A unit fault diagnosis system for power plants
By designing a power plant unit fault diagnosis system, using unit load and status parameters, obtaining historical and operating data, determining the fault points and degree of faults, the problem of low fault diagnosis efficiency of thermal power units is solved, the diagnosis efficiency and accuracy are improved, and the power is ensured Stability of production.
Patent Information
- Application Number
- CN202311077126.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-24
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2043-08-24
AI Technical Summary
The fault diagnosis efficiency of thermal power units is low, difficult to detect in a timely and comprehensive manner, and there are limitations in determining the degree of fault, which affects the stability of power production.
A power plant unit fault diagnosis system was designed. Through the status determination module, the shutdown state detection module, the operation status detection module, the fault positioning module and the fault determination module, the unit load data and status parameters are used to obtain historical process data and operation data, and determine the Fault points and fault degree to improve fault diagnosis efficiency and accuracy.
The fault diagnosis of key units of the power plant is achieved, the fault diagnosis efficiency and accuracy are improved, and the stability of power production and reasonable allocation of resources are ensured.
Smart Images

Figure CN117310480B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of thermal power unit fault diagnosis, and in particular to a unit fault diagnosis system of a power plant. Background Art
[0002] As the scale of power plants continues to expand, thermal power units are becoming more and more complex. Electricity production requires both stable operation of thermal power units and timely response to grid dispatching plans. Therefore, in actual operation, thermal power units often experience various faults, which in turn affect the stability of power production. Currently, fault diagnosis of thermal power units mainly relies on manual detection. However, thermal power units are large in scale and manual detection is inefficient, making it difficult to achieve timely and comprehensive detection of faults. In addition, there are great limitations in determining the degree of faults of various types.
[0003] Therefore, the present invention provides a unit fault diagnosis system for a power plant. Summary of the invention
[0004] The present invention provides a unit fault diagnosis system for a power plant, which is used to determine the current state of a key unit of the power plant according to unit load data and unit state parameters; obtain historical process data when the key unit is in a shutdown state, and determine whether the key unit is shut down normally; obtain the second operation data of the key unit after receiving an automatic power generation control instruction, and determine whether the key unit is operating normally; obtain the fault point according to the fault data, and determine the fault degree of each fault point; both realize the fault diagnosis of the key unit of the power plant and improve the fault diagnosis efficiency and accuracy.
[0005] The present invention provides a unit fault diagnosis system for a power plant, comprising:
[0006] Status determination module: determines the current status of key units in the power plant based on unit load data and unit status parameters;
[0007] Shutdown status detection module: when it is determined that the key unit is in the shutdown state, the historical process data of the key unit in the shutdown state is obtained, and it is determined whether the key unit is shut down normally;
[0008] Operation status detection module: when it is determined that the key unit is in operation, the control system sends an automatic power generation control instruction to the key unit, obtains the second operation data of the key unit after receiving the automatic power generation control instruction, and determines whether the key unit is operating normally;
[0009] Fault location module: when there is a shutdown fault or operation fault, the fault point is obtained according to the fault data;
[0010] Fault determination module: obtains standard data of each fault point from the fault database according to the fault type of each fault point, and compares and analyzes it with the corresponding fault data to determine the fault degree of each fault point.
[0011] Preferably, the state determination module includes:
[0012] A key unit acquisition unit is used to acquire the continuous power generation of each generator set in the power plant in a specified period of time. When the continuous power generation is greater than the preset power generation and the continuous power generation is stable, the corresponding generator set is determined to be a key unit of the power plant, wherein the generator set is a thermal power unit;
[0013] A state determination unit, used to obtain the current unit load of the key unit and the speed of the steam turbine in the key unit, and when the current unit load is lower than the rated load and the speed of the steam turbine is lower than the rated speed, determine that the corresponding key unit is in a shutdown state;
[0014] Otherwise, it is determined that the corresponding key unit is in operation.
[0015] Preferably, the shutdown state detection module includes:
[0016] A historical process data acquisition unit, used for acquiring historical process data of the key unit in the shutdown state when it is determined that the key unit is in the shutdown state, wherein the historical process data is data of the key unit from the time when the shutdown instruction is received to the time when the shutdown is completed;
[0017] A shutdown state detection unit is used to determine that the corresponding key unit is shut down normally when the historical process data is consistent with the standard shutdown data corresponding to the standard shutdown process;
[0018] Otherwise, it is determined that the corresponding key unit has a shutdown failure.
