A safety evaluation and diagnosis system and method for a steam turbine generator under deep peak regulation conditions

Abstract

The present application relates to a kind of deep peak shaving operating condition under steam turbine generator safety evaluation diagnosis system and method, system includes generator multiple parameter state evaluation model and generator common fault intelligent diagnosis model;Generator multiple parameter state evaluation model compares the each parameter state information of generator real-time operation in DCS system with the operating standard of corresponding parameter, the difference between the state measured value and standard value of multiple parameters is quantitatively analyzed and processed, whether the current state of each parameter of generator is qualified according to the deviation between state measured value and standard value;When the state evaluation result of certain parameter of generator is unqualified, generator common fault intelligent diagnosis model diagnoses and analyzes the reason of motor anomaly, establishes comprehensive analysis model, finds out the index that can distinguish different types of faults and analyzes fault reason;Expert diagnosis library is established in combination with fault case and expert experience criterion, according to the mapping relationship between fault type and maintenance strategy, the corresponding maintenance strategy is obtained.

Description

Technical Field

[0001] This invention relates to the field of generator safety technology, specifically to a safety evaluation and diagnostic system and method for steam turbine generators under deep peak shaving conditions. Background Technology

[0002] Currently, wind power, photovoltaic power, and other new energy sources are gradually becoming the main power sources in my country. Due to the instability of new energy power generation, the guarantee of power output requires the support and guarantee of thermal power with regulation capabilities. Thermal power generation is shifting from a main power source that guarantees power output to a regulation-type power source, and thermal power units will face the trend of operating at deep peak shaving up to 20% of rated load. However, deep peak shaving conditions have a significant impact on the reliability and lifespan of steam turbine generators, and even threaten the safe and stable operation of generators. The generator safety of deep peak shaving units is particularly important, and currently there is no safety evaluation and diagnostic system for steam turbine generators under deep peak shaving conditions. Summary of the Invention

[0003] Therefore, the present invention aims to address the current deficiency of lacking a safety evaluation and diagnosis system for steam turbine generators under deep peak shaving conditions, thereby providing a safety evaluation and diagnosis system and method for steam turbine generators under deep peak shaving conditions.

[0004] A safety evaluation and diagnostic system for steam turbine generators under deep peak shaving conditions includes a multi-parameter state evaluation model for the generator and an intelligent diagnostic model for common generator faults.

[0005] The generator multi-parameter status evaluation model compares the status information of each parameter of the generator in real time in the DCS system with the corresponding operating standards. The generator multi-parameter status evaluation model performs quantitative analysis and processing on the differences between the status measurement values ​​and standard values ​​of multiple parameters, and evaluates whether the current status of each parameter of the generator is qualified based on the deviation between the status measurement values ​​and standard values.

[0006] When the evaluation result of a certain parameter of the generator is unqualified, the intelligent diagnostic model for common generator faults diagnoses and analyzes the causes of the generator abnormality, and establishes a comprehensive analysis model from the perspectives of spatial distribution and time scale to identify indicators that can distinguish different types of faults and analyze the causes of the faults. The intelligent diagnostic model for common generator faults combines typical fault cases and expert experience criteria to establish an expert diagnostic database, and derives corresponding maintenance strategies based on the mapping relationship between various fault types and maintenance strategies.

[0007] Furthermore, the system performs intelligent diagnosis of rotor winding inter-turn short circuit faults, stator grounding faults, and stator bar blockages.

[0008] Furthermore, the system's diagnosis process for inter-turn short circuit faults in the rotor windings is as follows: Based on the generator's active power, reactive power, terminal voltage, and excitation current data during normal generator operation, a generator excitation current calculation model is established, establishing the correspondence between generator active power, reactive power, terminal voltage, and excitation current. Using this model, the system monitors the generator's active power, reactive power, and terminal voltage in real time, calculating a baseline value for the excitation current under this operating condition. By comparing the actual excitation current with the baseline value, it is determined whether there is an increase in excitation current. If the deviation between the actual measured excitation current and the model's calculated value is within a threshold range, it is considered that the excitation current has not increased significantly, and no further judgment is made. If an increase in excitation current is detected, it is considered that there is a possibility of an inter-turn short circuit. Data on the excitation current and other generator parameters are retrieved, and the correlation coefficients between the other parameters and the excitation current are calculated. Taking into account all the above factors and combining them with an expert diagnostic database, the possibility of an inter-turn short circuit is assessed. Finally, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated.

