Fault prediction method and device for cooling system of steam turbine generator

Abstract

The invention relates to a turbine generator cooling system fault prediction method and device. The method comprises the steps that historical fault events and operation data of a turbine generator are acquired; the historical fault events are screened, and the fault events of the target equipment are reserved; fault cause analysis and classification are carried out on the screened fault events; according to the classified fault events, analyzing different fault operation data change conditions; performing logic association on different fault events and operation data change conditions in a fault tree form; performing logic setting on the distributed control system of the steam turbine generator according to the fault tree; and comparing the operation data with complete evolution characteristics of a fault tree preset in the distributed control system to realize fault prediction or positioning. According to the method, when the steam turbine generator operates normally or has a fault, fault prediction can be carried out on the cooling system or the existing fault can be positioned in time by analyzing the operation data, so that the fault prediction timeliness and prediction accuracy are improved.

Description

Technical Field

[0001] The present application relates to the field of electric power safety technology, and in particular to a method and device for predicting faults in a steam turbine generator cooling system. Background Art

[0002] Large steam turbine generators are key power generation equipment in coal-fired thermal power plants. Currently, most steam turbine generators use a "water-hydrogen-hydrogen" cooling method to remove the heat generated during operation, that is, cooling water is responsible for removing the heat generated by the stator coil, and hydrogen is responsible for removing the heat generated by the rotor coil and the stator core. Among them, the stator cooling water system of the generator must not only ensure that the cooling water flows through the stator coil uninterruptedly, but also control the pressure, temperature, flow rate, conductivity and pH value of the cooling medium when it enters the stator coil to meet the operating regulations, thereby ensuring the normal operation of the generator. However, due to the large number of pipes, valves and other structures involved in the system and the high requirements for the water quality of cooling water, the system often fails frequently in the daily production and operation of thermal power plants. In order to reduce the losses caused by unplanned downtime due to stator cooling water system failures, it is necessary to conduct timely fault prediction of the stator cooling water system of the steam turbine generator.

[0003] However, the current monitoring method for the turbine generator cooling system is to monitor a single parameter in the system in real time, such as conductivity, flow rate, and temperature, through the measurement points installed on the generator and pipeline. However, in the stator cooling water system, the impact between the fault and the system parameters is not single, and multiple parameters are often abnormal at the same time, which also makes it difficult to prevent the stator cooling water system before the fault occurs, the hiddenness of the fault is high, the harm after the fault occurs is greater, and the difficulty of troubleshooting is high. Summary of the invention

[0004] In order to overcome the above-mentioned deficiencies of the prior art, the present application provides a method and device for predicting faults in a turbine generator cooling system, which specifically adopts the following technical solutions: A method for predicting faults in a turbine generator cooling system, the method comprising the following steps: Obtain historical fault events of the steam turbine generator and the operating data of each device when the corresponding fault event occurs; Filter historical fault events and retain the fault events of the target device and the operating data of the corresponding device; Analyze the causes of the faults after screening and classify them according to the causes; According to the classified fault events, analyze the changes in operating data of different fault events in the early, middle and late stages; Use the fault tree form to logically associate different fault events and the changes in the operating data of the corresponding fault events in different periods to obtain the complete evolution characteristics of different fault events; According to the fault tree, the distributed control system of the steam turbine generator is logically set up so that the distributed control system can obtain the operating data of the equipment associated with different fault events respectively; The operating data of each device in the steam turbine generator is obtained in real time, and the operating data is compared with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault prediction or location.

[0005] Optionally, the step of logically associating the fault data and the changes in the equipment operation data at different fault occurrence periods in the form of a fault tree to obtain the complete evolution characteristics of different fault events includes: Obtain each fault event and the operating data associated with the corresponding fault event; According to the fault events and corresponding operation data analysis, the top events, intermediate events and basic events of different fault events are obtained; The top event is used as the top of the fault tree and the intermediate events and basic events are arranged in descending order according to the hierarchy. The top event, intermediate events and basic events of different fault events are connected by logic gates to form a fault tree; wherein the structure of the fault tree is: ; in The status of the turbine generator cooling system; is the state of each basic event; n is the number of basic events; The fault tree analysis obtains the complete evolution path of different fault events starting from the bottom event, passing through the intermediate events and leading to the top event, as well as the change characteristics of the operating data.

