Thermal power plant water supply system fault analysis system and method based on data driving

Abstract

The invention discloses a thermal power plant water supply system fault analysis system and method based on data driving. The system comprises a mathematical model early warning module, a module for continuously alarming for more than five times, a mechanism model judgment module, a unit load prediction module, a rotating speed monitoring module, a module for monitoring steam pressure parameters from auxiliary steam to a water feeding pump turbine, a module for monitoring steam pressure parameters from industrial steam extraction to the water feeding pump turbine, a module for less than 5MW / min and a module for more than 50r / min. A first module greater than 0.5 MPa and a second module greater than 0.5 MPa; the method can identify the following four faults: a feed pump turbine steam inlet regulating valve jamming and on-site small machine steam inlet regulating valve actual working state module, a feed pump turbine steam inlet parameter low and steam inlet parameter lifting module, a steam feed pump non-operation state module and a steam feed pump operation output normal state module.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent monitoring and control of main water supply systems of thermal power plants, and in particular relates to a data-driven fault analysis system and method for water supply systems of thermal power plants. Background Art

[0002] The main function of the feed water system is to increase the pressure of the main feed water in the deaerator water tank through the feed water pump, and after further heating by the high-pressure heater, it is transported to the economizer inlet of the boiler as the boiler feed water. In addition, the feed water system also provides cooling water to the desuperheater of the boiler reheater, the first and second desuperheaters of the superheater, and the desuperheater of the high-pressure bypass device of the steam turbine to adjust the temperature of the steam outlet of the above equipment. The initial water injection of the feed water system comes from the condensate system. The pump that supplies water to the boiler is called the feed water pump. Its function is to increase the pressure of the deoxygenated feed water with a certain temperature in the deaerator water tank and transport it to the boiler to meet the boiler water needs. Due to the high feed water temperature (the saturation temperature corresponding to the deaerator pressure), water is easy to vaporize at the inlet of the feed water pump, which will form cavitation and cause water outflow interruption, and finally lead to insufficient output of the feed water pump. When the feedwater pump fails to operate properly, the outlet pressure of the feedwater pump decreases. Although the feedwater pump operates normally, it cannot supply water to the boiler normally due to the high pressure of the boiler itself, resulting in dry burning of the boiler, boiler tube burst, unit equipment damage, and unit unstoppable. Currently, the protection mechanism for the safe operation of insufficient feedwater pump output only sets the unit to trip after the normal operation signal of the feedwater pump disappears; it is unable to issue an early warning signal for the abnormality of insufficient feedwater pump output, and then take measures to eliminate the defect and avoid further damage. Summary of the invention

[0003] In view of the above problems, the purpose of the present invention is to provide a data-driven fault analysis system and method for a thermal power plant water supply system. By collecting and analyzing the historical data of the system operation, a mathematical model and a mechanism model of the water supply pump abnormality are established. By combining the mathematical model and the mechanism model, real-time monitoring of the operating state of insufficient output of the water supply pump can be achieved, and timely warning of abnormal operation of the water supply pump can be provided.

[0004] In order to achieve the above object, the present invention adopts the following technical solution: A data-driven fault analysis system for a thermal power plant feedwater system, comprising a mathematical model early warning module, a module for the number of consecutive alarms greater than 5 times, a mechanism model judgment module, a unit load prediction module, a speed monitoring module, a steam pressure parameter monitoring module for an auxiliary steam to a feedwater pump turbine, a steam pressure parameter monitoring module for an industrial extraction steam to a feedwater pump turbine, a module less than 5MW / min, a module greater than 50r / min, a first module greater than 0.5MPa, and a second module greater than 0.5MPa; The mathematical model early warning module is connected to the module with continuous alarm times greater than 5 times; the mechanism model judgment module is respectively connected to the unit load prediction module, the speed monitoring module, the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module and the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module; the unit load prediction module is connected to the less than 5MW / min module, the speed monitoring module is connected to the greater than 50r / min module, the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module is connected to the first greater than 0.5MPa module, and the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module is connected to the second greater than 0.5MPa module.

[0005] A further improvement of the present invention is that when the number of consecutive alarms is greater than 5 times and the module is 0, it is connected to the mathematical model early warning module and re-judgment is made; when the number of consecutive alarms is greater than 5 times and the module is 1, it is connected to the activation mechanism model judgment module.

