generator is falling and the damage degree H2 is increasing, the fault reason is judged according to the results of H2 and H s .

[0033] When the performance degradation is less than 0.8 and the damage degree rises to 0.3, it is judged that the partial discharge data is faulty, and is accompanied by output power reduction, efficiency reduction, and damage degree performance is insulation material performance degradation, corona sound or spark sound abnormal sound, immediately stop running and carry out partial discharge detection, check the condition of the insulation system, if the partial discharge source is found, positioning and repairing.

[0034] When the performance degradation is less than 0.75 and the damage degree rises to 0.4, it is judged that the rotor problem is faulty, and the performance degradation is manifested as speed fluctuation drop, and the damage degree is manifested as abnormal rise of rotor temperature, increase of vibration or increase of noise, reduce the load and arrange professional personnel to check the rotor, carry out vibration analysis to determine whether the rotor is unbalanced or has structural problems, if the rotor winding problem, repair to ensure the normal operation of the rotor cooling system and avoid overheating.

[0035] When the performance degradation is less than 0.6 and the damage degree rises to 0.5, it is judged that the end vibration is faulty, and the performance degradation is manifested as unstable operation of the motor, and the damage degree is manifested as rise of bearing temperature, and the lubricating oil analysis shows that the metal particles increase, reduce the running speed and check the bearing and mechanical structure, carry out vibration measurement to determine the cause and degree of vibration, check whether the bearing is worn or damaged, rebalance the rotor, and check the centering condition.

[0036] When the performance degradation is less than 0.7 and the damage degree rises to 0.2, it is judged that the shaft voltage and shaft current information is faulty, and the performance degradation is manifested as abnormal temperature rise of the motor, and the damage degree is manifested as electric corrosion of the bearing surface, and the lubricating oil analysis shows that the conductivity increases, check the measurement value of the shaft voltage and the shaft current, determine the cause of the abnormal shaft voltage and shaft current, check the shaft grounding device, and reduce the influence of the shaft voltage and the shaft current.

[0037] As a preferred scheme of the health condition evaluation and fault early warning comprehensive method of the steam turbine generator, wherein: the intelligent monitoring and dynamic early warning model of the generator comprehensive data includes analyzing and predicting the insulation state of the stator and rotor of the generator when the health evaluation appears problems and the fault cause is identified:

[0038] When P(I s ,I r ,t) is greater than or equal to the first threshold value, a high-risk prompt of insulation degradation is made, and the degradation degree shows a rapid rising trend, indicating that the fault cause accelerates the insulation degradation, the intelligent monitoring carries out emergency light flashing and urgent sound early warning, stops the work of the steam turbine generator, carries out initial repair and waits for the repair personnel to repair and replace.

[0039] When the first threshold value is less than P(I s ,I rWhen P(I

[0040] When P(I s ,I r ,t) is greater than the second threshold value, a low-risk insulation deterioration prompt is made, and the deterioration degree shows a gentle upward trend, indicating that the insulation condition is stable and the failure cause does not accelerate insulation deterioration, and the changes of insulation parameters are recorded for regular inspection and maintenance.

[0041] Wherein, P(I s ,I r ,t) represents the evaluation and prediction of insulation deterioration trend, d b and r b represent the insulation parameters of the stator and the rotor respectively, I s represents the stator insulation index, I r represents the rotor insulation index, t represents time, and B represents the number of insulation parameter pairs considered.

[0042] Another object of the present application is to provide a comprehensive system for health condition assessment and fault warning of a steam turbine generator, which utilizes a data acquisition and processing module to monitor various parameters of the generator in real time, improves the accuracy of data analysis by filtering noise and normalizing the original data, utilizes an online monitoring and evaluation module to evaluate the health condition of the generator and identify the failure cause, utilizes a fault diagnosis and warning module to predict the insulation deterioration trend of the generator, and finally utilizes a maintenance decision module to make maintenance decisions based on the diagnosis results to ensure the safe operation of the generator. Through the comprehensive application of the modules, the comprehensive effects of real-time monitoring, warning, diagnosis and maintenance are achieved, ensuring the safe and stable operation of the steam turbine generator, improving the power generation efficiency, prolonging the service life of the equipment, reducing the maintenance cost, and realizing the comprehensive management and control of the health condition of the steam turbine generator.

[0043] As a preferred scheme of the comprehensive system for health condition assessment and fault warning of a steam turbine generator, it comprises a data acquisition and processing module, an online monitoring and evaluation module, a fault diagnosis and warning module, and a maintenance decision module.