[0009] Furthermore, the specific process of the system for stator grounding faults is as follows: Based on the data of generator terminal voltage, terminal current, generator active power, and generator reactive power during normal generator operation, a generator terminal voltage calculation model is established, establishing the correspondence between the generator terminal current, generator active power, generator reactive power, and generator terminal voltage. This model monitors the generator terminal current, generator active power, and generator reactive power in real time, calculating the reference value of the generator terminal voltage under this operating condition. By comparing the actual generator terminal voltage with the reference value, it is determined whether there is a decrease in generator terminal voltage. If the deviation between the actual measured generator terminal voltage and the model calculation value is within a threshold range, it is considered that the generator terminal voltage has not decreased significantly, and no further judgment is made. If signs of a decrease in generator terminal voltage are found, it is considered that there is a possibility of stator grounding. Data on generator terminal voltage and other generator parameters are retrieved, and the correlation coefficient between each parameter and the generator terminal voltage is calculated. Taking into account all the above factors and combining them with an expert diagnostic database, the possibility of stator grounding is assessed. Then, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated.

[0010] Furthermore, the specific process of the system for diagnosing stator bar blockage is as follows: Based on data of stator bar outlet water temperature, bar interlayer temperature, core temperature, generator active power, and generator reactive power during normal generator operation, a stator bar outlet water temperature calculation model is established, establishing the correspondence between bar interlayer temperature, core temperature, generator active power, generator reactive power, and stator bar outlet water temperature. Using this model, the system monitors the bar interlayer temperature, core temperature, generator active power, and generator reactive power in real time, calculates the reference value of the stator bar outlet water temperature under this operating condition, and compares the actual stator bar outlet water temperature with the reference value to determine if there is blockage. If the stator bar outlet water temperature increases, and the deviation between the actual measured stator bar outlet water temperature and the model calculation value is within the threshold range, it is considered that the stator bar outlet water temperature has not increased significantly, and no further judgment is made. If signs of increased stator bar outlet water temperature are found, it is considered that there is a possibility of stator bar blockage. Data on stator bar outlet water temperature and other generator parameters are retrieved, and the correlation coefficient between each parameter and stator bar outlet water temperature is calculated. Taking into account the above factors and combining them with the expert diagnostic database, the possibility of stator bar blockage is assessed, and then an intelligent maintenance strategy that can be selected is generated based on the assessment results and the expert diagnostic database.

[0011] A method for safety evaluation and diagnosis of steam turbine generator under deep peak shaving conditions is as follows: the status information of each parameter of the generator in real time in the DCS system is compared with the corresponding parameter operation standard. The generator multi-parameter status evaluation model performs quantitative analysis and processing on the difference between the status measurement value and the standard value of multiple parameters. The current status of each parameter of the generator is evaluated as qualified based on the deviation between the status measurement value and the standard value.

[0012] When the status evaluation result of a certain parameter of the generator is unqualified, the cause of the generator abnormality is diagnosed and analyzed, and a comprehensive analysis model is established from two aspects: spatial distribution and time scale. The model identifies indicators that can distinguish different types of faults and analyzes the cause of the fault. The intelligent diagnosis model for common generator faults combines typical fault cases and expert experience criteria to establish an expert diagnosis database. Based on the mapping relationship between various fault types and maintenance strategies, the corresponding maintenance strategies are derived.

[0013] Furthermore, the method can intelligently diagnose rotor winding inter-turn short circuit faults, stator grounding faults, and stator bar blockages.