[0006] A further improvement of the present invention is that it also includes an OR module, a first AND module and a module for checking the stuck steam inlet regulating valve of a feedwater pump turbine and the actual working state of the steam inlet regulating valve of a small turbine on site; The first module greater than 0.5MPa and the second module greater than 0.5MPa are both connected to the OR module; the 5MW / min module, the greater than 50r / min module and the OR module are all connected to the first AND module, and the first AND module is connected to the module for checking the stuck steam inlet regulating valve of the feed pump turbine and the actual working status of the small machine steam inlet regulating valve on-site.

[0007] A further improvement of the present invention is that it also includes a second AND module and a feedwater pump turbine steam inlet parameter low and steam inlet parameter improvement module; the 5MW / min module and the OR module are both connected to the second AND module, and the second AND module is connected to the feedwater pump turbine steam inlet parameter low and steam inlet parameter improvement module.

[0008] A further improvement of the present invention is that it also includes a third AND module and a steam-driven water pump non-operating state module; the 5MW / min module, the greater than 50r / min module and the OR module are all connected to the third AND module, and the third AND module is connected to the steam-driven water pump non-operating state module.

[0009] A further improvement of the present invention is that it also includes a fourth module and a steam-driven water supply pump normal operating output state module; the module less than 5MW / min, or the module and the module with continuous alarm times greater than 5 times are connected to the fourth module, and the fourth module is connected to the steam-driven water supply pump normal operating output state module.

[0010] A data-driven method for analyzing a failure of a water supply system in a thermal power plant, the method is based on the data-driven system for analyzing a failure of a water supply system in a thermal power plant, and comprises: When the mathematical model warning module is 1, the next step of the continuous alarm number greater than 5 times module is triggered; when the continuous alarm number greater than 5 times module is 1, the next step of the activation mechanism model judgment module is triggered; the activation mechanism model judgment module directly triggers the unit load prediction module, the speed monitoring module and the or module; at this time, the unit load prediction module satisfies the less than 5MW / min module, the speed monitoring module satisfies the greater than 50r / min module, the auxiliary steam to the feedwater pump turbine steam pressure parameter monitoring module satisfies the first greater than 0.5MPa module or the industrial extraction steam to the feedwater pump turbine steam pressure parameter monitoring module satisfies the second greater than 0.5MPa module. When all the above conditions are met, the first and module is triggered, and the middle module outputs the feedwater pump turbine steam inlet regulating valve stuck and the on-site inspection of the small unit steam inlet regulating valve actual working status module.

[0011] A further improvement of the present invention is that it also includes: When the mathematical model warning module is 1, the next step of the continuous alarm number greater than 5 times module is triggered; when the continuous alarm number greater than 5 times module is 1, the next step of the activation mechanism model judgment module is triggered; the activation mechanism model judgment module directly triggers the unit load prediction module, the speed monitoring module and the or module; at this time, the unit load prediction module satisfies the less than 5MW / min module, the speed monitoring module satisfies the greater than 50r / min module, the auxiliary steam to the feedwater pump turbine steam pressure parameter monitoring module does not satisfy the first greater than 0.5MPa module and the industrial extraction steam to the feedwater pump turbine steam pressure parameter monitoring module does not satisfy the second greater than 0.5MPa module. When all the above conditions are met, the second and module is triggered, and the middle module outputs the feedwater pump turbine steam inlet parameters low and the steam inlet parameter improvement module.

[0012] A further improvement of the present invention is that it also includes: When the mathematical model warning module is 1, the next step of the continuous alarm number greater than 5 times module is triggered; when the continuous alarm number greater than 5 times module is 1, the next step of the activation mechanism model judgment module is triggered; the activation mechanism model judgment module directly triggers the unit load prediction module, the speed monitoring module and or module; at this time, the unit load prediction module satisfies the less than 5MW / min module, the speed monitoring module does not satisfy the greater than 50r / min module, the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module satisfies the first greater than 0.5MPa module or the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module satisfies the second greater than 0.5MPa module. When all the above conditions are met, the third and module is triggered, and the middle module outputs the steam-driven feedwater pump non-operating status module.

[0013] A further improvement of the present invention is that it also includes: When the mathematical model warning module is 1, the next step of the continuous alarm number greater than 5 times module is triggered; when the continuous alarm number greater than 5 times module is 1, the next step of the activation mechanism model judgment module is triggered; the activation mechanism model judgment module directly triggers the unit load prediction module, the speed monitoring module and or module; at this time, the unit load prediction module satisfies the less than 5MW / min module, the speed monitoring module satisfies the greater than 50r / min module, the auxiliary steam to the feedwater pump turbine steam pressure parameter monitoring module satisfies the first greater than 0.5MPa module or the industrial extraction steam to the feedwater pump turbine steam pressure parameter monitoring module satisfies the second greater than 0.5MPa module, and the continuous alarm number greater than 5 times module is not triggered. When all the above conditions are met, the fourth and module, the steam-driven feedwater pump operating output normal state module, is triggered.