[0006] Optional: When performing logical association, use the descending algorithm to determine the minimum cut set of the fault tree: Starting from the top event of the fault tree, each step replaces the previous level event with the next level event from top to bottom; When replacing the upper and lower level events, write the AND gate events horizontally in parallel and the OR gate events vertically in series until all logic gates are replaced by the basic event matrix, where each row of the basic event matrix represents a cut set; The minimum cut set of the fault tree is obtained according to the basic event matrix, wherein the top event in the fault tree is represented as: ; in T is the top event of the fault tree; A j The fault tree jan intermediate event; X k The first k Minimal cut sets; m is the number of intermediate events; s is the minimum number of cut sets.

[0007] Optionally, the step of logically setting the distributed control system of the steam turbine generator according to the fault tree so that the distributed control system respectively obtains the operating data of the equipment associated with different fault events includes: Analyze the top event, intermediate event and specific equipment associated with basic event of each fault event based on the fault tree; Optimize the architecture of the distributed control system based on the correspondence between each event and specific equipment in each fault event; Data acquisition logic is written for the distributed control system according to the logical relationship of the fault tree; when the device corresponding to a basic event detects abnormal data, the distributed control system is enabled to quickly acquire the operating data of other devices related to the current data logic through the data acquisition logic.

[0008] Optionally, the step of comparing the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault prediction includes: Obtain real-time operating data of different equipment of the steam turbine generator respectively; Analyze whether the changing trend of the real-time collected operation data conforms to the complete evolution characteristics of a certain fault event in the fault tree; When the change trend of one or more equipment operation data meets the complete evolution characteristics of a fault event in the fault tree, it is determined that the steam turbine generator has the risk of the corresponding fault; When the change trend of the equipment operation data collected in real time does not conform to the complete evolution characteristics of a fault event in the fault tree, the operation data record is kept.

[0009] Optionally: an early warning interface is provided in the distributed control system of the steam turbine generator, and the early warning interface is used to display fault prediction results.

[0010] Optionally, the step of comparing the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault location includes: Obtain the operating data recorded by the distributed control system when the fault occurs; Analyze whether the change trend of the operating data of each device when the fault occurs conforms to the complete evolution characteristics of a fault event in the fault tree; When the change trend of one or more equipment operation data meets the complete evolution characteristics of a fault event in the fault tree, the corresponding fault is determined to be the fault event of the current steam turbine generator, and the alarm is located according to the fault cause of the corresponding fault event; When the change trend of the operating data of each device does not conform to the complete evolution characteristics of a fault event in the fault tree, the current fault event is determined to be an unrecorded fault event, and the corresponding operating data is added to the fault tree of the distributed control system.

[0011] Optionally: An alarm interface is provided in the distributed control system of the steam turbine generator, and the alarm interface is used to display the fault location result.

[0012] Optional: The causes of the failure include at least human error, equipment aging, poor quality, and improper operation.

[0013] In addition, the present application also discloses a fault prediction device for a steam turbine generator cooling system, the device comprising: A data acquisition module is used to acquire historical fault events of the steam turbine generator and the operating data of each device when the corresponding fault event occurs; Data screening module, used to screen historical fault events and retain the fault events of target devices and the operating data of corresponding devices; The fault classification module is used to analyze the causes of the fault events after screening and classify them according to the causes of the faults; The fault analysis module is used to analyze the changes in operating data of different fault events in the early, middle and late stages according to the classified fault events; The feature evolution module is used to logically associate different fault events and the changes in the operating data of the corresponding fault events in different periods in the form of a fault tree to obtain the complete evolution features of different fault events; The logic download module is used to perform logic settings on the distributed control system of the steam turbine generator according to the fault tree, so that the distributed control system can obtain the operating data of the equipment associated with different fault events respectively; The fault output module is used to obtain the operating data of each device in the steam turbine generator in real time, and compare the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault prediction or location.

[0014] Furthermore, the present application also discloses an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any one of the above items.