[0044] The data acquisition and processing module installs sensors to collect electrical parameters, mechanical parameters and environmental parameter data for online real-time monitoring, and filters noise and normalizes the collected data to make the data reach the same scale.

[0045] The online monitoring and evaluation module constructs a comprehensive state online monitoring model, performs time series analysis and frequency domain analysis on partial discharge data, rotor magnetic flux data and end vibration data, evaluates the health state of the generator according to the online monitoring result, identifies the fault cause, and provides a data basis for subsequent analysis.

[0046] The fault diagnosis and early warning module analyzes and predicts the insulation degradation trend of the generator according to the health evaluation result, performs dynamic early warning, determines the specific fault of the generator, gives maintenance suggestions, predicts the insulation degradation trend of the generator, and discovers potential risks in advance.

[0047] The maintenance decision module makes maintenance decisions including suspension of operation and maintenance according to the fault diagnosis result, and guarantees the safe operation of the generator.

[0048] A computer device comprises a memory and a processor, the memory stores a computer program, characterized in that the processor implements the steps of the method for comprehensive health condition evaluation and fault early warning of a steam turbine generator when executing the computer program.

[0049] A computer readable storage medium stores a computer program, characterized in that the computer program implements the steps of the method for comprehensive health condition evaluation and fault early warning of a steam turbine generator when executed by a processor.

[0050] The present application has the following beneficial effects: The present application comprehensively monitors the state of the steam turbine generator, captures various key indicators of the generator in real time, reveals the trend and pattern behind the data, provides technical support for accurately evaluating the health condition of the generator, continuously monitors the insulation state of the generator, discovers potential risks in advance, provides decision support for preventive maintenance, helps the operator to take measures in time, prevents the occurrence of faults, and improves the reliability and safety of the generator. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0052] Fig. 1 is a general flowchart of a method for comprehensive health condition evaluation and fault early warning of a steam turbine generator according to an embodiment of the present application.

[0053] Fig. 2 is a system function architecture diagram of a comprehensive system for health condition evaluation and fault early warning of a steam turbine generator according to an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the above objectives, features and advantages of the present application more clear and comprehensible, specific embodiments of the present application are described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present application.

[0055] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application may, however, be practiced without the specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not to obscure the present application. The present application is not limited to the embodiments described herein which can be practiced with or without the certain details that are set forth.

[0056] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor does it mean that the embodiment is mutually exclusive with other embodiments or is selected.

[0057] The present application is described in detail with reference to the accompanying drawings. In the detailed description of the embodiments of the present application, the cross-sectional view of the device structure is partially enlarged without the general proportion for the convenience of description, and the schematic view is only an example which should not limit the scope of protection of the present application. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in the actual manufacture.

[0058] Meanwhile, in the description of the present application, it should be noted that the terms "upper, lower, inner and outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0059] Unless otherwise specifically defined and limited, the terms "mounting, connecting, connection" in the present application should be understood broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through intermediate medium, or it can be the communication between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0060] Example 1

[0061] Referring to Fig. 1, a first embodiment of the present application provides a comprehensive method for health condition assessment and fault early warning of a steam turbine generator, which comprises the following steps:

[0062] S1: install sensors to collect data for online real-time monitoring, and build a comprehensive state online monitoring model for comprehensive data analysis.

[0063] Further, the collected data includes electrical parameters, mechanical parameters, and environmental parameters.

[0064] The electrical parameters include voltage and current, insulation resistance, and partial discharge data.

[0065] The mechanical parameters include rotational speed, displacement, expansion, and vibration data.

[0066] The environmental parameters include humidity, temperature, and dust and particles.

[0067] Preferably, the sensors include a coupling capacitor of 80 pF installed at the high-voltage inlet end of the generator to monitor partial discharge data, including discharge amount, discharge frequency, discharge phase, and discharge spectrum; a magnetic flux probe to monitor rotor magnetic flux data; a vibration sensor installed at the end of the stator to collect end vibration data; and a shaft voltage and current sensor installed at the bearing to collect shaft voltage and current information for online real-time monitoring. After data collection, noise filtering and normalization are performed to make the data have the same scale.

[0068] It should be noted that according to the collected data, the partial discharge data, rotor magnetic flux data, end vibration data, and shaft voltage and current information collected by the sensors are fused for data analysis. Time series analysis is performed on the partial discharge data to reveal the degradation trend and potential failure mode of the generator insulation system.

