A model-driven unit non-stop supervision method, system, device and storage medium

Abstract

The present invention discloses a model-driven unit non-stop supervision method, system, device and storage medium, which relates to the field of electric power engineering technology, including: judging the closing state of the generator outlet circuit breaker and obtaining the turbine speed information; constructing a unit start-stop supervision model to judge the unit operating state; the unit operating state includes an operating state and a shutdown state; judging the unit shutdown type, and constructing a unit shutdown ledger based on the unit shutdown type. The model-driven unit non-stop supervision method provided by the present invention constructs a unit non-stop supervision model by introducing multi-physical field simulation technology and data fusion analysis, and can monitor the operating state of the generator set in real time, automatically distinguish between planned shutdowns and unplanned shutdowns, and automatically generate and report when an unplanned shutdown event occurs. Through an automated and standardized monitoring process, the problems of low efficiency, feedback lag and inaccurate data in traditional methods are significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power engineering, and in particular to a method, system, device and storage medium for non-stop supervision of a unit based on model driving. Background Art

[0002] In modern power systems, the stable operation of steam turbine generator sets is the key to ensuring the continuity and reliability of power supply. However, in the long-term operation of the units, it is inevitable that the units will encounter outages caused by equipment failures, maintenance needs or external interference. According to the regulations of the power industry, the outages of generator sets are divided into two types: planned outages and unplanned outages. Planned outages are pre-arranged shutdown operations, usually used for equipment maintenance or system upgrades, aimed at ensuring the long-term safe and stable operation of the units. Unplanned outages are unexpected outages caused by sudden failures or other unexpected events, which will not only affect the stability of power supply, but may also pose a threat to the overall safety of the power system.

[0003] Traditional unit outage monitoring and management methods mainly rely on manual inspections and data recording. Although this method can meet basic management needs to a certain extent, with the complexity of power systems and the sharp increase in data volume, this manual monitoring method faces serious efficiency and accuracy issues.

[0004] A large amount of data needs to be collected and processed manually, which is not only time-consuming and labor-intensive, but also easily leads to data omissions or errors, which in turn affects the timely reporting and handling of outage events.

[0005] Due to reliance on manual reporting, information on unit failures cannot be uploaded in a timely manner, which may adversely affect scheduling and power balance and increase the pressure on grid operation.

[0006] Manual operation is prone to omissions or false alarms, which makes it impossible for regulatory authorities to accurately grasp the actual operating conditions of the unit, thus affecting decision-making and the implementation of subsequent measures.

[0007] In view of the existence of the above-mentioned problems, the present invention proposes a model-driven unit non-shutdown supervision method, which aims to overcome the shortcomings of traditional methods through the construction of intelligent models and automatic processing of real-time data, and realize accurate monitoring of the operating status of generator sets and automatic classification and reporting of shutdown events. Summary of the invention

[0008] In view of the above-mentioned problems, the present invention is proposed.

[0009] Therefore, the technical problem solved by the present invention is: the existing generator set shutdown monitoring method has the problems of low manual monitoring efficiency, delayed information feedback and insufficient data accuracy, as well as how to optimize the real-time monitoring and automatic classification of the generator set operating status.

[0010] In order to solve the above technical problems, the present invention provides the following technical solutions: a model-driven non-stop monitoring method for a unit, comprising:

[0011] Determine the closing status of the generator output circuit breaker and obtain the steam turbine speed information; build a unit start-stop supervision model to determine the unit operating status; the unit operating status includes operating status and shutdown status; determine the unit shutdown type, and build a unit shutdown ledger based on the unit shutdown type.