[0015] Beneficial Effects The technical solution of this application has the following beneficial effects: (1) The turbine generator cooling system fault prediction method of the present application can timely predict the fault of the cooling system or locate the existing fault by analyzing the operating data collected by the distributed control system (DCS) when the turbine generator is operating normally or a fault occurs, thereby improving the timeliness of fault prediction. In addition, the method can comprehensively consider all operating data that affect the fault, accurately obtain the fault prediction result, and improve the prediction accuracy.

[0016] (2) The turbine generator cooling system fault prediction method of the present application downloads the fault tree logic into the DCS, which can continuously monitor and alarm the system operation status; and the prediction results or alarm results can be directly reflected in the DCS screen, which is convenient for operation and maintenance personnel to promptly discover potential hidden dangers of the system.

[0017] (3) The turbine generator cooling system fault prediction method of the present application is based on a logical analysis of cooling system fault instances collected historically, so that the resulting fault tree can better adapt to the cooling system failure mechanism of most coal-fired power units, with good versatility and high reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Flow chart of a method for predicting faults in a turbine generator cooling system in an embodiment of the present application.

[0019] Figure 2 This is a historical fault collection table of the steam turbine generator system of a coal-fired power plant in the embodiment of the present application.

[0020] Figure 3 It is a logical association diagram of fault events and operating data changes in the form of a fault tree in the embodiment of the present application.

[0021] Figure 4 It is a logical association diagram of the fault tree represented by parameter symbols in the embodiment of the present application.

[0022] Figure 5 This is a complete evolution characteristic diagram of different fault events in the embodiments of the present application.

[0023] Figure 6 1 is a structural diagram of a fault prediction device for a steam turbine generator cooling system in an embodiment of the present application.

[0024] Figure 7 This is a structural diagram of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The present application is further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application, and cannot be used to limit the scope of protection of the present application. It should be noted that the following detailed descriptions are all exemplary and are intended to provide further explanation of the present application.

[0026] Combination Figure 1 As shown, the embodiment of the present application discloses a method for predicting faults of a turbine generator cooling system, the method comprising the following steps: Step S1: Obtain historical fault events of the steam turbine generator and the operating data of each device when the corresponding fault event occurs; for example, this embodiment collects and summarizes the faults occurring in the steam turbine generator system of the current coal-fired thermal power plant based on nearly a thousand fault cases in the power plant accident case compilation, such as Figure 2 shown.

[0027] Step S2: Filter historical fault events and retain the fault events of the target device and the operation data of the corresponding device; Figure 2 The faults collected in the system are screened, the faults related to the generator stator cooling water system are retained, and the faults of other systems are deleted, as shown in Table 1.

[0028] Table 1 Step S3: Analyze the causes of the faults after screening, and classify them according to the causes of the faults; the causes of the faults in step S3 at least include human factors, equipment aging, poor quality, and improper operation. Based on the fault list after screening in Table 1, this embodiment classifies the causes of the faults into human factors, equipment aging, poor quality, improper operation, etc., as shown in Table 2.

[0029] Table 2 Step S4: Analyze the changes in the operating data of different fault events at the early, middle and late stages according to the classified fault events; Step S5: logically associate different fault events and the changes in the operating data of the corresponding fault events in different periods in the form of a fault tree to obtain the complete evolution characteristics of different fault events; Specifically, the specific steps of logically associating different fault events and the changes in the operation data of the corresponding fault events at different periods in step S5 include: Obtain each fault event and the operating data associated with the corresponding fault event; for example, for a stator cooling water system fault in a steam turbine generator, the operating data that may be collected include the change values ​​of flow, pressure, conductivity, temperature, pressure difference and other parameters in the stator cooling water system before, during and after the fault occurs.

[0030] According to the fault events and the corresponding operation data analysis, the top events, intermediate events and basic events of different fault events are obtained; for example, for the stator cooling water system failure in the steam turbine generator, the stator cooling water system failure can be regarded as a top event, and the intermediate events may be water pressure failure, flow failure, etc.; the basic events may be the inability of the solenoid valve to replenish water, leakage in the water circuit, high cooler pressure, etc. At the same time, combined with the changes in equipment operation data at different times when the fault occurs, the conditions and sequence of occurrence of each event are judged. For example, if the water tank level continues to drop abnormally before the fault occurs, it may be an important factor leading to the intermediate event of cooling water pressure failure.