[0014] Compared with the prior art, the present invention has at least the following beneficial technical effects: The present invention provides a data-driven thermal power plant feedwater system fault analysis system and method, which adopts a data-driven thermal power plant feedwater system fault analysis system to analyze various types of faults, and classify them into: the feedwater pump steam turbine steam inlet regulating valve is stuck, and the actual working state of the small machine steam inlet regulating valve is checked on site; the feedwater pump steam turbine steam inlet parameters are low, and the steam inlet parameters are increased; the steam-driven feedwater pump is not in operation; the steam-driven feedwater pump is in normal operation output state. In addition, the abnormal working condition mechanism analysis is carried out in combination with the feedwater pump output insufficient abnormal expert knowledge base, and the specific abnormal causes and solutions are comprehensively pushed out, so as to guide the operation monitoring personnel to adjust the unit operating conditions in time, and prevent the unit from being unplanned down due to the feedwater pump output insufficient operation abnormality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention is a structural schematic diagram of a data-driven thermal power plant water supply system fault analysis system.

[0016] Figure 2 Prediction effect diagram for the test set.

[0017] Description of reference numerals: 001, mathematical model warning module, 002, continuous alarm number greater than 5 times module, 003, activation mechanism model judgment module, 004, unit load prediction module, 005, speed monitoring module, 006, auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module, 007, industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module, 008, less than 5MW / min module, 009, greater than 50r / min module, 010, the first greater than 0.5MPa Module, 011, the second is greater than 0.5MPa module, 012, or module, 013, the first and module, 014, the second and module, 015, the third and module, 016, the fourth and module, 017, the feedwater pump turbine steam inlet regulating valve stuck and on-site inspection of the actual working status of the small machine steam inlet regulating valve module, 018, the feedwater pump turbine steam inlet parameters are low and the steam inlet parameters are increased module, 019, the steam-driven feedwater pump is not running status module, 020, the steam-driven feedwater pump is running normally output status module. DETAILED DESCRIPTION

[0018] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0019] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0020] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0021] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0022] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0023] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0024] Example 1 See also Figure 1 The present invention provides a data-driven thermal power plant water supply system fault analysis system, comprising: Mathematical model warning module 001, module 002 for the number of consecutive alarms being greater than 5 times, module 003 for judging the activation mechanism model, module 004 for predicting the load of the unit, module 005 for monitoring the speed, module 006 for monitoring the steam pressure parameters of the auxiliary steam to the feedwater pump turbine, module 007 for monitoring the steam pressure parameters of the industrial extraction steam to the feedwater pump turbine, module 008 for less than 5MW / min, module 009 for greater than 50r / min, module 010 for the first being greater than 0.5MPa, module 011 for the second being greater than 0.5MPa, or module 012, first and module 013, second and module 014, third and module 015, fourth and module 016, module 017 for checking the actual working status of the steam inlet regulating valve of the feedwater pump turbine when it is stuck and on-site inspection of the actual working status of the steam inlet regulating valve of the small machine, module 018 for checking the low steam inlet parameters of the feedwater pump turbine and improving the steam inlet parameters, module 019 for the non-operating status of the steam-driven feedwater pump, and module 020 for the normal operating output of the steam-driven feedwater pump.

[0025] The connection method of each module is: 1) The mathematical model warning module 001 is connected to the continuous alarm number greater than 5 times module 002. When the continuous alarm number greater than 5 times module 002 is 0, it is connected to the mathematical model warning module 001 and re-judged. When the continuous alarm number greater than 5 times module 002 is 1, it is connected to the activation mechanism model judgment module 003. The mechanism model judgment module 003 is respectively connected to the unit load prediction module 004, the speed monitoring module 005, the auxiliary steam to feedwater pump steam turbine steam pressure parameter monitoring module 006, and the industrial extraction steam to feedwater pump steam turbine steam pressure parameter monitoring module 007. The unit load prediction module 004 is connected to the less than 5MW / min module 008, the speed monitoring module 005 is connected to the greater than 50r / min module 009, the auxiliary steam to feedwater pump steam turbine steam pressure parameter monitoring module 006 is connected to the first greater than 0.5MPa module 010, and the industrial extraction steam to feedwater pump steam turbine steam pressure parameter monitoring module 007 is connected to the second greater than 0.5MPa module 011.