[0014] Furthermore, the method for diagnosing inter-turn short-circuit faults in rotor windings is as follows: Based on the generator's active power, reactive power, terminal voltage, and excitation current data during normal generator operation, a generator excitation current calculation model is established, showing the correspondence between generator active power, reactive power, terminal voltage, and excitation current. Using this model, the generator's active power, reactive power, and terminal voltage are monitored in real time, and a benchmark value for the excitation current under this operating condition is calculated. By comparing the actual excitation current with the benchmark value, it is determined whether there is an increase in excitation current. If the deviation between the actual measured excitation current and the model's calculated value is within a threshold range, it is considered that the excitation current has not increased significantly, and no further judgment is made. If an increase in excitation current is detected, it is considered that there is a possibility of an inter-turn short circuit. Data on the excitation current and other generator parameters are retrieved, and the correlation coefficients between the other parameters and the excitation current are calculated. Taking into account all the above factors and combining them with an expert diagnostic database, the possibility of an inter-turn short circuit is assessed. Finally, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated.

[0015] Furthermore, the method for diagnosing stator grounding faults is as follows: Based on data of generator terminal voltage, terminal current, generator active power, and generator reactive power during normal generator operation, a generator terminal voltage calculation model is established, establishing the correspondence between terminal current, generator active power, generator reactive power, and generator terminal voltage. This model is used to monitor the generator terminal current, generator active power, and generator reactive power in real time, calculating the reference value of the generator terminal voltage under this operating condition. By comparing the actual generator terminal voltage with the reference value, it is determined whether there is a decrease in generator terminal voltage. If the deviation between the actual measured generator terminal voltage and the model calculation value is within a threshold range, it is considered that the generator terminal voltage has not decreased significantly, and no further judgment is made. If signs of a decrease in generator terminal voltage are found, it is considered that there is a possibility of stator grounding. Data on generator terminal voltage and other generator parameters are retrieved, and the correlation coefficient between each parameter and the generator terminal voltage is calculated. Taking into account all the above factors and combining them with an expert diagnostic database, the possibility of stator grounding is assessed. Finally, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated.

[0016] Furthermore, the method for diagnosing stator bar blockage involves: establishing a stator bar outlet water temperature calculation model based on data from the stator bar outlet water temperature, bar interlayer temperature, core temperature, generator active power, and generator reactive power during normal generator operation; using this model to monitor the bar interlayer temperature, core temperature, generator active power, and generator reactive power in real time; calculating a reference value for the stator bar outlet water temperature under this operating condition; and comparing the actual stator bar outlet water temperature with the reference value to determine if there is blockage. If the stator bar outlet water temperature increases, and the deviation between the actual measured stator bar outlet water temperature and the model calculation value is within the threshold range, it is considered that the stator bar outlet water temperature has not increased significantly, and no further judgment is made. If signs of increased stator bar outlet water temperature are found, it is considered that there is a possibility of stator bar blockage. Data on stator bar outlet water temperature and other generator parameters are retrieved, and the correlation coefficient between each parameter and stator bar outlet water temperature is calculated. Taking into account the above factors and combining them with the expert diagnostic database, the possibility of stator bar blockage is assessed, and then an intelligent maintenance strategy that can be selected is generated based on the assessment results and the expert diagnostic database.

[0017] The technical solution of this invention can realize early warning and intelligent diagnosis of potential typical faults in generator operation, guide power plant personnel to formulate maintenance strategies and analyze and deal with problems, ensure the safe and stable operation of generators, and avoid economic losses to power plants due to generator failure shutdowns. Attached Figure Description

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 Flowchart of the safety evaluation and diagnosis system for steam turbine generators under deep peak shaving conditions;

[0020] Figure 2 Flowchart of generator rotor inter-turn short circuit fault diagnosis and intelligent decision-making model;

[0021] Figure 3 Flowchart of generator stator grounding fault diagnosis and intelligent decision-making model;

[0022] Figure 4 Flowchart of stator bar blockage fault diagnosis and intelligent decision-making model; Detailed Implementation

[0023] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0025] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0026] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0027] Please see Figure 1 A safety evaluation and diagnosis system for steam turbine generators under deep peak shaving conditions includes a multi-parameter state evaluation model for the generator and an intelligent diagnosis model for common generator faults.