[0069] where g(y) is the partial discharge data analysis function, K represents the number of partial discharge data samples, y k represents the kth sample of the partial discharge data y, represents the average value of the kth sample of the partial discharge data, represents the standard deviation of the kth sample of the partial discharge data, y n is the amplitude of the partial discharge signal.

[0070] Frequency domain analysis is performed on the rotor magnetic flux data:

[0071] where h(z) represents the rotor magnetic flux data analysis function, ζ represents the normalization constant, z m represents the time series data of the rotor magnetic flux data z, μ z represents the average value of the rotor magnetic flux data, and σ zstandard deviation of rotor flux data, ω m angular frequency of rotor flux data, t is running time.

[0072] time domain and frequency domain analysis of end vibration data and shaft voltage and current information, and construction of comprehensive state online monitoring model:

[0073] wherein i(w) represents analysis function of end vibration data and shaft voltage and current information, E represents number of data points, w j time series data of end vibration data and shaft voltage and current information, μ w average value of end vibration data and shaft voltage and current information, σ w standard deviation of end vibration data and shaft voltage and current information, λ j filtering parameter of end vibration data and shaft voltage and current information.

[0074] comprehensive results of partial discharge data analysis, rotor flux data analysis and end vibration data analysis:

[0075] wherein f(g, h, i) represents output result of comprehensive state online monitoring model, x n acquired data of the nth sensor, μ y,z,w average value of data, σ y,z,w standard deviation of data.

[0076] according to the output result of f(g, h, i), when 0≤f(g, h, i)<20, it indicates that the acquired data belongs to normal state within the running time, if there is abnormal data point at this time, the system considers that it does not affect the operation and is allowed to be ignored, the steam turbine generator remains the current operation mode unchanged, and data acquisition and data analysis are maintained.

[0077] when 20≤f(g, h, i)<50, it indicates that the number of acquired abnormal data points exceeds the number of abnormal data points set according to the current environment x abnormal , the health of the steam turbine generator is immediately evaluated, and whether the performance of the generator is decreased is judged according to the evaluation result, if the performance is not decreased, whether the abnormal data causes insulation degradation is judged according to the running time point, if it does not cause insulation degradation, fault light flashing is performed at the abnormal data point, rapid positioning and notification of the staff for maintenance are performed, if the performance is decreased, it is switched to abnormal operation mode, the power consumption and loss of the steam turbine generator are reduced, and fault prediction is performed.

[0078] When f(g, h, i) ≥ 50, it means that the collected data is normal data point below 3, and it is also considered that the steam turbine generator has existed fault before the running time of collection, the health of the steam turbine generator is evaluated, the damage degree and insulation deterioration degree of the steam turbine generator are judged and dynamic early warning is carried out, and the emergency operation mode is switched, the work of the steam turbine generator is suspended, and the comprehensive maintenance preparation is made.

[0079] S2: According to the comprehensive analysis result, the health state of the generator is comprehensively evaluated, and the fault reason is identified.

[0080] Further, according to the partial discharge data, the rotor magnetic flux data, the end vibration data, the shaft voltage and shaft current information, the normal health evaluation H0 of the steam turbine generator is expressed as:

[0081] When H0 = 1, it means that the generator is in the best health state, and when H0 = 0, it means that the generator is in the fault state, wherein t0 and t f respectively represent the starting and ending time points of the evaluation in the running time, n is the number of sensors, W i is the weight of the i th sensor data, Y i is the complex information filtering function of the i th sensor, y i (t) is the partial discharge data collected by the i th sensor at time t, ε0 and ε f respectively represent the starting and ending positions of the rotor magnetic flux data measurement, H is the normalization function of the rotor magnetic flux data, z R (ε) is the rotor magnetic flux data measured at position ε, ω0 and ω f respectively represent the starting and ending angular frequency of the end vibration data measurement, U is the integral function of the end vibration data, w(x, ω) is the vibration data at position l and angular frequency ω, V0 and V f respectively represent the starting and ending voltage of the shaft voltage and current data measurement, F is the exponential function of the shaft voltage and current data, A(l) is the shaft current information measured at voltage l.