[0019] Preferably, it also includes: a startup state detection module, including:
[0020] A start-up detection unit is used to obtain a start-up test instruction and perform a start-up operation on the key unit when it is determined that the key unit is normally shut down;
[0021] The startup data of the key unit during the startup operation is obtained. When the startup data is consistent with the standard startup data, it is determined that the corresponding key unit can be started normally.
[0022] Preferably, the running status detection module includes:
[0023] A control instruction unit, configured to issue an automatic power generation control instruction to a key unit according to the control system, and extract a first power generation amount for controlling the key unit based on the automatic power generation control instruction;
[0024] An operation status detection unit, configured to receive an automatic power generation control instruction and a first power generation amount when determining that the key unit is in an operation state or determining that the key unit can be started normally;
[0025] Monitor and obtain the second power generation and second operation data of the key unit during operation, and when the second power generation is consistent with the first power generation and the second operation data is consistent with the standard operation data, determine that the corresponding key unit is operating normally;
[0026] Otherwise, it is determined that the corresponding key unit has an operating failure.
[0027] Preferably, the fault location module includes:
[0028] A fault location unit is used to obtain fault data and standard data adapted to the fault data when it is determined that the corresponding key unit has a fault, and to perform time alignment processing and analysis on the fault data and the adapted standard data, and to locate the time continuous points that exceed the allowable error threshold of the standard data, and regard them as the fault time period;
[0029] Conduct data tracing for fault data during the fault time period and locate the fault point of the corresponding key unit;
[0030] Among them, the same fault point includes several actuators and sensors.
[0031] Preferably, the fault determination module includes:
[0032] The actuator fault determination unit is used to compare and analyze the working data curve of each actuator under the same fault point within the fault time period with the data change curves corresponding to different fault types of the same type of actuators, and obtain the similarities of several curves. When the maximum similarity is greater than the preset similarity, it is determined that the corresponding actuator has a real fault;
[0033] Otherwise, it is determined that the corresponding actuator has a false fault;
[0034] An actuator fault type determination unit is used to sort the curve similarities when determining that a true fault exists in the corresponding actuator, and select the first n0 fault types as the first type of the corresponding actuator according to the fault standard;
[0035] Obtain the historical detection results that are consistent with the first type of each actuator after being grouped, and compare them with the current detection results corresponding to the first type of each actuator. If the comparison accuracy is higher than the preset accuracy, it is determined that the curve similarity calculation is qualified;
[0036] An actuator fault degree determination unit is used to count the number of historical faults of the actuator with real faults, the fault type of each historical fault, and the total number of faults of the actuator involved in the corresponding fault point, and determine the abnormal factor of the corresponding real fault actuator;
[0037] A value extraction unit, used for extracting the maximum value and the minimum value in the corresponding working data curve of each truly faulty actuator;
[0038] Determine a first fault value corresponding to the true fault actuator according to the maximum value, the minimum value, the abnormal factor, and the data variation range when the corresponding true fault actuator does not have a fault;
[0039] A sensor fault determination unit, used to calculate the preset monitoring thresholds of each sensor involved in the same fault point;
[0040] f(x i1 )=λ i1 ×(A1+A2) C1
[0041]
[0042]
[0043]
[0044] Among them, f(x i1 ) is the preset monitoring threshold of the i1th sensor involved in the same fault point; i1 is the characteristic value of the vector constructed by the monitoring value of the i1th sensor involved in the same fault point during the fault period; p i1 is the correct detection fault probability of the i1th sensor obtained from the historical database; n1 is the total number of sensors involved in the same fault point; A1 represents the first statistical detection coefficient; A2 represents the second statistical detection coefficient; C1 represents the detection adjustment coefficient; (A1+A2) C1 represents the detection function; where The value range of is (0,1); The value range of is (0,1);
[0045] A fault value calculation unit, used to compare the monitoring values of each sensor involved in the same fault point with the corresponding preset monitoring threshold value, and determine the second fault value monitored by the corresponding sensor;
[0046] The fault degree determination unit is used to obtain the fault degree of the corresponding fault point according to all the first fault values and the monitored second fault values under the same fault point.