[0026] 2) The first module 010 greater than 0.5MPa and the second module 011 greater than 0.5MPa are both connected to the OR module 012. The 5MW / min module 008, the greater than 50r / min module 009 and the OR module 012 are all connected to the first AND module 013, and the first AND module 013 is connected to the feed pump turbine steam inlet regulating valve stuck and on-site inspection of the actual working status of the small machine steam inlet regulating valve module 017.

[0027] 3) The 5MW / min module 008 and the OR module 012 are both connected to the second AND module 014 , and the second AND module 014 is connected to the feedwater pump turbine steam inlet parameter low and boost steam inlet parameter module 018 .

[0028] 4) The 5MW / min module 008, the greater than 50r / min module 009 and the OR module 012 are all connected to the third AND module 015, and the third AND module 015 is connected to the steam-driven feedwater pump non-operating state module 019.

[0029] 5) The module 008 less than 5MW / min, or the module 012 and the module 002 with the number of consecutive alarms greater than 5 times are both connected to the fourth module 016, and the fourth module 016 is connected to the normal output state module 020 of the steam-driven feedwater pump.

[0030] Example 1 See also Figure 1 The present invention provides a data-driven method for analyzing a failure of a water supply system in a thermal power plant, comprising: 1) The practical application of the module 017 for checking the actual working status of the steam inlet regulating valve of the feedwater pump turbine and the actual working status of the steam inlet regulating valve of the small unit on site is: when the mathematical model early warning module 001 is 1, the next step of the continuous alarm number greater than 5 times module 002 is triggered. When the continuous alarm number greater than 5 times module 002 is 1, the next step of the activation mechanism model judgment module 003 is triggered. The activation mechanism model judgment module 003 directly triggers the unit load prediction module 004, the speed monitoring module 005 and or module 012. At this time, the unit load prediction module 004 needs to satisfy the less than 5MW / min module 008, the speed monitoring module 005 needs to satisfy the greater than 50r / min module 009, the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module 006 needs to satisfy the first greater than 0.5MPa module 010 or the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module 007 needs to satisfy the second greater than 0.5MPa module 011. When all the above conditions are met, the first and module 013 is triggered, and the middle module outputs the feedwater pump turbine steam inlet regulating valve stuck and the on-site inspection of the small unit steam inlet regulating valve actual working status module 017.

[0031] 2) The actual application of the module 018 for low steam inlet parameters and increased steam inlet parameters of the feedwater pump turbine is as follows: when the mathematical model early warning module 001 is 1, the next step of the continuous alarm number greater than 5 times module 002 is triggered. When the continuous alarm number greater than 5 times module 002 is 1, the next step of the activation mechanism model judgment module 003 is triggered. The activation mechanism model judgment module 003 directly triggers the unit load prediction module 004, the speed monitoring module 005 and / or the module 012. At this time, the unit load prediction module 004 needs to satisfy the less than 5MW / min module 008, the speed monitoring module 005 satisfies the greater than 50r / min module 009, the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module 006 does not satisfy the first greater than 0.5MPa module 010 and the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module 007 does not satisfy the second greater than 0.5MPa module 011. When all the above conditions are met, the second and module 014 is triggered, and the middle module outputs the feedwater pump turbine steam inlet parameters low and increased steam inlet parameters module 018.

[0032] 3) The actual application of the steam-driven feedwater pump non-operating state module 019 is as follows: when the mathematical model warning module 001 is 1, the next step of the continuous alarm number greater than 5 times module 002 is triggered. When the continuous alarm number greater than 5 times module 002 is 1, the next step of the activation mechanism model judgment module 003 is triggered. The activation mechanism model judgment module 003 directly triggers the unit load prediction module 004, the speed monitoring module 005 and or module 012. At this time, the unit load prediction module 004 needs to meet the less than 5MW / min module 008, the speed monitoring module 005 does not meet the greater than 50r / min module 009, the auxiliary steam to feedwater pump steam turbine steam pressure parameter monitoring module 006 meets the first greater than 0.5MPa module 010 or the industrial extraction steam to feedwater pump steam turbine steam pressure parameter monitoring module 007 meets the second greater than 0.5MPa module 011. When all the above conditions are met, the third and module 015 is triggered, and the middle module outputs the steam-driven feedwater pump non-operating state module 019.