[0028] The generator multi-parameter status evaluation model compares the real-time status information of various parameters of the generator in the DCS system with the corresponding operating standards. The generator multi-parameter status evaluation model performs quantitative analysis and processing on the differences between the status measurement values ​​and standard values ​​of multiple parameters, and evaluates whether the current status of each parameter of the generator is qualified based on the deviation between the status measurement values ​​and the standard values. When the deviation between the status measurement values ​​and the standard values ​​exceeds the threshold range, it indicates that there is an abnormality in the generator status. The larger the deviation, the higher the possibility of generator failure, thus realizing early warning of potential typical faults in generator operation.

[0029] When the state evaluation result of a certain parameter of the generator is unqualified, the intelligent diagnostic model for common generator faults diagnoses and analyzes the causes of the generator abnormality, and establishes a comprehensive analysis model from two aspects: spatial distribution and time scale. On the one hand, it studies the static spatial distribution characteristics of various state variables of the generator and finds indicators that can distinguish different types of faults; on the other hand, it studies the dynamic trend change characteristics of various state variables, quantifies the trend change characteristics, and uses this as a basis to analyze the causes of the fault. The intelligent diagnostic model for common generator faults combines typical fault cases and expert experience criteria to establish an expert diagnostic database. Based on the mapping relationship between various fault types and maintenance strategies, it derives corresponding maintenance strategies to guide power plant personnel in analysis and handling.

[0030] The system performs intelligent diagnosis of rotor winding inter-turn short circuit faults, stator grounding faults, and stator bar blockages.

[0031] Please see Figure 2 Based on the fault characteristics of rotor winding inter-turn short circuits, this paper mainly considers four fault characteristics for diagnosing rotor winding inter-turn short circuits: excitation current deviation, generator terminal voltage, and generator active and reactive power. By inputting relevant data, a generator rotor inter-turn short circuit fault diagnosis and intelligent decision-making model can be quickly established. The specific process is as follows: First, centralized data is imported into the diagnostic system to establish a generator excitation current calculation model. This model is based on the generator active power, generator reactive power, generator terminal voltage, and excitation current data during normal engine operation, establishing a generator excitation current calculation model that establishes the corresponding relationship between generator active power, generator reactive power, generator terminal voltage, and excitation current. This model primarily provides a reference value for the excitation current for each operating condition. Based on this model, the generator active power, generator reactive power, and generator terminal voltage are monitored in real time to calculate the reference value for the excitation current under this operating condition. This is then verified through actual... The excitation current is compared with the reference value to determine if there is an increase in excitation current. If the deviation between the actual measured excitation current and the model calculated value is within the threshold range, it is considered that there is no significant increase in excitation current, and no further judgment is made. If an increase in excitation current is found, it is considered that there is a possibility of inter-turn short circuit. Data on excitation current and other generator parameters are retrieved, and the correlation coefficients between other parameters and excitation current are calculated. If necessary, the excitation current can be appropriately increased or decreased to obtain data. Taking into account all the above factors and combining them with the expert diagnostic database, the possibility of inter-turn short circuit is assessed. Then, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated to guide power plant personnel in finding and handling defects. For example, in the case of a particularly serious inter-turn short circuit, it is recommended to shut down the unit in time for handling. For minor inter-turn short circuits, operation can continue with enhanced monitoring until the next major overhaul, when other means can be used for verification and handling.

[0032] Please see Figure 3Based on the fault characteristics currently observed during stator grounding, the diagnosis primarily considers four fault characteristics: generator terminal voltage, generator terminal current, generator active power, and generator reactive power. Inputting relevant data allows for the rapid establishment of a generator stator grounding fault diagnosis and intelligent decision-making model. Specifically: First, centralized data is imported into the diagnostic system to establish a generator terminal voltage calculation model. This model establishes the corresponding relationship between generator terminal voltage, generator active power, generator reactive power, and generator terminal voltage based on data from the generator during normal operation. This model primarily aims to provide a reference value for the generator terminal voltage for each operating condition. Through this model, the generator terminal current and generator active power are monitored in real time. Considering the generator's reactive power, the reference value of the generator terminal voltage under this operating condition is calculated. By comparing the actual generator terminal voltage with the reference value, it is determined whether there is a decrease in the generator terminal voltage. If the deviation between the actual measured generator terminal voltage and the calculated value is within the threshold range, it is considered that there is no significant decrease in the generator terminal voltage, and no further judgment is made. If signs of a decrease in generator terminal voltage are found, it is considered that there is a possibility of stator grounding. Data on generator terminal voltage and other generator parameters are retrieved, and the correlation coefficients between each parameter and the generator terminal voltage are calculated. Taking into account all the above factors and combining them with the expert diagnostic database, the possibility of stator grounding is assessed. Then, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated to guide power plant personnel in finding and handling defects. For example, if stator grounding has been confirmed, the generator should be shut down immediately for handling.