[0012] As a preferred solution of the model-driven unit non-stop supervision method described in the present invention, wherein: the judgment of the closing state of the generator output circuit breaker includes analyzing the operating conditions of the circuit breaker through multi-physical field simulation technology, arranging sensors at key positions prone to abnormalities during operation, and real-time monitoring of stress data, temperature data and electromagnetic field data; analyzing the external environment of the circuit breaker, arranging sensors in areas susceptible to environmental noise and electromagnetic interference, and monitoring environmental noise data and electromagnetic interference data; arranging measurement points in the vicinity of the circuit breaker to detect common mode noise data and vibration data in the electrical system; normalizing the data at different measurement points to construct a closing state evaluation model, expressed as,

[0013] ,

[0014] ,

[0015] ,

[0016] ,

[0017] ,

[0018] ,

[0019] ,

[0020] ,

[0021] in, represents the total thermal stress, represents the base stress, represents the thermal expansion coefficient of the material, represents Young's modulus, Indicates temperature change, represents the electromagnetic stress, represents the internal electromagnetic field strength, is the magnetic permeability in vacuum, represents the total stress, represents the noise power density, Indicates the intensity of ambient noise, represents acoustic impedance, represents the electromagnetic interference power density, Indicates the strength of external electromagnetic interference, represents electrical impedance, represents the total power density of external interference, Indicates the system health state energy, represents the common-mode noise voltage, represents the vibration acceleration, Indicates the quality of the circuit breaker. represents the comprehensive evaluation index, represents the maximum allowable stress, represents the maximum permissible interference power density, Indicates the maximum allowable health state energy.

[0022] like >Preset state judgment threshold to judge whether the circuit breaker is in the closed state. ≤ the preset status judgment threshold, judging that the circuit breaker is in the disconnected state.

[0023] As a preferred solution of the model-driven unit non-stop supervision method described in the present invention, wherein: the steam turbine speed information is obtained through mechanical vibration analysis, moment of inertia analysis and thermal effect analysis to determine the key measuring point positions of the steam turbine shaft section; the mechanical vibration analysis uses finite element analysis to simulate the vibration mode of the steam turbine rotor, identifies the anti-nodes and node positions in the vibration mode, and selects the vibration mode nodes to arrange the measuring points; the moment of inertia analysis calculates the rotational inertia distribution of the rotor along the axial direction, identifies the inertia mutation points, and arranges the measuring points at the inertia mutation points; the thermal effect analysis analyzes the temperature distribution under different working conditions through thermodynamic simulation, identifies the area where the temperature gradient is greater than the preset temperature threshold and arranges the measuring points; sensors are installed at the measuring point positions to measure the speed, vibration and temperature data in real time, and pre-process the data.

[0024] In data preprocessing, the speed measurement results are corrected by vibration data and temperature data, which is expressed as,

[0025] ,

[0026] ,

[0027] ,

[0028] in, Indicates measuring point The corrected speed value, Indicates measuring point The raw speed measurement value, Indicates measuring point Correction factors based on vibration data, Indicates measuring point The vibration acceleration at Indicates the maximum allowable value of vibration acceleration, Indicates measuring point Correction factors based on temperature data, Indicates measuring point The temperature change at Indicates the maximum allowable value of temperature change.

[0029] Construct the speed fusion analysis model, expressed as,

[0030] ,

[0031] in, Represents the final speed value after fusion, Indicates measuring point The weight of Indicates measuring point The corrected speed value, Indicates the number of measurement points, Indicates the number of the measuring point; when >Minimum operating speed threshold and the circuit breaker is in the closed state, the unit is judged to be in the operating state, otherwise the unit is judged to be in the shutdown state.

[0032] As a preferred scheme of the model-driven unit non-stop supervision method described in the present invention, wherein: the unit shutdown type is judged by logic one, logic two, logic three and logic four; if logic one, logic two, logic three and logic four all meet the preset standards, it is judged as a planned shutdown; if logic four meets the preset standards, but any of logic one, logic two and logic three does not meet the preset standards, it is judged as an unplanned shutdown.

[0033] As a preferred scheme of the model-driven unit non-stop supervision method described in the present invention, wherein: the logic one is to judge the operating pressure drop rate of the normal load reduction of the unit; the logic two is to judge the load allowable state of the normal shutdown of the unit; the logic three is to judge the allowable load drop rate of the normal load reduction of the unit; the logic four is to judge the tripping state of the unit.