[0082] When H0 = 0, whether the performance H s of the generator decreases is judged:

[0083] Wherein, P(x) represents the performance index of the generator, S(x) represents the data collected by the sensor, n i represents the collected data of the n th sensor, β represents the normalization coefficient of the sensor data, γ represents the coefficient of the logarithmic function, η is the attenuation of the performance index of the generator with time, δ i and δ j represent the time attenuation coefficient of the measurement characteristic of the sensor i, p i and pj is a parameter of signal strength of sensor i, j, which is adjusted according to the importance of the sensor or the reliability of the signal.

[0084] When H s = 1, it means that the performance of the steam turbine generator is not degraded, when 0 < H s < 1, it means that the performance of the steam turbine generator is degraded, when H s is smaller, it means that the performance is more seriously degraded.

[0085] When the number of normal data points is less than 3, the damage degree H2 of the generator is evaluated as: H2 = H s · (1 - e- κ(3-G(x)) )

[0086] When the value of H2 is smaller, it means that the damage degree is higher, where κ represents the coefficient of the normal data points, and G(x) represents the number of normal data points.

[0087] It should be noted that according to the judgment after the comprehensive health evaluation of the steam turbine generator, when the performance H s of the steam turbine generator is degraded and the damage degree H2 is increased, the cause of the fault is determined according to the results of H2 and H s .

[0088] When the performance degradation is less than 0.8 and the damage degree rises to 0.3, it is judged as a fault of partial discharge data, accompanied by a decrease in output power and a decrease in efficiency, and the damage degree is manifested as a decrease in the performance of the insulation material, abnormal sound of corona or spark, and the operation is immediately stopped and partial discharge detection is performed to check the condition of the insulation system, and if a partial discharge source is found, it is located and repaired.

[0089] When the performance degradation is less than 0.75 and the damage degree rises to 0.4, it is judged as a fault of rotor problem, and the performance degradation is manifested as a decrease in speed fluctuation, and the damage degree is manifested as an abnormal increase in rotor temperature, an increase in vibration or an increase in noise, the load is reduced and professional personnel is arranged to check the rotor, vibration analysis is performed to determine whether the rotor is unbalanced or has structural problems, if the rotor winding problem, it is repaired to ensure the normal operation of the rotor cooling system and avoid overheating.

[0090] When the performance degradation is less than 0.6 and the damage degree rises to 0.5, it is judged as a fault of end vibration, and the performance degradation is manifested as unstable operation of the motor and an increase in noise, and the damage degree is manifested as an increase in bearing temperature and an increase in metal particles in lubricating oil analysis, the running speed is reduced and the bearing and mechanical structure are checked, vibration measurement is performed to determine the cause and degree of vibration, and the bearing is checked for wear or damage, the rotor is rebalanced, and the centering condition is checked.

[0091] When the performance degradation is less than 0.7 and the damage degree rises to 0.2, it is judged that the shaft voltage and shaft current information has a problem, the performance degradation shows motor temperature rise anomaly and current imbalance, and the damage degree shows bearing surface electric corrosion and lubricating oil analysis shows that the conductivity increases, the measurement values of the shaft voltage and the shaft current are checked, the causes of the abnormal shaft voltage and shaft current are determined, the shaft grounding device is checked, and the influence of the shaft voltage and the shaft current is reduced.

[0092] By introducing the weight factor and the information filtering function, the accuracy and flexibility of the evaluation are improved, it is ensured that different types of data can be effectively integrated in the health evaluation, the performance index and the damage degree evaluation provide a quantitative basis for the maintenance and fault prediction of the generator, the operation efficiency and reliability of the steam turbine generator are improved, and a new technical approach is provided for preventive maintenance and intelligent fault diagnosis.

[0093] S3: Constructing a generator comprehensive data intelligent monitoring and dynamic early warning model to analyze and predict the insulation deterioration trend of the generator.

[0094] Further, when the health evaluation has a problem and the fault cause is identified, the insulation state of the generator stator and rotor is analyzed and predicted:

[0095] When P(I s ,I r ,t) is greater than or equal to the first threshold value, it is prompted that the insulation deterioration is high risk, and the deterioration degree shows a rapid upward trend, indicating that the fault cause accelerates the insulation deterioration, the intelligent monitoring performs emergency light flashing and urgent sound warning, stops the work of the steam turbine generator, performs initial repair and waits for repair personnel to repair and replace.

[0096] When the first threshold value is less than P(I s ,I r ,t) is less than or equal to the second threshold value, it is prompted that the insulation deterioration is medium risk, and the deterioration degree shows an upward trend but the upward speed is slow, indicating that the fault cause accelerates the insulation deterioration, the intelligent monitoring performs intermittent sound warning, notifies the operator to pay attention to the potential insulation problem, and prepares for preventive maintenance.