[0031] With the top event as the top of the fault tree and the rules of arranging the intermediate events and basic events in descending order according to the hierarchy, the top events, intermediate events and basic events of different fault events are connected by logic gates to form a fault tree. In the embodiments of the present application, logic gates such as "AND" and "OR" are generally used to describe the logical relationship between the top event, the intermediate event and the basic event. For example, if the intermediate event will only occur when multiple basic events occur at the same time, then the top event and the multiple basic events are in an "AND" logical relationship; if any one of the multiple basic events occurs, the intermediate event will occur, then the top event and the multiple basic events are in an "OR" logical relationship.

[0032] This embodiment takes the failure of the cooling system of a steam turbine generator as an example, and based on the classified fault list in Table 2, statistics are made on the changes of various parameters in the stator cooling water system when each fault occurs, such as: in a copper oxide corrosion fault in a power plant, the flow rate continues to decrease, and increasing the cooling water pressure still cannot maintain the flow rate, and the maximum temperature difference between the wire rod layers gradually increases over time; in a hydrogen leakage fault in a power plant, the pH value decreases and the conductivity fluctuates. After replacing the drugs in the stator cooling water optimization device, the pH value still decreases, and the exhaust volume of the stator cooling water tank is too high; in a wire rod blockage fault in a power plant, the outlet water temperature difference is high for a long time, the temperature difference gradually increases under rated load, and the outlet water temperature of some wire rods increases significantly with the increase of load; in a local blockage fault in a power plant, The temperature and temperature difference of some windings are too high, the cooling water flow and pressure are normal, and the temperature of the wire rod changes with the load; in the tripping failure of a certain power plant unit, there is a sudden increase in the conductivity and pH value of the cooling water in the generator, which continues to exceed the standard for 23 minutes and then slowly decreases, and the stator grounding alarm occurs; the above changes are counted and a fault tree model is constructed for the steam turbine generator cooling system. The specific process is: the failure of the steam turbine generator cooling system is set as the top event, the direct cause of the failure of the top event is analyzed, and the parameter abnormalities of the water temperature, water quality, flow, and water pressure in the steam turbine generator cooling system are set as intermediate events; the causes of the above four parameter abnormalities are analyzed in detail, and the causes of the parameter abnormalities are listed as bottom events, that is, basic events. Finally, the following are obtained: Figure 3 The fault tree logic diagram is shown.

[0033] Since the fault events of the turbine generator cooling system are complex, it is necessary to determine the minimum cut set and calculate the fault tree model value. In this embodiment, the determination of the minimum cut set adopts a downward algorithm, namely the Fuseo algorithm. Starting from the top event of the fault tree, the previous level event is replaced by the next level event from top to bottom, and the AND gate events are written horizontally in parallel, or the gate events are written vertically in series, until all logic gates are replaced with the basic event matrix. Each row of the basic event matrix represents a cut set, and the entire basic event matrix represents all the cut sets of the fault tree. Then, the minimum cut set of the fault tree is found from all the cut sets. In this embodiment, for ease of description, the symbols in Table 3 are used to replace Figure 3 The parameters of the fault tree logic diagram can be obtained Figure 4 .

[0034] according to Figure 4 The fault tree is combined with the descending algorithm to solve the minimum cut set, as shown in Table 4: The structural function of the fault tree of the turbine generator cooling system can be obtained as follows: ; in The status of the turbine generator cooling system; is the state of each basic event; n is the number of basic events.

[0035] The top event in the fault tree is represented as: ; in T is the top event of the fault tree; A j The fault tree j an intermediate event; X k The first k Minimal cut sets; m is the number of intermediate events; s is the minimum number of cut sets. Taking the failure of the cooling system of the steam turbine generator as an example, j =1,2,3,4 means 4 abnormal operation data events (intermediate events), k =1,2,...,11 represents 11 minimum cut sets.

[0036] Finally, the fault tree analysis is used to obtain the complete evolution path of different fault events starting from the bottom event, passing through the intermediate events and leading to the top event, as well as the change characteristics of the operating data, such as Figure 5 shown.