[0047] Preferably, it also includes:
[0048] The stability determination module is used to obtain the number of fault points of the key unit in the current time period, the fault type and degree of each fault point, and the weight of each fault type on the operating stability of the key unit, and calculate the operating stability of the key unit in the current time period;
[0049] A stability comparison module, used for determining that the key unit is unstable in operation and needs to be shut down for maintenance immediately when the operation stability of the key unit in the current time period is lower than the preset operation stability;
[0050] Otherwise, it is determined that the critical unit is running stably, and routine maintenance is performed on the critical unit according to a preset fault maintenance plan.
[0051] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.
[0052] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0054] Figure 1 The present invention is a structural diagram of a unit fault diagnosis system of a power plant in an embodiment of the present invention. DETAILED DESCRIPTION
[0055] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.
[0056] The embodiment of the present invention provides a unit fault diagnosis system for a power plant, such as Figure 1 As shown, including:
[0057] Status determination module: determines the current status of key units in the power plant based on unit load data and unit status parameters;
[0058] Shutdown status detection module: when it is determined that the key unit is in the shutdown state, the historical process data of the key unit in the shutdown state is obtained, and it is determined whether the key unit is shut down normally;
[0059] Operation status detection module: when it is determined that the key unit is in operation, the control system sends an automatic power generation control instruction to the key unit, obtains the second operation data of the key unit after receiving the automatic power generation control instruction, and determines whether the key unit is operating normally;
[0060] Fault location module: when there is a shutdown fault or operation fault, the fault point is obtained according to the fault data;
[0061] Fault determination module: obtains standard data of each fault point from the fault database according to the fault type of each fault point, and compares and analyzes it with the corresponding fault data to determine the fault degree of each fault point.
[0062] In this embodiment, the unit load refers to the output power of the thermal power units of the power plant during the power production process.
[0063] In this embodiment, the unit status includes: shutdown status, startup status and operation status.
[0064] In this embodiment, the key unit of the power plant refers to the thermal power unit that undertakes the key power production task among the thermal power units used for power production in the power plant. At present, the power units of the power plant are mainly thermal power units, among which the structure of the thermal power units includes: boilers, steam turbines, generators and auxiliary equipment.
[0065] In this embodiment, the historical process data refers to the data of the key unit during the process from receiving the shutdown command to the complete shutdown when the key unit is in the shutdown state.
[0066] In this embodiment, the control system refers to a system that controls the thermal power generation unit to complete the power production task within the specified working time and under the specified working conditions.
[0067] In this embodiment, the automatic power generation control instruction refers to the power plant used to adjust the power production of each thermal power unit according to the preset regulation rate based on the power dispatch plan to ensure that the stability and safety of the power system meet the power production target requirements.
[0068] In this embodiment, the second operating data refers to the data of the key unit in the operation process.
[0069] In this embodiment, the fault point refers to the location point where the key unit fails. For example, a fault is detected at location 1 of the generator of the key unit, wherein there are several actuators and sensors at the same fault point.
[0070] In this embodiment, the fault degree refers to the degree of influence of the fault occurring at the fault point on the stability of power production.
[0071] The beneficial effects of the above technical solution are: judging the current status of the key units of the power plant according to the unit load data and the unit status parameters; obtaining the historical process data of the key units when they are in the shutdown state, and judging whether the key units are shut down normally; obtaining the second operation data of the key units after receiving the automatic power generation control instructions, and judging whether the key units are operating normally; obtaining the fault points according to the fault data, and judging the fault degree of each fault point, which not only realizes the fault diagnosis of the key units of the power plant, but also improves the fault diagnosis efficiency and accuracy.
[0072] The embodiment of the present invention provides a unit fault diagnosis system of a power plant, a state determination module, including:
[0073] A key unit acquisition unit is used to acquire the continuous power generation of each generator set in the power plant in a specified period of time. When the continuous power generation is greater than the preset power generation and the continuous power generation is stable, the corresponding generator set is determined to be a key unit of the power plant, wherein the generator set is a thermal power unit;
[0074] A state determination unit, used to obtain the current unit load of the key unit and the speed of the steam turbine in the key unit, and when the current unit load is lower than the rated load and the speed of the steam turbine is lower than the rated speed, determine that the corresponding key unit is in a shutdown state;
[0075] Otherwise, it is determined that the corresponding key unit is in operation.