[0097] When P(I s ,I r ,t) is greater than the second threshold value, it is prompted that the insulation deterioration is low risk, and the deterioration degree shows a gentle upward trend, indicating that the insulation condition is stable and the fault cause does not accelerate the insulation deterioration, the changes of the insulation parameters are recorded, and regular inspection and maintenance are performed.

[0098] Wherein, P(I s ,I r ,t) represents the evaluation and prediction of the insulation deterioration trend, d b and r brepresents the insulation parameter of the stator and rotor, respectively, I s represents the insulation index of the stator, I r represents the insulation index of the rotor, t represents time, and B represents the number of considered pairs of insulation parameters.

[0099] It should be noted that the above examples are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application, and they should be covered in the scope of the claims of the present application.

[0100] Example 2

[0101] In one embodiment of the present application, a comprehensive method for health condition assessment and fault early warning of a steam turbine generator is provided. In order to verify the beneficial effects of the present application, scientific demonstration is carried out through experiments.

[0102] The test object is a steam turbine generator of model TG-2000, which has been running for 5 years with regular maintenance. In order to verify the effectiveness of the health condition assessment and fault early warning comprehensive method described in the present application, we first installed various sensors to collect electrical, mechanical and environmental parameters. Specifically, they include:

[0103] Electrical parameters: voltage, current, insulation resistance, partial discharge data;

[0104] Mechanical parameters: speed, displacement, expansion, vibration data;

[0105] Environmental parameters: humidity, temperature, dust and particles.

[0106] In particular, we installed an 80pF coupling capacitor to monitor the partial discharge data at the high-voltage inlet end of the generator, used a magnetic flux probe to monitor the rotor magnetic flux data, and installed a vibration sensor at the end of the stator to collect end vibration data. Shaft voltage and current sensors were installed at the bearing to collect shaft voltage and current information. All sensors have online real-time monitoring and data transmission functions.

[0107] After data collection, we use advanced signal processing techniques to filter out noise and normalize the data to ensure that the data is on the same scale, making it easier for subsequent comprehensive data analysis.

[0108] Next, we constructed a comprehensive state online monitoring model that integrates partial discharge data, rotor magnetic flux data, end vibration data, and shaft voltage and current information. Through time series analysis and frequency domain analysis, we can assess the health condition of the generator in real time.

[0109] According to the output results of the online monitoring model, we set three warning levels corresponding to different degrees of data anomalies. When the number of abnormal data points exceeds a certain number, the system will automatically issue a fault warning and take appropriate measures such as reducing power consumption, switching operating modes, or suspending work according to the specific situation.

[0110] Finally, we use the comprehensive evaluation expression to quantitatively evaluate the health status of the generator and predict the damage and insulation degradation level of the generator according to the evaluation results.

[0111] Table 1

[0112] By comparing the test objects TG-2000 and TG-2003 in the data table, we can clearly see the advantages of the method. TG-2000 adopts the method of the application, and its comprehensive evaluation score is 32, in the second warning state, indicating that there is a certain degree of abnormality, but it has not reached a serious level. While TG-2003 does not use the method of the application, its comprehensive evaluation score is 55, in the third warning state, indicating a serious risk of failure.

[0113] In addition, the method of the application can monitor and warn the health status of the generator in real time, compared with the traditional periodic maintenance method, it can discover and handle potential problems more timely, thereby significantly improving the operating efficiency and safety of the generator.

[0114] It should be noted that the above examples are only used to illustrate the technical solutions of the application and are not limiting. Although the application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the application, which should be covered in the scope of the claims of the application.

[0115] Example 3

[0116] The third embodiment of the application is different from the first two embodiments:

[0117] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the part of the technical solutions that essentially contribute to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0118] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logic functions, and can be specifically embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or in conjunction with these instructions execution systems, apparatuses, or devices. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport programs for use by an instruction execution system, apparatus, or device, or in conjunction with these instruction execution systems, apparatuses, or devices.

[0119] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection having one or more wires (electrical devices), a portable computer diskette (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, as the program can be electronically obtained, for example, by optical scanning of the paper or other medium, followed by editing, interpreting, or otherwise processing, if necessary, in other suitable ways to be electronically obtained, and then stored in the computer memory.