[0034] As a preferred solution of the model-driven unit non-shutdown supervision method described in the present invention, wherein: the operating pressure drop rate of the normal load reduction of the unit is determined by obtaining the main steam pressure value on the boiler side from the SIS database; calculating the pressure drop rate of the main steam pressure on the boiler side within 30 minutes; if the pressure drop rate is ≤0 and the absolute value of the pressure drop rate is ≤ the power plant operation pressure reduction rate; the judgment logic 1 satisfies the preset standard, if any condition is not met, the judgment logic 1 does not meet the preset standard; the load allowable state of the normal shutdown of the unit is determined by obtaining the unit load value from the SIS database, calculating the average value of the unit load for 10 minutes, and when the average value is less than 15% of the rated load, it is judged as logic Logic 2 satisfies the preset standard, otherwise logic 2 is judged to not meet the preset standard; the judgment of the allowable load reduction rate of normal unit load reduction includes obtaining the unit load value from the SIS database; the rate of load reduction within 30 minutes of the computer unit load; if the load reduction rate is ≤0 and the absolute value of the load reduction rate is ≤ the power plant operation load reduction rate; the judgment logic 3 meets the preset standard, if any condition is not met, the judgment logic 3 does not meet the preset standard; the judgment of the unit tripping status includes reading the turbine tripping signal and the boiler main fuel tripping signal from the SIS database, if the turbine tripping signal and the boiler main fuel tripping signal both show tripping, it is judged that logic 4 meets the preset standard, otherwise it is judged that logic 4 does not meet the preset standard.

[0035] As a preferred scheme of the model-driven unit non-stop supervision method described in the present invention, wherein: the construction of the unit shutdown ledger includes pushing the shutdown or operation record to the unit shutdown ledger when the unit is monitored to be shut down or running; recording the time when the start-stop supervision model is triggered as the start time of the unit state; the unit state switches between the running state and the shutdown state, and when switching to the next state, the start time of the next state is the end time of the previous state; recording the duration of the unit state as the end time of the previous state minus the start time of the unit state; if the unit state is not switched, the duration is the current time minus the start time of the unit state; when a planned shutdown or unplanned shutdown is monitored, the shutdown record is marked as a planned shutdown or unplanned shutdown; when an unplanned shutdown of the unit is monitored, the unit shutdown ledger information is automatically reported immediately through the interface.

[0036] Another object of the present invention is to provide a model-driven non-stop monitoring system for the unit, which can solve the problems of strong manual dependence, untimely monitoring, and inaccurate data processing in the existing shutdown monitoring methods by constructing a model-driven non-stop monitoring system for the unit, and realize real-time monitoring, accurate judgment and automatic reporting of the start-up and shutdown process of the generator set.

[0037] To solve the above technical problems, the present invention provides the following technical solutions: a model-driven unit non-stop supervision system, comprising: a data acquisition module, a start-stop supervision module and a shutdown supervision module; the data acquisition module is used to determine the closing status of the generator output circuit breaker and obtain the steam turbine speed information; the start-stop supervision module is used to construct a unit start-stop supervision model to determine the unit operating status; the unit operating status includes an operating status and a shutdown status; the shutdown supervision module is used to determine the unit shutdown type and construct a unit shutdown ledger based on the unit shutdown type.

[0038] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned model-driven unit non-stop supervision method when executing the computer program.

[0039] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned model-driven unit non-stop supervision method.

[0040] Beneficial effects of the present invention: The model-driven unit non-stop supervision method provided by the present invention constructs a unit non-stop supervision model by introducing multi-physical field simulation technology and data fusion analysis. It can monitor the operating status of the generator set in real time, automatically distinguish between planned shutdowns and unplanned shutdowns, and automatically generate and report when an unplanned shutdown event occurs.

[0041] Through automated and standardized monitoring processes, the problems of inefficiency, feedback lag and inaccurate data in traditional methods have been significantly improved, ensuring the stability and reliability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0043] Figure 1 An overall flow chart of a model-driven unit non-shutdown supervision method provided for one embodiment of the present invention.

[0044] Figure 2 An event reporting flow chart of a model-driven unit non-shutdown supervision method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Example 1

[0048] Reference Figure 1-Figure 2 , is an embodiment of the present invention, and provides a non-stop supervision method for a unit based on model driving, comprising:

[0049] Step S101: Real-time monitoring of the unit start-stop supervision model.