[0033] Please see Figure 4Based on the current fault characteristics of stator bar blockage, the diagnosis mainly considers five fault characteristics: stator bar outlet water temperature deviation, bar interlayer temperature, core temperature, and generator active and reactive power. Inputting relevant data allows for the rapid establishment of a generator stator bar blockage fault diagnosis and intelligent decision-making model. Specifically: First, centralized data is imported into the diagnostic system to establish a stator bar outlet water temperature calculation model. This model establishes the correspondence between the stator bar outlet water temperature, bar interlayer temperature, core temperature, generator active power, and generator reactive power data during normal generator operation, and the stator bar outlet water temperature. This model primarily aims to provide a reference value for the stator bar outlet water temperature for each operating condition. Based on this model, the bar interlayer temperature and core temperature are monitored in real time. Based on the temperature, generator active power, and generator reactive power, a baseline value for the stator bar outlet water temperature under this operating condition is calculated. The actual stator bar outlet water temperature is compared with this baseline value to determine if there is an increase in stator bar outlet water temperature. If the deviation between the actual measured stator bar outlet water temperature and the model calculation value is within a threshold range, it is considered that the stator bar outlet water temperature has not increased significantly, and no further judgment is made. If signs of an increase in stator bar outlet water temperature are found, it is considered that there is a possibility of stator bar blockage. Data on the stator bar outlet water temperature and other generator parameters are retrieved, and the correlation coefficients between each parameter and the stator bar outlet water temperature are calculated. Taking all the above factors into account and combining them with an expert diagnostic database, the possibility of stator bar blockage is assessed. Then, the assessment results and the expert diagnostic database are used to generate selectable intelligent maintenance strategies to guide power plant personnel in finding and handling defects. For example, in the case of particularly severe stator bar blockage, it is recommended to shut down the unit immediately for treatment. For minor stator bar blockage, operation can continue with enhanced monitoring, and verification and treatment can be carried out through other means during the next major overhaul.

[0034] This invention also includes a method for safety evaluation and diagnosis of steam turbine generators under deep peak shaving conditions. Specifically, the method involves comparing the status information of various parameters of the generator in real time in the DCS system with the corresponding operating standards. The generator multi-parameter status evaluation model performs quantitative analysis and processing on the differences between the status measurement values ​​and standard values ​​of multiple parameters. The method evaluates whether the current status of each parameter of the generator is qualified based on the deviation between the status measurement values ​​and the standard values.

[0035] When the status evaluation result of a certain parameter of the generator is unqualified, the cause of the generator abnormality is diagnosed and analyzed, and a comprehensive analysis model is established from two aspects: spatial distribution and time scale. The model identifies indicators that can distinguish different types of faults and analyzes the cause of the fault. The intelligent diagnosis model for common generator faults combines typical fault cases and expert experience criteria to establish an expert diagnosis database. Based on the mapping relationship between various fault types and maintenance strategies, the corresponding maintenance strategies are derived.

[0036] The method can intelligently diagnose rotor winding inter-turn short circuit faults, stator grounding faults, and stator bar blockages.