[0120] It should be understood that various parts of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any of the following technologies, known in the art, or a combination thereof, can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0121] Embodiment 4

[0122] Referring to FIG. 2, a fourth embodiment of the present application provides a comprehensive system for health assessment and fault early warning of a steam turbine generator, including a data acquisition and processing module, an online monitoring and assessment module, a fault diagnosis and early warning module, and a maintenance decision module.

[0123] The data acquisition and processing module installs sensors to collect electrical parameters, mechanical parameters, and environmental parameter data, performs online real-time monitoring, filters and normalizes the collected data to make the data reach the same scale.

[0124] The online monitoring and assessment module constructs a comprehensive online monitoring model, performs time series analysis and frequency domain analysis on partial discharge data, rotor magnetic flux data, and end vibration data, assesses the health status of the generator according to the online monitoring results, identifies the fault cause, and provides a data basis for subsequent analysis.

[0125] The fault diagnosis and early warning module analyzes and predicts the insulation degradation trend of the generator according to the health assessment results, performs dynamic early warning, determines the specific fault of the generator, gives maintenance suggestions, predicts the insulation degradation trend of the generator, and discovers potential risks in advance.

[0126] The maintenance decision module makes maintenance decisions including suspension of operation and maintenance according to the fault diagnosis results, and ensures the safe operation of the generator.