[0050] Step S102: The unit start-stop supervision model is triggered.

[0051] Step S103: Push the running or stopping status to the start and stop record, and automatically generate a new start and stop record.

[0052] Step S104: Mark the outage type to the outage record of the current unit.

[0053] Step S105: Automatically report the outage information of type "non-outage".

[0054] Specifically, determine the closing status of the generator output circuit breaker and obtain the steam turbine speed information; build a unit start and stop supervision model to determine the unit operating status; the unit operating status includes operating status and shutdown status; determine the unit shutdown type, and build a unit shutdown ledger based on the unit shutdown type.

[0055] Judging the closing status of the generator output circuit breaker includes analyzing the operating conditions of the circuit breaker through multi-physics field simulation technology, placing sensors at key locations where abnormalities are prone to occur during operation, and monitoring stress data, temperature data, and electromagnetic field data in real time; analyzing the external environment of the circuit breaker, placing sensors in areas susceptible to environmental noise and electromagnetic interference, and monitoring environmental noise data and electromagnetic interference data; and placing measurement points in the vicinity of the circuit breaker to detect common-mode noise data and vibration data in the electrical system.

[0056] The data of different measuring points are normalized and the closing state evaluation model is constructed, which is expressed as:

[0057] ,

[0058] ,

[0059] ,

[0060] ,

[0061] ,

[0062] ,

[0063] ,

[0064] ,

[0065] in, represents the total thermal stress, represents the base stress, represents the thermal expansion coefficient of the material, represents Young's modulus, Indicates temperature change, represents the electromagnetic stress, represents the internal electromagnetic field strength, is the magnetic permeability in vacuum, represents the total stress, represents the noise power density, Indicates the intensity of ambient noise, represents acoustic impedance, represents the electromagnetic interference power density, Indicates the strength of external electromagnetic interference, represents electrical impedance, represents the total power density of external interference, Indicates the system health state energy, represents the common-mode noise voltage, represents the vibration acceleration, Indicates the quality of the circuit breaker. represents the comprehensive evaluation index, represents the maximum allowable stress, represents the maximum permissible interference power density, Indicates the maximum allowable health state energy.

[0066] like >Preset state judgment threshold to judge whether the circuit breaker is in the closed state. ≤ the preset status judgment threshold, judging that the circuit breaker is in the disconnected state.

[0067] Obtaining turbine speed information includes determining the key measuring point locations of turbine shaft sections through mechanical vibration analysis, moment of inertia analysis, and thermal effect analysis; mechanical vibration analysis uses finite element analysis to simulate the vibration mode of the turbine rotor, identify the anti-nodes and node locations in the vibration mode, and select the vibration mode nodes to arrange measuring points; moment of inertia analysis calculates the distribution of the rotor's moment of inertia along the axial direction, identifies the inertia mutation points, and arranges measuring points at the inertia mutation points; thermal effect analysis uses thermodynamic simulation to analyze the temperature distribution under different operating conditions, identifies areas where the temperature gradient is greater than the preset temperature threshold, and arranges measuring points; sensors are installed at the measuring points to measure the speed, vibration, and temperature data in real time, and pre-process the data.

[0068] In data preprocessing, the speed measurement results are corrected by vibration data and temperature data to eliminate the influence of mechanical vibration and thermal expansion on the speed measurement, which is expressed as:

[0069] ,

[0070] ,

[0071] ,

[0072] in, Indicates measuring point The corrected speed value, Indicates measuring point The raw speed measurement value, Indicates measuring point Correction factors based on vibration data, Indicates measuring point The vibration acceleration at Indicates the maximum allowable value of vibration acceleration, Indicates measuring point Correction factors based on temperature data, Indicates measuring point The temperature change at Indicates the maximum allowable value of temperature change.