[0076] In this embodiment, the key units of the power plant, for example, the preset power generation of each thermal power unit is 5, and the continuous power generation of a thermal power unit a1 is 10 and the continuous power generation is stable, then the thermal power unit a1 is determined to be the key unit of the power plant.
[0077] In this embodiment, the key units of the power plant undertake most of the power production tasks, and the power production of the key units is stable.
[0078] In this embodiment, it is determined that the corresponding key unit is in a shutdown state. For example, for the key unit A1, it is obtained that the current unit load is 3, the turbine speed is 10, the rated load is 5, and the rated speed is 15, then it is determined that the key unit A1 is in a shutdown state.
[0079] The beneficial effects of the above technical solution are: determining the key units of the power plant is conducive to the reasonable allocation of resources for fault diagnosis, improving resource allocation to key units, and ensuring the stability of power production; determining the status of key units is conducive to improving the efficiency and accuracy of fault diagnosis.
[0080] The embodiment of the present invention provides a unit fault diagnosis system of a power plant, a shutdown state detection module, including:
[0081] A historical process data acquisition unit, used for acquiring historical process data of the key unit in the shutdown state when it is determined that the key unit is in the shutdown state, wherein the historical process data is data of the key unit from the time when the shutdown instruction is received to the time when the shutdown is completed;
[0082] A shutdown state detection unit is used to determine that the corresponding key unit is shut down normally when the historical process data is consistent with the standard shutdown data corresponding to the standard shutdown process;
[0083] Otherwise, it is determined that the corresponding key unit has a shutdown failure.
[0084] In this embodiment, standard shutdown data, for example, during the shutdown process of the key unit, keeps the main steam parameters unchanged, adjusts the throttle through the control system within the specified time, controls the drop rate of the turbine metal temperature of the key unit to be within the rated drop rate, and reduces the unit load to 0.
[0085] In this embodiment, when the historical process data is consistent with the standard shutdown data, it is determined that the critical unit is shut down normally.
[0086] The beneficial effect of the above technical solution is that by obtaining historical process data, it is determined whether there is a shutdown fault for the key unit, which is conducive to the subsequent positioning of the fault point, determination of the fault type and determination of the fault degree, and the efficiency of fault diagnosis is improved.
[0087] The embodiment of the present invention provides a unit fault diagnosis system for a power plant, further comprising: a startup state detection module, including:
[0088] A start-up detection unit is used to obtain a start-up test instruction and perform a start-up operation on the key unit when it is determined that the key unit is normally shut down;
[0089] The startup data of the key unit during the startup operation is obtained. When the startup data is consistent with the standard startup data, it is determined that the corresponding key unit can be started normally.
[0090] In this embodiment, the startup test instruction refers to an instruction to start the key unit after it is determined that the key unit is shut down normally, which is used to test whether the key unit can be started normally after it is shut down normally. For example, if the key unit A1 is determined to be shut down normally, the corresponding startup test instruction is obtained to execute the startup operation.
[0091] In this embodiment, the standard startup data refers to the data of the key unit from the shutdown state to the operating state, for example, the process data of the steam turbine in the key unit from the speed of 0 to the rated speed and the unit load from 0 to the rated load.
[0092] In this embodiment, when it is determined that a shutdown fault exists in a critical unit, the shutdown fault is detected and diagnosed, and after the shutdown fault detection and repair is completed, a startup operation is performed to avoid a larger failure of the critical unit caused by direct startup testing due to the presence of a shutdown fault.
[0093] In this embodiment, the startup operation and the precautions for the startup process are obtained based on the historical startup database.
[0094] The beneficial effect of the above technical solution is: by executing the startup operation on the key unit, it is determined whether the key unit can be started normally, and further fault diagnosis is performed on the key unit, ensuring that the key unit starts normally and improving the location analysis of subsequent fault data.
[0095] The embodiment of the present invention provides a unit fault diagnosis system of a power plant, an operation status detection module, including:
[0096] A control instruction unit, configured to issue an automatic power generation control instruction to a key unit according to the control system, and extract a first power generation amount for controlling the key unit based on the automatic power generation control instruction;
[0097] An operation status detection unit, configured to receive an automatic power generation control instruction and a first power generation amount when determining that the key unit is in an operation state or determining that the key unit can be started normally;
[0098] Monitor and obtain the second power generation and second operation data of the key unit during operation, and when the second power generation is consistent with the first power generation and the second operation data is consistent with the standard operation data, determine that the corresponding key unit is operating normally;
[0099] Otherwise, it is determined that the corresponding key unit has an operating failure.