[0037] The method for diagnosing inter-turn short-circuit faults in rotor windings is as follows: Based on the generator's active power, reactive power, terminal voltage, and excitation current data during normal generator operation, a generator excitation current calculation model is established, showing the correspondence between generator active power, reactive power, terminal voltage, and excitation current. This model is used to monitor the generator's active power, reactive power, and terminal voltage in real time, and a benchmark value for the excitation current under this operating condition is calculated. By comparing the actual excitation current with the benchmark value, it is determined whether there is an increase in excitation current. If the deviation between the actual measured excitation current and the model's calculated value is within a threshold range, it is considered that the excitation current has not increased significantly, and no further judgment is made. If an increase in excitation current is detected, it is considered that there is a possibility of an inter-turn short circuit. Data on the excitation current and other generator parameters are retrieved, and the correlation coefficients between the other parameters and the excitation current are calculated. Taking into account all the above factors and combining them with an expert diagnostic database, the possibility of an inter-turn short circuit is assessed. Finally, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated.

[0038] The method for diagnosing stator grounding faults involves the following steps: A generator terminal voltage calculation model is established based on data from the generator's terminal voltage, terminal current, active power, and reactive power during normal operation. This model monitors the terminal current, active power, and reactive power in real time, calculating a reference value for the terminal voltage under this operating condition. The actual terminal voltage is compared with the reference value to determine if there is a decrease in terminal voltage. If the deviation between the measured terminal voltage and the calculated value is within a threshold range, it is considered that the terminal voltage has not decreased significantly, and no further judgment is made. If signs of a decrease in terminal voltage are detected, a stator grounding fault is considered possible. Data on the terminal voltage and other generator parameters are retrieved, and the correlation coefficients between each parameter and the terminal voltage are calculated. Taking all these factors into account and combining them with an expert diagnostic database, the possibility of stator grounding is assessed. Finally, the assessment results and the expert diagnostic database are used to generate selectable intelligent maintenance strategies.

[0039] The method for diagnosing stator bar blockage involves the following steps: Based on data from the stator bar outlet water temperature, interlayer temperature, core temperature, generator active power, and generator reactive power during normal generator operation, a stator bar outlet water temperature calculation model is established, establishing the correspondence between these parameters and the stator bar outlet water temperature. This model is used to monitor the interlayer temperature, core temperature, generator active power, and generator reactive power in real time, calculating a baseline value for the stator bar outlet water temperature under this operating condition. The actual stator bar outlet water temperature is then compared to the baseline value to determine if stator bar blockage is present. If the stator bar outlet water temperature increases, and the deviation between the actual measured stator bar outlet water temperature and the model calculation value is within the threshold range, it is considered that the stator bar outlet water temperature has not increased significantly, and no further judgment is made. If signs of increased stator bar outlet water temperature are found, it is considered that there is a possibility of stator bar blockage. Data on stator bar outlet water temperature and other generator parameters are retrieved, and the correlation coefficient between each parameter and stator bar outlet water temperature is calculated. Taking into account the above factors and combining them with the expert diagnostic database, the possibility of stator bar blockage is assessed, and then an intelligent maintenance strategy that can be selected is generated based on the assessment results and the expert diagnostic database.