[0037] Step S6: logically setting the distributed control system of the steam turbine generator according to the fault tree so that the distributed control system can respectively obtain the operating data of the equipment associated with different fault events.

[0038] Specifically, the specific steps of performing logic setting on the distributed control system of the steam turbine generator in step S6 include: First, based on the obtained fault tree, the top event, intermediate events and specific equipment associated with the basic events of each fault are analyzed; for example, if the top event of a fault tree is abnormal power output of a steam turbine generator, the intermediate events may involve excitation system failure, steam supply system failure, etc., and the excitation system failure is related to equipment such as the excitation regulator and excitation transformer; the steam supply system failure is related to equipment such as steam valves and turbine blades.

[0039] The architecture of the distributed control system is optimized based on the correspondence between each event and the specific equipment in each fault event; for example, a special data acquisition module can be set up in the system to plan data acquisition channels for equipment associated with different types of faults: for equipment related to electrical faults, such as excitation transformers, independent current and voltage data acquisition channels are set up; for equipment related to mechanical faults, such as turbine blades, vibration, temperature and other data acquisition channels are set up.

[0040] According to the logical relationship of the fault tree, the data acquisition logic is written for the distributed control system; when the device corresponding to a basic event detects abnormal data, the data acquisition logic enables the distributed control system to quickly obtain the operating data of other devices related to the current data logic. By setting up the data acquisition logic in the distributed control system, when a certain operating data is abnormal, the relevant operating data of all potential faults can be quickly judged, and all abnormal data can be aggregated and analyzed to obtain all potential fault events, which can accurately realize the fault prediction and alarm of the system and improve the prediction efficiency.

[0041] Step S7: Acquire the operating data of each device in the steam turbine generator in real time, and compare the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault prediction or location.

[0042] Specifically, in step S7, the operation data is compared with the complete evolution characteristics of the fault tree preset in the distributed control system, and the step of realizing fault prediction includes: Obtain real-time operating data of different equipment of the steam turbine generator respectively; Analyze whether the changing trend of the real-time collected operation data conforms to the complete evolution characteristics of a certain fault event in the fault tree; When the change trend of one or more equipment operation data meets the complete evolution characteristics of a fault event in the fault tree, it is determined that the steam turbine generator has the risk of the corresponding fault; When the change trend of the equipment operation data collected in real time does not conform to the complete evolution characteristics of a fault event in the fault tree, the operation data record is kept.

[0043] Furthermore, in step S7, after fault prediction is achieved by comparing the operating data with the complete evolution characteristics of the fault tree in the distributed control system, an early warning interface can be provided in the distributed control system of the steam turbine generator, and the fault prediction results can be displayed using the early warning interface. By highlighting the possible faults in the cooling system and the possible components where the faults may occur on the early warning interface, the unit operating personnel can make corresponding adjustments based on the early warning information and the current operating conditions of the unit, or dispatch maintenance personnel to strengthen inspection and monitoring of the components that may fail.

[0044] In addition, the step S7 of comparing the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault location includes: Obtain the operating data recorded by the distributed control system when the fault occurs; Analyze whether the change trend of the operating data of each device when the fault occurs conforms to the complete evolution characteristics of a fault event in the fault tree; When the change trend of one or more equipment operation data meets the complete evolution characteristics of a fault event in the fault tree, the corresponding fault is determined to be the fault event of the current steam turbine generator, and the alarm is located according to the fault cause of the corresponding fault event; When the change trend of the operating data of each device does not conform to the complete evolution characteristics of a fault event in the fault tree, the current fault event is determined to be an unrecorded fault event, and the corresponding operating data is added to the fault tree of the distributed control system.

[0045] Furthermore, after the fault location is achieved in step S7, an alarm interface can be set in the distributed control system of the steam turbine generator, and the alarm interface can be used to display the fault location result. The distributed control system can make inferences on the alarm interface about the possible causes of the fault that has occurred, and the unit maintenance personnel can troubleshoot the fault based on the inference. For example, if the ring lead at the outlet end of the stator winding burns out, and the historical data of the unit operation shows that the cooling water flow rate was low and the hydrogen concentration in the cooling water tank had abnormally increased, then the logic compares it with the previous fault characteristics and concludes that the fault may be caused by a water leak that causes hydrogen to enter the waterway, causing gas blockage and eventually deteriorating to steam blockage, resulting in the melting of the ring lead. At this time, the unit maintenance personnel can quickly locate the fault location based on the inference results, thereby improving maintenance efficiency and reducing losses caused by the fault.