[0100] In this embodiment, an automatic power generation control instruction is issued to the key unit according to the control system. For example, an automatic power generation control instruction is issued to the key unit A1 according to the control system to adjust the power production of the key unit A1 to 10.
[0101] In this embodiment, the first power generation refers to the power generation of the key unit extracted from the automatic power generation control instruction, that is, the preset power generation of the key unit after the grid scheduling planning. For example, the first power generation of the key unit A1 is extracted to be 10.
[0102] In this embodiment, the second power generation refers to the actual power generation of the corresponding key unit during the actual operation process. For example, the second power generation of the key unit A1 obtained through actual monitoring is 10. At the same time, the second operating data is consistent with the standard operating data, then it is determined that the key unit A1 is operating normally.
[0103] In this embodiment, the standard operation data refers to the unit load data and turbine speed data during the normal operation of the key units.
[0104] In this embodiment, the fault types of the key units under different unit states are inconsistent.
[0105] The beneficial effect of the above technical solution is: according to the control system, automatic power generation control instructions are issued to the key units to determine whether the corresponding key units are operating normally, which is conducive to effective fault diagnosis for operating faults, improves fault diagnosis efficiency and accuracy, and ensures the operating stability of the key units of the power plant.
[0106] The embodiment of the present invention provides a unit fault diagnosis system of a power plant, a fault location module, including:
[0107] A fault location unit is used to obtain fault data and standard data adapted to the fault data when it is determined that the corresponding key unit has a fault, and to perform time alignment processing and analysis on the fault data and the adapted standard data, and to locate the time continuous points that exceed the allowable error threshold of the standard data, and regard them as the fault time period;
[0108] Conduct data tracing for fault data during the fault time period and locate the fault point of the corresponding key unit;
[0109] Among them, the same fault point includes several actuators and sensors.
[0110] In this embodiment, the fault time period refers to the time period obtained by time alignment processing and analysis based on the fault data and the corresponding adapted standard data. For example, the fault data b1 of the key unit A1 is processed and analyzed to obtain the fault start time c1 and the fault end time c2, then the time period c1c2 is the fault time period of the key unit A1.
[0111] In this embodiment, the fault point refers to the location point where the fault occurs that is located by tracing the fault data in the fault time period. For example, by tracing the fault data b1 in the time period c1c2, the fault point D1 is located, that is, it is determined that a fault occurs at position D1 and fault diagnosis needs to be performed.
[0112] In this embodiment, the actuator refers to a machine in a key unit that is used to execute various control instructions and drive the key unit to perform stop and start operations. For example, during the startup process, when it is monitored that the unit load reaches the rated load, the actuator is used to control the unit load to remain stable.
[0113] In this embodiment, the sensor refers to a machine used by the key unit to monitor various condition parameters of the working process, for example, monitoring the temperature, rotation speed and unit load of the key unit under various unit states.
[0114] In this embodiment, the fault point fault includes sensor fault and actuator fault.
[0115] The beneficial effect of the above technical solution is: by time-aligning the fault data with the adapted standard data for processing and analysis, the fault point of the key unit is located, which is conducive to specific analysis and diagnosis of the faults of each fault point based on the historical database, thereby improving the fault detection efficiency and fault detection accuracy.