[0073] Construct the speed fusion analysis model, expressed as,

[0074] ,

[0075] in, Represents the final speed value after fusion, Indicates measuring point The weight of Indicates measuring point The corrected speed value, Indicates the number of measurement points, Indicates the number of the measuring point; when >Minimum operating speed threshold and the circuit breaker is in the closed state, the unit is judged to be in the operating state, otherwise the unit is judged to be in the shutdown state.

[0076] The unit shutdown type is judged by logic one, logic two, logic three and logic four; if logic one, logic two, logic three and logic four all meet the preset standards, it is judged as a planned shutdown; if logic four meets the preset standards, but any of logic one, logic two and logic three does not meet the preset standards, it is judged as an unplanned shutdown.

[0077] If logic four does not meet the preset standard, it is judged as preparing to shut down, and the monitoring frequency of the preparing to shut down state is increased.

[0078] Logic one is to determine the rate of decrease of operating pressure during normal load reduction of the unit; Logic two is to determine the allowable load state of normal shutdown of the unit; Logic three is to determine the allowable load decrease rate during normal load reduction of the unit; Logic four is to determine the tripping state of the unit.

[0079] Determining the normal operating pressure drop rate of the unit for load reduction includes obtaining the main steam pressure value on the boiler side from the SIS database; calculating the pressure drop rate of the main steam pressure on the boiler side within 30 minutes; if the pressure drop rate is ≤0 and the absolute value of the pressure drop rate is ≤ the power plant operating pressure reduction rate; judging that logic one meets the preset standard, if any condition is not met, judging that logic one does not meet the preset standard; judging the load allowable state of the unit for normal shutdown includes obtaining the unit load value from the SIS database, calculating the average value of the unit load for 10 minutes, and when the average value is less than 15% of the rated load, judging that logic two meets the preset standard, otherwise judging that logic two does not meet the preset standard. Meet the preset standard; determine the allowable load reduction rate of normal unit load reduction, including obtaining the unit load value from the SIS database; calculate the load reduction rate of the unit within 30 minutes; if the load reduction rate is ≤0 and the absolute value of the load reduction rate is ≤the power plant operation load reduction rate; determine that logic three meets the preset standard, if any condition is not met, determine that logic three does not meet the preset standard; determine the unit tripping status, including reading the turbine tripping signal and the boiler main fuel tripping signal from the SIS database, if the turbine tripping signal and the boiler main fuel tripping signal both show tripping, determine that logic four meets the preset standard, otherwise determine that logic four does not meet the preset standard.

[0080] Building a unit shutdown ledger includes pushing the shutdown or operation record to the unit shutdown ledger when the unit is monitored to be shut down or running; recording the time when the start-stop supervision model is triggered as the start time of the unit status; the unit status switches between the running status and the shutdown status, and when switching to the next status, the start time of the next status is the end time of the previous status; recording the duration of the unit status as the end time of the previous status minus the start time of the unit status; if the unit status is not switched, the duration is the current time minus the start time of the unit status; when a planned shutdown or unplanned shutdown is monitored, the shutdown record is marked as a planned shutdown or unplanned shutdown; when an unplanned shutdown of the unit is monitored, the unit shutdown ledger information is automatically reported immediately through the interface.

[0081] like Figure 2 As shown, the power plant management system provides basic information of the unit, and the power plant SIS system provides real-time data of unit operation, which is input into the start-stop supervision system, and the non-stop time is automatically reported to the superior supervision and management department.

[0082] Example 2

[0083] According to an embodiment of the present invention, a model-driven non-stop monitoring system for a unit is provided, comprising:

[0084] Data acquisition module, start-stop supervision module and shutdown supervision module.

[0085] The data acquisition module is used to determine the closing status of the generator output circuit breaker and obtain the turbine speed information.

[0086] The start-stop supervision module is used to build a unit start-stop supervision model to determine the unit operating status; the unit operating status includes the operating status and the shutdown status.

[0087] The shutdown supervision module is used to determine the shutdown type of the unit and build a unit shutdown ledger based on the unit shutdown type.