[0033] 4) The actual application of the steam-driven feedwater pump normal output state module 020 is: when the mathematical model warning module 001 is 1, the next step of the continuous alarm number greater than 5 times module 002 is triggered. When the continuous alarm number greater than 5 times module 002 is 1, the next step of the activation mechanism model judgment module 003 is triggered. The activation mechanism model judgment module 003 directly triggers the unit load prediction module 004, the speed monitoring module 005 and or module 012. At this time, the unit load prediction module 004 needs to meet the less than 5MW / min module 008, the speed monitoring module 005 meets the greater than 50r / min module 009, the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module 006 meets the first greater than 0.5MPa module 010 or the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module 007 meets the second greater than 0.5MPa module 011, and the continuous alarm number is greater than 5 times module 002 is not triggered. When all the above conditions are met, the fourth and module 016 are triggered, and the steam-driven feedwater pump operating output normal state module 020 is triggered.

[0034] Example 3 See also Figure 2, the prediction effect diagram of the test set, the prediction times are more than 1600, and the actual label and the label are precisely overlapped in the range of 800-1200, which shows the accuracy and consistency of the prediction; using the judgment method between each module, the historical data of the unit is imported into the judgment module process to verify the consistency between the label of the actual working condition and the label predicted by the model. It is verified that the prediction effect of the model is good, and the fault of the thermal power plant feed water system can be judged, and the following four faults can be identified: the feed water pump turbine steam inlet regulating valve is stuck and the actual working state of the small unit steam inlet regulating valve is checked on site 017, the feed water pump turbine steam inlet parameters are low and the steam inlet parameters are increased 018, the steam-driven feed water pump is not running Module 019 and the steam-driven feed water pump is running at normal output Module 020.

[0035] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0036] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A data-driven fault analysis system for a thermal power plant water supply system, characterized in that: It includes a mathematical model early warning module (001), a continuous alarm number greater than 5 times module (002), a mechanism model judgment module (003), a unit load prediction module (004), a speed monitoring module (005), an auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module (006), an industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module (007), a less than 5MW / min module (008), a greater than 50r / min module (009), a first greater than 0.5MPa module (010) and a second greater than 0.5MPa module (011); The mathematical model early warning module (001) is connected to the module for continuous alarm times greater than 5 times (002); the mechanism model judgment module (003) is respectively connected to the unit load prediction module (004), the speed monitoring module (005), the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module (006) and the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module (007); the unit load prediction module (004) is connected to the less than 5MW / min module (008), the speed monitoring module (005) is connected to the greater than 50r / min module (009), the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module (006) is connected to the first greater than 0.5MPa module (010), and the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module (007) is connected to the second greater than 0.5MPa module (011).

2. A data-driven thermal power plant water supply system fault analysis system according to claim 1, characterized in that: When the number of consecutive alarms is greater than 5 times and the module (002) is 0, it is connected to the mathematical model warning module (001) and re-judged. When the number of consecutive alarms is greater than 5 times and the module (002) is 1, it is connected to the activation mechanism model judgment module (003).

3. A data-driven thermal power plant water supply system fault analysis system according to claim 2, characterized in that: It also includes an OR module (012), a first AND module (013), and a module (017) for checking the actual working state of the steam inlet regulating valve of the feedwater pump turbine and for checking the actual working state of the steam inlet regulating valve of the small turbine on site; The first module (010) greater than 0.5MPa and the second module (011) greater than 0.5MPa are both connected to the OR module (012); the 5MW / min module (008), the module (009) greater than 50r / min and the OR module (012) are all connected to the first AND module (013), and the first AND module (013) is connected to the feedwater pump steam turbine steam inlet regulating valve stuck and on-site inspection of the actual working status of the small machine steam inlet regulating valve module (017).

4. A data-driven thermal power plant water supply system fault analysis system according to claim 3, characterized in that: It also includes a second AND module (014) and a feedwater pump steam turbine low steam inlet parameter and increased steam inlet parameter module (018); the 5MW / min module (008) and the OR module (012) are both connected to the second AND module (014), and the second AND module (014) is connected to the feedwater pump steam turbine low steam inlet parameter and increased steam inlet parameter module (018).

5. A data-driven thermal power plant water supply system fault analysis system according to claim 4, characterized in that: It also includes a third AND module (015) and a steam-driven water supply pump non-operating state module (019); the 5MW / min module (008), the greater than 50r / min module (009) and the OR module (012) are all connected to the third AND module (015), and the third AND module (015) is connected to the steam-driven water supply pump non-operating state module (019).