[0116] The embodiment of the present invention provides a unit fault diagnosis system of a power plant, and a fault determination module, including:
[0117] The actuator fault determination unit is used to compare and analyze the working data curve of each actuator under the same fault point within the fault time period with the data change curves corresponding to different fault types of the same type of actuators, and obtain the similarities of several curves. When the maximum similarity is greater than the preset similarity, it is determined that the corresponding actuator has a real fault;
[0118] Otherwise, it is determined that the corresponding actuator has a false fault;
[0119] An actuator fault type determination unit is used to sort the curve similarities when determining that a true fault exists in the corresponding actuator, and select the first n0 fault types as the first type of the corresponding actuator according to the fault standard;
[0120] Obtain the historical detection results that are consistent with the first type of each actuator after being grouped, and compare them with the current detection results corresponding to the first type of each actuator. If the comparison accuracy is higher than the preset accuracy, it is determined that the curve similarity calculation is qualified;
[0121] An actuator fault degree determination unit is used to count the number of historical faults of the actuator with real faults, the fault type of each historical fault, and the total number of faults of the actuator involved in the corresponding fault point, and determine the abnormal factor of the corresponding real fault actuator;
[0122] A value extraction unit, used for extracting the maximum value and the minimum value in the corresponding working data curve of each truly faulty actuator;
[0123] Determine a first fault value corresponding to the true fault actuator according to the maximum value, the minimum value, the abnormal factor, and the data variation range when the corresponding true fault actuator does not have a fault;
[0124] A sensor fault determination unit, used to calculate the preset monitoring thresholds of each sensor involved in the same fault point;
[0125] f(x i1 )=λ i1 ×(A1+A2)C1
[0126]
[0127]
[0128]
[0129] Among them, f(x i1 ) is the preset monitoring threshold of the i1th sensor involved in the same fault point; i1 is the characteristic value of the vector constructed by the monitoring value of the i1th sensor involved in the same fault point during the fault period; p i1 is the correct detection fault probability of the i1th sensor obtained from the historical database; n1 is the total number of sensors involved in the same fault point; A1 represents the first statistical detection coefficient; A2 represents the second statistical detection coefficient; C1 represents the detection adjustment coefficient; (A1+A2) C1 represents the detection function; where The value range of is (0,1); The value range of is (0,1);
[0130] A fault value calculation unit, used to compare the monitoring values of each sensor involved in the same fault point with the corresponding preset monitoring threshold value, and determine the second fault value monitored by the corresponding sensor;
[0131] The fault degree determination unit is used to obtain the fault degree of the corresponding fault point according to all the first fault values and the monitored second fault values under the same fault point.
[0132] In this embodiment, the working data curve of each actuator in the fault time period refers to the fault output data curve of the actuator in the fault time period. For example, the working data curve 1 of the actuator a1 in the fault time period is a horizontal curve.
[0133] In this embodiment, the data change curves corresponding to different fault types of the same type of actuator are inconsistent. For example, the actuator fault types can generally be a stuck fault, a dead zone fault, a deviation fault, a gain fault, and a stick-slip fault, and the data change curves caused by each fault type are inconsistent.
[0134] In this embodiment, comparative analysis is performed to obtain several curve similarities. For example, the data change curves e1, e2 and e3 corresponding to different fault types of actuator a1, and the curve similarities obtained by comparative analysis of working data curve 1 are 0.7, 0.9 and 0.4 respectively.
[0135] In this embodiment, when the maximum similarity is greater than the preset similarity, it is determined that the corresponding actuator has a true fault. For example, if the preset similarity is 0.8 and the maximum similarity of actuator a1 is 0.9, it is determined that actuator a1 has a true fault.
[0136] In this embodiment, a true fault means that the corresponding actuator itself has a fault; a false fault means that the corresponding actuator itself does not have a fault and only requires routine maintenance.
[0137] In this embodiment, the first type refers to the fault type obtained after the actuator is screened according to the fault standard. For example, if the fault standard is that the curve similarity is greater than 0.6, the first type of actuator a1 is the fault type corresponding to the data change curves e1 and e2.
[0138] In this embodiment, when the calculation of the determination curve similarity is qualified, the first type of the actuator is detected correctly, that is, the first type of the actuator is determined.
[0139] In this embodiment, the abnormal factor corresponding to the truly faulty actuator is determined according to the corresponding number of historical faults, the corresponding fault type, and the total number of faults of the actuator involved in the corresponding fault point, and is used to reflect the fault frequency of the actuator.
[0140] In this embodiment, the first fault value refers to the fault degree of the actuator. The higher the first fault value is, the higher the fault degree of the first type of the corresponding actuator is.
[0141] In this embodiment, the preset monitoring threshold of each sensor refers to the value at which the sensor failure can be detected when the sensor fails. For example, the preset monitoring threshold of the sensor is 3. When the monitoring value of the corresponding sensor is 2, the sensor failure cannot be detected, that is, it is determined that the sensor has not failed.
[0142] In this embodiment, the second fault value refers to the fault degree of the sensor.
[0143] In this embodiment, the fault degree of the fault point refers to the sum of all first fault values and second fault values under the same fault point. For example, the first fault values of fault point 1 are 0.02, 0.04 and 0.01, and the second fault value is 0.05, then the fault degree of the fault point is 0.12.