[0127] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

A comprehensive method for health condition assessment and fault early warning of a steam turbine generator, characterized in that: The application relates to a generator health state monitoring and early warning system. The system comprises the following steps: Collecting data through installed sensors for online real-time monitoring, and constructing an online comprehensive state monitoring model for comprehensive data analysis; According to the comprehensive analysis result, the health state of the generator is comprehensively evaluated, and the fault cause is identified; A comprehensive method for evaluating the health condition and early warning of faults of a steam turbine generator as claimed in claim 1, characterized in that: A generator comprehensive data intelligent monitoring and dynamic early warning model is constructed to analyze and predict the insulation deterioration trend of the generator. The collected data comprises electrical parameters, mechanical parameters and environmental parameters; The electrical parameters comprise voltage and current, insulation resistance and partial discharge data; The mechanical parameters comprise rotating speed, displacement, expansion and vibration data; The environmental parameters comprise humidity, temperature, dust and particles; A comprehensive method for health condition evaluation and fault early warning of a steam turbine generator according to claim 2, characterized in that: The comprehensive state online monitoring model comprises collecting and fusing partial discharge data, rotor magnetic flux data, end vibration data, shaft voltage and shaft current information collected by sensors, performing data analysis, and performing time series analysis on the partial discharge data: where g(y) is a local data analysis function, K represents the number of local data samples, y k represents the kth sample of the local data y, an average value of the kth sample of the local discharge data, standard deviation of the kth sample of the partial discharge data, y n is the amplitude of the partial discharge signal; Frequency domain analysis is performed on the rotor flux data: where h(z) represents the rotor flux data analysis function, ζ represents a normalization constant, z m represents the time series data of rotor flux data z, μ z represents the mean of rotor flux data, σ z represents the standard deviation of rotor flux data, ω m represents the angular frequency of rotor flux data, t is the running time; The end vibration data and shaft voltage and current information are analyzed in time domain and frequency domain to construct an integrated state online monitoring model: where i(w) represents an analysis function of the end vibration data and the shaft voltage and current information, E represents the number of data points, w j represents time series data of the end vibration data and the shaft voltage and current information, μ w represents the mean value of the end vibration data and the shaft voltage and current information, σ w represents the standard deviation of the end vibration data and the shaft voltage and current information, λ j represents a filter parameter of the end vibration data and the shaft voltage and current information; The results of partial discharge data analysis, rotor flux data analysis and end vibration data analysis are comprehensively analyzed: wherein f(g, h, i) represents the output result of the comprehensive state online monitoring model, x n represents the collected data of the nth sensor, μ y,z,w represents the average value of the data, and σ y,z,w represents the standard deviation of the data. A comprehensive method for health condition evaluation and fault early warning of a steam turbine generator according to claim 3, characterized in that: The installed sensors comprise a 80pF coupling capacitor installed at a high-voltage inlet end of the generator to monitor partial discharge data, the partial discharge data comprising discharge quantity, discharge frequency, discharge phase and discharge spectrum, a magnetic flux probe is used to monitor rotor magnetic flux data, a vibration sensor is installed at the end of the stator to collect end vibration data, a bearing bush is provided with a shaft voltage and shaft current sensor to collect shaft voltage and shaft current information for online real-time monitoring, and after the data is collected, noise is filtered and the data is normalized to make the data reach the same scale. When 20≤f(g,h,i)<50, it indicates that the collected abnormal data points exceed the number x of abnormal data points set according to the current environment abnormal The health of the steam turbine generator is immediately evaluated, and whether the performance of the generator is degraded is judged according to the evaluation result. If the performance is not degraded, whether the abnormal data will cause insulation degradation is judged according to the running time point. If the insulation is not degraded, the fault light flashes at the abnormal data point, the staff is quickly located and notified to repair. If the performance is degraded, the abnormal operation mode is switched, the power consumption and loss of the steam turbine generator are reduced, and fault prediction is performed. The comprehensive data analysis comprises the following steps: A comprehensive method for health condition evaluation and fault early warning of a steam turbine generator according to claim 4, characterized in that: The comprehensive evaluation of the generator health state includes normalizing health evaluation H0 of the steam turbine generator according to the partial discharge data, the rotor magnetic flux data, the end vibration data, and the shaft voltage and shaft current information, and is expressed as: H0= 1 indicates that the generator is in an optimal health state, and H0= 0 indicates that the generator is in a fault state, where t0and t f respectively represent the start and end time points of the evaluation within the operating time, n is the number of sensors, W i is the weight of the i-th sensor data, Y i is the complex information filtering function of the i-th sensor, y i (t) is the partial discharge data collected by the i-th sensor at time t, ε0and ε f respectively represent the start and end positions of the rotor flux data measurement, H is the normalization function of the rotor flux data, z R (ε) is the rotor flux data measured at position ε, ω0and ω f respectively represent the start and end angular frequencies of the end vibration data measurement, U is the integral function of the end vibration data, w(x, ω) is the vibration data at position l and angular frequency ω, V0and V f respectively represent the start and end voltages of the shaft voltage and current data measurement, F is the exponential function of the shaft voltage and current data, A(l) is the shaft current information measured at voltage l; When H0=0, the generator performance H is judged s whether it is decreased: where P(x) represents the performance index of the generator, S(x) represents the data collected by the sensor, n i represents the collected data of the nth sensor, β represents the normalization coefficient of the sensor data, γ represents the coefficient of the logarithmic function, η is the attenuation of the performance index of the generator over time, δ i and δ j represent the time attenuation coefficient of the measurement characteristics of sensor i, p i and p j are parameters of the signal intensity of sensors i, j, which are adjusted according to the importance of the sensor or the reliability of the signal; When H s = 1, it means that the performance of the steam turbine generator has not decreased, when 0 < H s < 1, it means that the performance of the steam turbine generator is decreasing, and when H s is smaller, it means that the performance is decreasing more seriously. When 0<=f(g,h,i)<20, the collected data is in a normal state within