[0046] In addition, Figure 6 As shown, the present application also discloses a fault prediction device for a steam turbine generator cooling system, the device comprising: A data acquisition module is used to acquire historical fault events of the steam turbine generator and the operating data of each device when the corresponding fault event occurs; Data screening module, used to screen historical fault events and retain the fault events of target devices and the operating data of corresponding devices; The fault classification module is used to analyze the causes of the fault events after screening and classify them according to the causes of the faults; The fault analysis module is used to analyze the changes in operating data of different fault events in the early, middle and late stages according to the classified fault events; The feature evolution module is used to logically associate different fault events and the changes in the operating data of the corresponding fault events in different periods in the form of a fault tree to obtain the complete evolution features of different fault events; The logic download module is used to perform logic settings on the distributed control system of the steam turbine generator according to the fault tree, so that the distributed control system can obtain the operating data of the equipment associated with different fault events respectively; The fault output module is used to obtain the operating data of each device in the steam turbine generator in real time, and compare the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault prediction or location.

[0047] The device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment will not be described again here.

[0048] like Figure 7 As shown, the embodiment of the present application also provides an electronic device, including a processor and a memory, a program or instruction stored in the memory and executable on the processor, and when the program or instruction is executed by the processor, the following is achieved: Figure 1 The various processes of the method embodiment shown in the figure can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0049] The embodiment of the present application also provides a readable storage medium on which a program or instruction is stored. When the program or instruction is executed by a processor, the above Figure 1 The various processes of the method embodiments described above can achieve the same technical effect, and will not be described again here to avoid repetition.

[0050] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the above Figure 1 The various processes of the method embodiments described above can achieve the same technical effect, and will not be described again here to avoid repetition.

[0051] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0052] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0053] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another device, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0054] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0055] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0056] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0057] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device (which can be a terminal or a platform, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0058] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for predicting faults in a turbine generator cooling system, characterized in that: The method comprises the following steps: Obtain historical fault events of the steam turbine generator and the operating data of each device when the corresponding fault event occurs; Filter historical fault events and retain the fault events of the target device and the operating data of the corresponding device; Analyze the causes of the faults after screening and classify them according to the causes; According to the classified fault events, analyze the changes in operating data of different fault events in the early, middle and late stages; Use the fault tree form to logically associate different fault events and the changes in the operating data of the corresponding fault events in different periods to obtain the complete evolution characteristics of different fault events; According to the fault tree, the distributed control system of the steam turbine generator is logically set up so that the distributed control system can obtain the operating data of the equipment associated with different fault events respectively; The operating data of each device in the steam turbine generator is obtained in real time, and the operating data is compared with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault prediction or location.

2. The method for predicting faults in a turbine generator cooling system according to claim 1, characterized in that: The step of logically associating the fault data and the operation data changes of the corresponding fault events in different periods in the form of a fault tree to obtain the complete evolution characteristics of different fault events includes: Obtain each fault event and the operating data associated with the corresponding fault event; According to the fault events and corresponding operation data analysis, the top events, intermediate events and basic events of different fault events are obtained; The top event is used as the top of the fault tree and the intermediate events and basic events are arranged in descending order according to the hierarchy. The top event, intermediate events and basic events of different fault events are connected by logic gates to form a fault tree; wherein the structure of the fault tree is: ； in The status of the turbine generator cooling system; is the state of each basic event; n is the number of basic events; The fault tree analysis obtains the complete evolution path of different fault events starting from the bottom event, passing through the intermediate events and leading to the top event, as well as the change characteristics of the operating data.