[0144] The beneficial effects of the above technical solution are: by analyzing the faults of the sensors and actuators at the fault points, determining the fault type and the corresponding fault degree, rationally utilizing historical data, achieving effective detection and diagnosis of key unit faults, improving the reliability of key unit actuators and sensors, and ensuring key unit power production.
[0145] An embodiment of the present invention provides a unit fault diagnosis system for a power plant, further comprising:
[0146] The stability determination module is used to obtain the number of fault points of the key unit in the current time period, the fault type and degree of each fault point, and the weight of each fault type on the operating stability of the key unit, and calculate the operating stability of the key unit in the current time period;
[0147] A stability comparison module, used for determining that the key unit is unstable in operation and needs to be shut down for maintenance immediately when the operation stability of the key unit in the current time period is lower than the preset operation stability;
[0148] Otherwise, it is determined that the critical unit is running stably, and routine maintenance is performed on the critical unit according to a preset fault maintenance plan.
[0149] In this embodiment, operational stability refers to the power production of the key unit in the current time period. All kinds of failures of the key unit will have a certain impact on power production. For example, the power production of the key unit A2 in the current time period is stable at 10, with a fluctuation of 0.2.
[0150] In this embodiment, the preset operation stability refers to the acceptable range of power fluctuations during the power production operation. For example, if the power production fluctuates up and down by 0.5, it is considered that the power production meets the preset operation stability.
[0151] In this embodiment, the machine is shut down for maintenance. For example, if the power production of the key unit A3 fluctuates by 1.0, the operating stability of the key unit A3 is lower than the preset operating stability and needs to be shut down for maintenance immediately.
[0152] In this embodiment, routine maintenance, for example, the power production of the key unit A2 fluctuates by 0.2, and the operating stability of the key unit A2 is higher than the preset operating stability, and routine maintenance is sufficient.
[0153] In this embodiment, the shutdown maintenance plan and the daily maintenance plan are obtained based on the historical maintenance database.
[0154] The beneficial effect of the above technical solution is: by calculating the operating stability of the key units in the current time period, it is determined whether the key units need to be shut down for maintenance and daily maintenance, which is conducive to the rational allocation of power plant resources, and at the same time effectively ensures the stability of the power plant's power production and the quality of power production.
[0155] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A unit fault diagnosis system for a power plant, characterized in that: include: Status determination module: determines the current status of key units in the power plant based on unit load data and unit status parameters; Shutdown status detection module: when it is determined that the key unit is in the shutdown state, the historical process data of the key unit in the shutdown state is obtained, and it is determined whether the key unit is shut down normally; Operation status detection module: when it is determined that the key unit is in operation, the control system sends an automatic power generation control instruction to the key unit, obtains the second operation data of the key unit after receiving the automatic power generation control instruction, and determines whether the key unit is operating normally; Fault location module: when there is a shutdown fault or operation fault, the fault point is obtained according to the fault data; Fault determination module: obtains standard data of each fault point from the fault database according to the fault type of each fault point, and compares and analyzes it with the corresponding fault data to determine the fault degree of each fault point; Fault location module, including: A fault location unit is used to obtain fault data and standard data adapted to the fault data when it is determined that the corresponding key unit has a fault, and to perform time alignment processing and analysis on the fault data and the adapted standard data, and to locate the time continuous points that exceed the allowable error threshold of the standard data, and regard them as the fault time period; Conduct data tracing for fault data during the fault time period and locate the fault point of the corresponding key unit; Among them, the same fault point includes several actuators and sensors; The fault determination module comprises: The actuator fault determination unit is used to compare and analyze the working data curve of each actuator under the same fault point within the fault time period with the data change curves corresponding to different fault types of the same type of actuators, and obtain the similarities of several curves. When the maximum similarity is greater than the preset similarity, it is determined that the corresponding actuator has a real fault; Otherwise, it is determined that the corresponding actuator has a false fault; The actuator fault type determination unit is used to sort the curve similarities when determining that the corresponding actuator has a true fault, and screen the previous The fault type is taken as the first type of the corresponding actuator; Obtain the historical detection results that are consistent with the first type of each actuator after being grouped, and compare them with the current detection results corresponding to the first type of each actuator. If the comparison accuracy is higher than the preset accuracy, it is determined that the curve similarity calculation is qualified; An actuator