the running time, if there are abnormal data points at the moment, the system considers that the abnormal data points do not affect the running and can be ignored, the steam turbine generator remains in the current running mode, and data collection and data analysis are maintained; H2= H s • (1 - e - k - (3 - G(x))) When f(g,h,i)>=50, the normal data points are less than 3, and it is considered that the steam turbine generator has been faulty before the collected running time, the health of the steam turbine generator is evaluated, the damage degree and insulation deterioration degree of the steam turbine generator are judged, and dynamic early warning is performed, and the steam turbine generator is switched to an emergency running mode and stopped for overall maintenance preparation. A comprehensive method for health condition evaluation and fault early warning of a steam turbine generator according to claim 5, characterized in that: The identifying the failure cause includes, according to the judgment after the comprehensive health assessment of the steam turbine generator, when the performance H s of the steam turbine generator is decreasing and the damage degree H2 is increasing, judging the failure cause according to the results of H2 and H s ​ When the normal data points are less than 3, the damage degree H2 of the generator is evaluated and expressed as follows: The smaller the value of H2 is, the higher the damage degree is, wherein kappa represents the coefficient of the normal data points, and G(x) represents the number of the normal data points. When the performance decline is less than 0.8 and the damage degree rises to 0.3, it is judged that the fault is a partial discharge data fault, and the performance decline is accompanied by output power reduction and efficiency reduction, and the damage degree is manifested as insulation material performance reduction, abnormal corona sound or spark sound, the running is immediately stopped, and partial discharge detection is performed; if a partial discharge source is found, the partial discharge source is located and repaired; When the performance decline is less than 0.75 and the damage degree rises to 0.4, it is judged that the fault is a rotor problem, the performance decline is manifested as rotating speed fluctuation reduction, and the damage degree is manifested as abnormal rotor temperature rise, vibration increase or noise increase, the load is reduced, and professional personnel are arranged to check the rotor, vibration analysis is performed to determine whether the rotor is unbalanced or has a structure problem, if the rotor winding has a problem, the rotor winding is repaired to ensure normal operation of the rotor cooling system and avoid overheating. When the performance degradation is less than 0.6 and the damage degree rises to 0.5, it is judged that the end vibration fault occurs, and the performance degradation is manifested as unstable operation of the motor and increased noise, and the damage degree is manifested as increased bearing temperature and increased metal particles in the lubricating oil analysis, the running speed is reduced and the bearing and mechanical structure are checked, vibration measurement is performed to determine the cause and degree of vibration, whether the bearing is worn or damaged is checked, the rotor is rebalanced, and the centering condition is checked; When the performance degradation is less than 0.7 and the damage degree rises to 0.2, it is judged that the shaft voltage and shaft current information problem occurs, and the performance degradation is manifested as abnormal temperature rise of the motor and unbalanced current, and the damage degree is manifested as surface electrocorrosion of the bearing and increased conductivity in the lubricating oil analysis, the measured values of the shaft voltage and the shaft current are checked to determine the cause of the abnormal shaft voltage and shaft current, the shaft grounding device is checked to reduce the influence of the shaft voltage and the shaft current. A comprehensive method for health condition evaluation and fault early warning of a steam turbine generator according to claim 6, characterized in that: The generator comprehensive data intelligent monitoring and dynamic early warning model comprises analysis and prediction of the insulation state of the generator stator and rotor after the health assessment has problems and the fault cause is identified: When P(I s ,I r ,t) is greater than or equal to the first threshold value, a high-risk prompt of insulation deterioration is made, and the degree of deterioration shows a rapid upward trend, indicating that the fault reason accelerates the insulation deterioration, the intelligent monitoring carries out the emergency light flashing and urgent sound warning, stops the work of the steam turbine generator, carries out the initial repair and waits for the repair personnel to repair and replace; when the first threshold < P(I s ,I r ,t) ≤ the second threshold, a medium risk prompt of insulation deterioration is made, and the deterioration degree shows an upward trend but the upward speed is slow, indicating that the failure cause accelerates insulation deterioration, the intelligent monitoring performs intermittent sound early warning, notifies the operator to pay attention to the potential insulation problem, and prepares to perform preventive maintenance; When P(I s ,I r ,t) > second threshold value, make insulation deterioration low risk prompt, and the deterioration degree shows gentle rising trend, indicating that the insulation condition is stable, the failure reason does not accelerate the insulation deterioration, record the change of insulation parameters, and regularly check and maintain; where P(I s , t) represents the evaluation and prediction of the insulation deterioration trend, d r and r b represent the insulation parameters of the stator and rotor, respectively, I b represents the stator insulation index, I s represents the rotor insulation index, t represents time, and B represents the number of pairs of insulation parameters considered. r ​ A system using the comprehensive method for health condition evaluation and fault early warning of a steam turbine generator according to any one of claims 1 to 7, characterized in that: The data acquisition and processing module, the online monitoring and evaluation module, the fault diagnosis and early warning module, and the maintenance decision module are included. The data acquisition and processing module installs sensors to collect electrical parameters, mechanical parameters, and environmental parameter data for online real-time monitoring, and performs noise filtering and normalization processing on the collected data to make the data reach the same scale. The online monitoring and evaluation module constructs a comprehensive state online monitoring model, performs time series analysis and frequency domain analysis on partial discharge data, rotor magnetic flux data, and end vibration data, evaluates the health status of the generator according to the online monitoring results, identifies the fault cause, and provides a data basis for subsequent analysis. The fault diagnosis and early warning module analyzes and predicts the insulation degradation trend of the generator according to the health evaluation results, performs dynamic early warning, determines the specific fault of the generator, gives maintenance suggestions, predicts the insulation degradation trend of the generator, and discovers potential risks in advance. The maintenance decision module makes maintenance decisions including suspension of operation and maintenance according to the fault diagnosis results to ensure safe operation of the generator. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to realize the steps of the method of any one of claims 1 to 7. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to realize the steps of the method of any one of claims 1 to 7.

Images