[0040] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A safety evaluation and diagnostic system for steam turbine generators under deep peak-shaving conditions, characterized in that, This includes a multi-parameter state evaluation model for generators and an intelligent diagnostic model for common generator faults; The generator multi-parameter status evaluation model compares the status information of each parameter of the generator in real time in the DCS system with the corresponding operating standards. The generator multi-parameter status evaluation model performs quantitative analysis and processing on the differences between the status measurement values ​​and standard values ​​of multiple parameters, and evaluates whether the current status of each parameter of the generator is qualified based on the deviation between the status measurement values ​​and standard values. When the state evaluation result of a certain parameter of the generator is unqualified, the intelligent diagnostic model for common generator faults diagnoses and analyzes the cause of the generator abnormality, and establishes a comprehensive analysis model from the two aspects of spatial distribution and time scale to find indicators that can distinguish different types of faults and analyze the cause of the fault. The intelligent diagnostic model for common generator faults combines typical fault cases and expert experience criteria to establish an expert diagnosis database, and derives the corresponding maintenance strategies based on the mapping relationship between various fault types and maintenance strategies. The steam turbine generator safety evaluation and diagnosis system under deep peak shaving conditions performs intelligent diagnosis of rotor winding inter-turn short circuit faults, stator grounding faults, and stator bar blockage. The specific process of the turbine generator safety evaluation and diagnosis system under deep peak shaving conditions for stator grounding faults is as follows: Based on the generator's terminal voltage, terminal current, active power, and reactive power data during normal operation, a generator terminal voltage calculation model is established, establishing the correspondence between terminal current, active power, reactive power, and terminal voltage. This model monitors the terminal current, active power, and reactive power in real time, calculating the reference value of the terminal voltage under this operating condition. By comparing the actual terminal voltage with the reference value, it is determined whether there is a decrease in terminal voltage. If the deviation between the actual measured terminal voltage and the model's calculated value is within a threshold range, it is considered that the terminal voltage has not decreased significantly, and no further judgment is made. If signs of a decrease in terminal voltage are found, it is considered that there is a possibility of stator grounding. Data on the terminal voltage and other generator parameters are retrieved, and the correlation coefficient between each parameter and the terminal voltage is calculated. Taking into account all the above factors and combining them with an expert diagnostic database, the possibility of stator grounding is assessed. Finally, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated. The specific process of stator bar blockage diagnosis by the turbine generator safety evaluation and diagnosis system under deep peak shaving conditions is as follows: Based on data of stator bar outlet water temperature, bar interlayer temperature, core temperature, generator active power, and generator reactive power during normal generator operation, a stator bar outlet water temperature calculation model is established, establishing the correspondence between bar interlayer temperature, core temperature, generator active power, generator reactive power, and stator bar outlet water temperature. Using this model, the interlayer temperature, core temperature, generator active power, and generator reactive power are monitored in real time to calculate the reference value of the stator bar outlet water temperature under this operating condition. The actual stator bar outlet water temperature is then compared with the reference value. The system determines whether there is an increase in stator bar outlet water temperature. If the deviation between the actual measured stator bar outlet water temperature and the model calculation value is within the threshold range, it is considered that the stator bar outlet water temperature has not increased significantly, and no further judgment is made. If signs of an increase in stator bar outlet water temperature are found, it is considered that there is a possibility of stator bar blockage. Data on stator bar outlet water temperature and other generator parameters are retrieved, and the correlation coefficient between each parameter and stator bar outlet water temperature is calculated. Taking into account the above factors and combining them with the expert diagnostic database, the possibility of stator bar blockage is assessed. Then, based on the assessment results and the expert diagnostic database, an intelligent maintenance strategy that can be selected is generated.

2. The system according to claim 1, characterized in that, The specific process of diagnosing inter-turn short circuit faults in the rotor winding of the turbine generator safety evaluation and diagnosis system under deep peak shaving conditions is as follows: Based on the generator active power, generator reactive power, terminal voltage and excitation current data during normal generator operation, a generator excitation current calculation model is established to correspond the generator active power, generator reactive power, terminal voltage and excitation current. Based on the model, the generator active power, generator reactive power and terminal voltage are monitored in real time, and the excitation current reference value under this operating condition is calculated. By comparing the actual excitation current with the reference value, it is determined whether there is an increase in excitation current. If the deviation between the actual measured excitation current and the model calculated value is within the threshold range, it is considered that there is no significant increase in excitation current, and no further judgment is made. If an increase in excitation current is detected, it is considered that there is a possibility of inter-turn short circuit. Data on excitation current and other generator parameters are retrieved, and the correlation coefficients between other parameters and excitation current are calculated. Taking into account all the above factors and combining them with the expert diagnostic database, the possibility of inter-turn short circuit is assessed. Then, based on the assessment results and the expert diagnostic database, an intelligent maintenance strategy that can be selected is generated.