6. A data-driven thermal power plant water supply system fault analysis system according to claim 5, characterized in that: It also includes a fourth AND module (016) and a steam-driven water supply pump normal operating output status module (020); the less than 5MW / min module (008), or the module (012) and the continuous alarm number greater than 5 times module (002) are both connected to the fourth AND module (016), and the fourth AND module (016) is connected to the steam-driven water supply pump normal operating output status module (020).

7. A data-driven method for analyzing failures in a thermal power plant water supply system, characterized in that: The method is based on a data-driven thermal power plant water supply system fault analysis system as described in claim 6, comprising: When the mathematical model warning module (001) is 1, the next step of the continuous alarm times greater than 5 times module (002) is triggered; when the continuous alarm times greater than 5 times module (002) is 1, the next step of the activation mechanism model judgment module (003) is triggered; the activation mechanism model judgment module (003) directly triggers the unit load prediction module (004), the speed monitoring module (005) and the or module (012); at this time, the unit load prediction module (004) meets the less than 5MW / min module (008), the speed monitoring module (010) and the or module (011). Module (005) satisfies the greater than 50r / min module (009), the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module (006) satisfies the first greater than 0.5MPa module (010) or the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module (007) satisfies the second greater than 0.5MPa module (011). When all of the above conditions are met, the first and module (013) is triggered, and the middle module outputs the feedwater pump turbine steam inlet regulating valve stuck and the on-site inspection of the small machine steam inlet regulating valve actual working status module (017).

8. The data-driven method for analyzing the failure of a thermal power plant water supply system according to claim 7 is characterized in that: Also includes: When the mathematical model warning module (001) is 1, the next step of the continuous alarm times greater than 5 times module (002) is triggered; when the continuous alarm times greater than 5 times module (002) is 1, the next step of the activation mechanism model judgment module (003) is triggered; the activation mechanism model judgment module (003) directly triggers the unit load prediction module (004), the speed monitoring module (005) and the or module (012); at this time, the unit load prediction module (004) satisfies the less than 5MW / min module (008), The speed monitoring module (005) satisfies the greater than 50r / min module (009), the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module (006) does not satisfy the first greater than 0.5MPa module (010), and the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module (007) does not satisfy the second greater than 0.5MPa module (011). When all of the above conditions are met, the second and module (014) is triggered, and the middle module outputs the feedwater pump turbine steam inlet parameter low and increased steam inlet parameter module (018).

9. A data-driven method for analyzing failures of a thermal power plant water supply system according to claim 8, characterized in that: Also includes: When the mathematical model warning module (001) is 1, the next step of the continuous alarm times greater than 5 times module (002) is triggered; when the continuous alarm times greater than 5 times module (002) is 1, the next step of the activation mechanism model judgment module (003) is triggered; the activation mechanism model judgment module (003) directly triggers the unit load prediction module (004), the speed monitoring module (005) and the or module (012); at this time, the unit load prediction module (004) satisfies the less than 5MW / min module ( 008), the speed monitoring module (005) does not satisfy the greater than 50r / min module (009), the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module (006) satisfies the first greater than 0.5MPa module (010) or the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module (007) satisfies the second greater than 0.5MPa module (011). When all of the above conditions are met, the third and module (015) is triggered, and the middle module outputs the steam-driven feedwater pump non-operating status module (019).

10. A data-driven method for analyzing failures of a thermal power plant water supply system according to claim 9, characterized in that: Also includes: When the mathematical model warning module (001) is 1, the next step of the continuous alarm times greater than 5 times module (002) is triggered; when the continuous alarm times greater than 5 times module (002) is 1, the next step of the activation mechanism model judgment module (003) is triggered; the activation mechanism model judgment module (003) directly triggers the unit load prediction module (004), the speed monitoring module (005) and the or module (012); at this time, the unit load prediction module (004) meets the less than 5MW / min module (008), the speed monitoring module (010) and the or module (011). Module (005) satisfies the greater than 50r / min module (009), the auxiliary steam to feedwater pump turbine steam pressure parameter monitoring module (006) satisfies the first greater than 0.5MPa module (010) or the industrial extraction steam to feedwater pump turbine steam pressure parameter monitoring module (007) satisfies the second greater than 0.5MPa module (011), and the continuous alarm number is greater than 5 times module (002) is not triggered. When all the above conditions are met, the fourth and module (016) are triggered, and the steam-driven feedwater pump operating output normal state module (020).

Images