[0088] Example 3

[0089] An embodiment of the present invention is different from the first two embodiments in that:

[0090] The present invention proposes a model-driven non-stop monitoring method for a generator set, which detects potential non-stop operation failures in advance and issues an early warning by real-time monitoring and prediction of the operating status of the generator set. In this embodiment, if the method of the present invention is sold or used as an independent product, it can be implemented by a computer device and stored in a computer-readable storage medium.

[0091] Specifically, the method of the present invention includes the following core steps: first, the system collects the real-time data and historical data of the unit, combines it with the external environment data, and builds a prediction model; then, the data is processed and analyzed by computer equipment to determine whether the unit has a potential non-shutdown risk; finally, early warning information is generated and feedback is provided to the operator through a visual interface. All steps of the method can be executed by computer programs, and these programs are stored in a computer-readable storage medium.

[0092] Based on this implementation, the technical solution of the present invention can exist in the form of computer software, which contains several instructions that enable a computer device (such as a personal computer, a server or a network device) to perform all or part of the steps in the above method. Specifically, computer-readable storage media can store instructions for implementing the method of the present invention, and these storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk, optical disk and other media that can store program codes.

[0093] In addition, the program stored in the storage medium can control the computer equipment to perform the following functions: receive real-time data of the unit and transmit the data to the computer system through the communication interface; use the prediction model to analyze the data and identify potential non-shutdown risks; generate and output early warning information to provide decision support; and display the analysis results to the operator through visualization means and issue an alarm.

[0094] In the method flow of the present invention, the described logic and steps can be used as a sequenced list of executable instructions for implementing logical functions, and these instructions can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or equipment (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or equipment and execute instructions), or used in combination with these instruction execution systems, devices or equipment. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or equipment, or in combination with these instruction execution systems, devices or equipment.

[0095] More specific examples of computer-readable media (a non-exhaustive list) include: an electrical connection with one or more wires (electronic devices), a portable computer disk case (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0096] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0097] Example 4

[0098] An embodiment of the present invention provides a model-driven non-shutdown supervision method for a unit. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0099] In the implementation process of the present invention, in order to verify the effectiveness of the method of the present invention, a simulation model of an actual generator set is used, and the units involved include generators, steam turbines, circuit breakers, sensors and other equipment. Using MATLAB / Simulink and Ansys multi-physics field simulation software, the operation of the unit in normal operation, planned shutdown and unplanned shutdown is simulated, and the performance of the three monitoring methods in terms of data processing efficiency, false alarm rate, missed alarm rate and event reporting time is analyzed in detail.

[0100] In the experiment, traditional method 1 is a manual monitoring method, in which operators rely on manual collection and recording of the unit's operating data, and analyze the data to determine whether an unplanned shutdown event has occurred. The significant disadvantage of this method is that it is highly dependent on manual operation, resulting in high false alarm and missed alarm rates, and the manual confirmation process prolongs the time for event reporting. The experimental results show that when using traditional method 1, the false alarm rate is 15.4%, the missed alarm rate is 12.3%, the data processing time is an average of 35 minutes, and the event reporting time is an average of 60 minutes, indicating that when a unit fails or anomalies occur, the traditional method is difficult to respond in time and is easily interfered by human factors.

[0101] Traditional method 2 uses a semi-automated monitoring system that can automatically collect some data and generate preliminary reports, but it still requires manual review and judgment. This method improves the efficiency of data processing to a certain extent, but due to the existence of manual intervention, the problems of false alarms and missed alarms have not been fundamentally solved. The experimental results show that the false alarm rate of traditional method 2 is 8.7%, the missed alarm rate is 7.2%, and the data processing time is shortened to 18 minutes, but the event reporting time is still 35 minutes, which still has a certain delay.

[0102] In comparison, the method of the present invention can automatically collect and process data in real time without human intervention through a model-driven intelligent monitoring system. The method relies on an intelligent model to judge the operating status of the unit, automatically distinguish between planned outages and unplanned outages, and generate reports in real time, which are directly reported to the regulatory authorities. Experimental results show that the false alarm rate of the method of the present invention is only 1.8%, the missed alarm rate is 0.9%, the data processing time is 5 minutes, and the event reporting time is 10 minutes, showing the significant advantages of the method of the present invention in efficiency and accuracy. Through real-time analysis of intelligent models, the present invention can process large amounts of complex data in a shorter time and make more accurate judgments, thereby effectively reducing the false alarm rate and missed alarm rate.