3. A method for safety evaluation and diagnosis of steam turbine generators under deep peak-shaving conditions, characterized in that, Specifically, the real-time status information of various parameters of the generator in the DCS system is compared with the corresponding operating standards. The generator multi-parameter status evaluation model performs quantitative analysis and processing on the differences between the status measurement values ​​and standard values ​​of multiple parameters, and evaluates whether the current status of each parameter of the generator is qualified based on the deviation between the status measurement values ​​and standard values. When the state evaluation result of a certain parameter of the generator is unqualified, the cause of the generator abnormality is diagnosed and analyzed, and a comprehensive analysis model is established from the two aspects of spatial distribution and time scale to find indicators that can distinguish different types of faults and analyze the cause of the fault. The intelligent diagnosis model of common generator faults combines typical fault cases and expert experience criteria to establish an expert diagnosis database. Based on the mapping relationship between various fault types and maintenance strategies, the corresponding maintenance strategies are derived. The method for safety evaluation and diagnosis of steam turbine generator under deep peak shaving conditions can intelligently diagnose rotor winding inter-turn short circuit faults, stator grounding faults and stator bar blockage. The process of diagnosing stator grounding faults using the turbine generator safety evaluation and diagnosis method under deep peak-shaving conditions is as follows: Based on the generator's terminal voltage, terminal current, active power, and reactive power data during normal operation, a generator terminal voltage calculation model is established, establishing the correspondence between terminal current, active power, reactive power, and terminal voltage. This model monitors the terminal current, active power, and reactive power in real time, calculating the reference value of the terminal voltage under this operating condition. By comparing the actual terminal voltage with the reference value, it is determined whether there is a decrease in terminal voltage. If the deviation between the actual measured terminal voltage and the model's calculated value is within a threshold range, it is considered that the terminal voltage has not decreased significantly, and no further judgment is made. If signs of a decrease in terminal voltage are found, it is considered that there is a possibility of stator grounding. Data on the terminal voltage and other generator parameters are retrieved, and the correlation coefficient between each parameter and the terminal voltage is calculated. Taking into account all the above factors and combining them with an expert diagnostic database, the possibility of stator grounding is assessed. Finally, based on the assessment results and the expert diagnostic database, selectable intelligent maintenance strategies are generated. The process of diagnosing stator bar blockage using the turbine generator safety evaluation and diagnosis method under deep peak-shaving conditions is as follows: Based on data of stator bar outlet water temperature, bar interlayer temperature, core temperature, generator active power, and generator reactive power during normal generator operation, a stator bar outlet water temperature calculation model is established, establishing the correspondence between bar interlayer temperature, core temperature, generator active power, generator reactive power, and stator bar outlet water temperature. Using this model, the interlayer temperature, core temperature, generator active power, and generator reactive power are monitored in real time to calculate a reference value for the stator bar outlet water temperature under this operating condition. The actual stator bar outlet water temperature is then compared with the reference value. The system determines whether there is an increase in stator bar outlet water temperature. If the deviation between the actual measured stator bar outlet water temperature and the model calculation value is within the threshold range, it is considered that the stator bar outlet water temperature has not increased significantly, and no further judgment is made. If signs of an increase in stator bar outlet water temperature are found, it is considered that there is a possibility of stator bar blockage. Data on stator bar outlet water temperature and other generator parameters are retrieved, and the correlation coefficient between each parameter and stator bar outlet water temperature is calculated. Taking into account the above factors and combining them with the expert diagnostic database, the possibility of stator bar blockage is assessed. Then, based on the assessment results and the expert diagnostic database, an intelligent maintenance strategy that can be selected is generated.

4. The method according to claim 3, characterized in that, The process of diagnosing inter-turn short circuit faults in the rotor winding of the turbine generator under deep peak shaving conditions is as follows: Based on the generator's active power, reactive power, terminal voltage, and excitation current data during normal operation, a generator excitation current calculation model is established to correspond the generator's active power, reactive power, terminal voltage, and excitation current. Based on this model, the generator's active power, reactive power, and terminal voltage are monitored in real time, and the excitation current reference value under this operating condition is calculated. By comparing the actual excitation current with the reference value, it is determined whether there is an increase in excitation current. If the deviation between the actual measured excitation current and the model calculated value is within the threshold range, it is considered that there is no significant increase in excitation current, and no further judgment is made. If an increase in excitation current is detected, it is considered that there is a possibility of inter-turn short circuit. Data on excitation current and other generator parameters are retrieved, and the correlation coefficients between other parameters and excitation current are calculated. Taking into account all the above factors and combining them with the expert diagnostic database, the possibility of inter-turn short circuit is assessed. Then, based on the assessment results and the expert diagnostic database, an intelligent maintenance strategy that can be selected is generated.

Images