fault degree determination unit is used to count the number of historical faults of the actuator with real faults, the fault type of each historical fault, and the total number of faults of the actuator involved in the corresponding fault point, and determine the abnormal factor of the corresponding real fault actuator; A value extraction unit, used for extracting the maximum value and the minimum value in the corresponding working data curve of each truly faulty actuator; Determine a first fault value corresponding to the true fault actuator according to the maximum value, the minimum value, the abnormal factor, and the data variation range when the corresponding true fault actuator does not have a fault; A sensor fault determination unit, used to calculate the preset monitoring thresholds of each sensor involved in the same fault point; in, The first Preset monitoring thresholds for each sensor; The first The characteristic value of the vector constructed by the monitoring values of the sensors during the fault period; The first The probability of correctly detecting a fault for each sensor; is the total number of sensors involved in the same fault point; represents the first statistical detection coefficient; represents the second statistical detection coefficient; represents the detection adjustment coefficient; represents the detection function; where The value range is ; The value range is ; A fault value calculation unit, used to compare the monitoring values of each sensor involved in the same fault point with the corresponding preset monitoring threshold value, and determine the second fault value monitored by the corresponding sensor; The fault degree determination unit is used to obtain the fault degree of the corresponding fault point according to all the first fault values and the monitored second fault values under the same fault point.
2. A unit fault diagnosis system for a power plant as claimed in claim 1, characterized in that: The state determination module includes: A key unit acquisition unit is used to acquire the continuous power generation of each generator set in the power plant in a specified period of time. When the continuous power generation is greater than the preset power generation and the continuous power generation is stable, the corresponding generator set is determined to be a key unit of the power plant, wherein the generator set is a thermal power unit; A state determination unit, used to obtain the current unit load of the key unit and the speed of the steam turbine in the key unit, and when the current unit load is lower than the rated load and the speed of the steam turbine is lower than the rated speed, determine that the corresponding key unit is in a shutdown state; Otherwise, it is determined that the corresponding key unit is in operation.
3. A unit fault diagnosis system for a power plant as claimed in claim 1, characterized in that: The shutdown state detection module includes: A historical process data acquisition unit, used for acquiring historical process data of the key unit in the shutdown state when it is determined that the key unit is in the shutdown state, wherein the historical process data is data of the key unit from the time when the shutdown instruction is received to the time when the shutdown is completed; A shutdown state detection unit is used to determine that the corresponding key unit is shut down normally when the historical process data is consistent with the standard shutdown data corresponding to the standard shutdown process; Otherwise, it is determined that the corresponding key unit has a shutdown failure.
4. A unit fault diagnosis system for a power plant as claimed in claim 1, characterized in that: Also includes: The startup status detection module includes: A start-up detection unit is used to obtain a start-up test instruction and perform a start-up operation on the key unit when it is determined that the key unit is normally shut down; The startup data of the key unit during the startup operation is obtained. When the startup data is consistent with the standard startup data, it is determined that the corresponding key unit can be started normally.
5. A unit fault diagnosis system for a power plant as claimed in claim 1, characterized in that: Running status detection module, including: A control instruction unit, configured to issue an automatic power generation control instruction to a key unit according to the control system, and extract a first power generation amount for controlling the key unit based on the automatic power generation control instruction; An operation status detection unit, configured to receive an automatic power generation control instruction and a first power generation amount when determining that the key unit is in an operation state or determining that the key unit can be started normally; Monitor and obtain the second power generation and second operation data of the key unit during operation, and when the second power generation is consistent with the first power generation and the second operation data is consistent with the standard operation data, determine that the corresponding key unit is operating normally; Otherwise, it is determined that the corresponding key unit has an operating failure.
6. A unit fault diagnosis system for a power plant as claimed in claim 1, characterized in that: Also includes: The stability determination module is used to obtain the number of fault points of the key unit in the current time period, the fault type and degree of each fault point, and the weight of each fault type on the operating stability of the key unit, and calculate the operating stability of the key unit in the current time period; A stability comparison module, used for determining that the key unit is unstable in operation and needs to be shut down for maintenance immediately when the operation stability of the key unit in the current time period is lower than the preset operation stability; Otherwise, it is determined that the critical unit is running stably, and routine maintenance is performed on the critical unit according to a preset fault maintenance plan.