3. The method for predicting faults in a turbine generator cooling system according to claim 2, characterized in that: When performing logical association, the descending algorithm is used to determine the minimum cut set of the fault tree: Starting from the top event of the fault tree, each step replaces the previous level event with the next level event from top to bottom; When replacing the upper and lower level events, write the AND gate events horizontally in parallel and the OR gate events vertically in series until all logic gates are replaced by the basic event matrix, where each row of the basic event matrix represents a cut set; The minimum cut set of the fault tree is obtained according to the basic event matrix, wherein the top event in the fault tree is represented as: ； in T is the top event of the fault tree; A j The fault tree j an intermediate event; X k The first k Minimal cut sets; m is the number of intermediate events; s is the minimum number of cut sets.

4. The method for predicting faults in a turbine generator cooling system according to claim 1, characterized in that: The step of logically setting the distributed control system of the steam turbine generator according to the fault tree so that the distributed control system respectively obtains the operating data of the equipment associated with different fault events includes: Analyze the top event, intermediate event and specific equipment associated with basic event of each fault event based on the fault tree; Optimize the architecture of the distributed control system based on the correspondence between each event and specific equipment in each fault event; Data acquisition logic is written for the distributed control system according to the logical relationship of the fault tree; when the device corresponding to a basic event detects abnormal data, the distributed control system is enabled to quickly acquire the operating data of other devices related to the current data logic through the data acquisition logic.

5. The method for predicting faults in a turbine generator cooling system according to claim 1, characterized in that: The step of comparing the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault prediction includes: Obtain real-time operating data of different equipment of the steam turbine generator respectively; Analyze whether the changing trend of the real-time collected operation data conforms to the complete evolution characteristics of a certain fault event in the fault tree; When the change trend of one or more equipment operation data meets the complete evolution characteristics of a fault event in the fault tree, it is determined that the steam turbine generator has the risk of the corresponding fault; When the change trend of the equipment operation data collected in real time does not conform to the complete evolution characteristics of a fault event in the fault tree, the operation data record is kept.

6. The method for predicting faults in a turbine generator cooling system according to claim 5, characterized in that: An early warning interface is provided in the distributed control system of the steam turbine generator, and the early warning interface is used to display the fault prediction result.

7. The method for predicting faults in a turbine generator cooling system according to claim 1, characterized in that: The step of comparing the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault location includes: Obtain the operating data recorded by the distributed control system when the fault occurs; Analyze whether the change trend of the operating data of each device when the fault occurs conforms to the complete evolution characteristics of a fault event in the fault tree; When the change trend of one or more equipment operation data meets the complete evolution characteristics of a fault event in the fault tree, the corresponding fault is determined to be the fault event of the current steam turbine generator, and the alarm is located according to the fault cause of the corresponding fault event; When the change trend of the operating data of each device does not conform to the complete evolution characteristics of a fault event in the fault tree, the current fault event is determined to be an unrecorded fault event, and the corresponding operating data is added to the fault tree of the distributed control system.

8. The method for predicting faults in a turbine generator cooling system according to claim 7, characterized in that: An alarm interface is provided in the distributed control system of the steam turbine generator, and the alarm interface is used to display the fault location result.

9. The method for predicting faults in a turbine generator cooling system according to claim 1, characterized in that: The causes of the failure include at least human factors, equipment aging, poor quality and improper operation.

10. A fault prediction device for a steam turbine generator cooling system, characterized in that: The device comprises: A data acquisition module is used to acquire historical fault events of the steam turbine generator and the operating data of each device when the corresponding fault event occurs; Data screening module, used to screen historical fault events and retain the fault events of target devices and the operating data of corresponding devices; The fault classification module is used to analyze the causes of the fault events after screening and classify them according to the causes of the faults; The fault analysis module is used to analyze the changes in operating data of different fault events in the early, middle and late stages according to the classified fault events; The feature evolution module is used to logically associate different fault events and the changes in the operating data of the corresponding fault events in different periods in the form of a fault tree to obtain the complete evolution features of different fault events; The logic download module is used to perform logic settings on the distributed control system of the steam turbine generator according to the fault tree, so that the distributed control system can obtain the operating data of the equipment associated with different fault events respectively; The fault output module is used to obtain the operating data of each device in the steam turbine generator in real time, and compare the operating data with the complete evolution characteristics of the fault tree preset in the distributed control system to achieve fault prediction or location.

Images