[0103] First, this embodiment greatly improves the efficiency of data processing through automatic analysis of the intelligent model, and can complete the entire process of data collection, analysis and report generation in a very short time. Secondly, the intelligent model can combine the various operating parameters of the unit to comprehensively analyze the status of the unit to ensure that unplanned shutdown events can be accurately identified in a timely manner, thereby avoiding false alarms and omissions caused by human factors in traditional methods. Finally, the automation characteristics of the method of the present invention greatly shorten the time for event reporting, allowing regulatory authorities to obtain event reports in a shorter time, facilitating timely response measures to ensure the safe operation of the unit.

[0104] The technical solution of the present invention, relying on the automated monitoring and report generation system driven by intelligent models, solves the problems of false alarms, missed alarms and slow response commonly found in traditional methods. Through the application of the present invention, the monitoring and processing efficiency of unit non-stop events has been greatly improved, while the accuracy and real-time performance have also been effectively guaranteed.

[0105] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A model-driven unit non-stop supervision method, characterized in that: include: Determine the closing status of the generator output circuit breaker and obtain the turbine speed information; Build a unit start-stop supervision model to determine the unit operating status; The unit operation status includes an operation status and a shutdown status; Determine the unit shutdown type and build a unit shutdown ledger based on the unit shutdown type; Determining the closing state of the generator outlet circuit breaker includes analyzing the operating conditions of the circuit breaker through multi-physics field simulation technology, arranging sensors at key locations prone to abnormalities during operation, and monitoring stress data, temperature data, and electromagnetic field data in real time; Analyze the external environment of the circuit breaker, place sensors in areas susceptible to environmental noise and electromagnetic interference, and monitor environmental noise data and electromagnetic interference data; Arrange measurement points in the vicinity of the circuit breaker to detect common mode noise and vibration data in the electrical system; The data of different measuring points are normalized and the closing state evaluation model is constructed, which is expressed as: s h =σ+α×E×ΔT Among them, σ h represents the total thermal stress, σ represents the basic stress, α represents the thermal expansion coefficient of the material, E represents the Young's modulus, ΔT represents the temperature change, σ m represents electromagnetic stress, B1 represents the internal electromagnetic field strength, μ0 represents the magnetic permeability in vacuum, σ t represents the total stress, P n represents the noise power density, L n Indicates the intensity of environmental noise, Z a Represents acoustic impedance, P m represents the electromagnetic interference power density, B2 represents the external electromagnetic interference intensity, Z e Represents electrical impedance, P x Represents the total power density of external interference, E h Represents the system health state energy, V c represents the common mode noise voltage, a v represents vibration acceleration, m represents the mass of the circuit breaker, I ev represents the comprehensive evaluation index, σ max Indicates the maximum allowable stress, P x_max Indicates the maximum permissible interference power density, E h_max It represents the maximum allowable health state energy; If I ev >Preset state judgment threshold, judge that the circuit breaker is in the closed state, if I ev ≤ the preset status judgment threshold, judging that the circuit breaker is in the disconnected state.

2. The model-driven non-stop supervision method for a unit as claimed in claim 1, characterized in that: The obtaining of the turbine speed information includes determining the key measuring point positions of the turbine shaft section through mechanical vibration analysis, moment of inertia analysis and thermal effect analysis; The mechanical vibration analysis uses finite element analysis to simulate the vibration mode of the steam turbine rotor, identify the anti-nodes and node positions in the vibration mode, and select the vibration mode nodes to arrange the measurement points; The moment of inertia analysis calculates the distribution of the moment of inertia of the rotor along the axial direction, identifies the inertia mutation point, and arranges measurement points at the inertia mutation point; The thermal effect analysis analyzes the temperature distribution under different working conditions through thermodynamic simulation, identifies the areas where the temperature gradient is greater than the preset temperature threshold and arranges the measuring points; Install sensors at the measuring points to measure the speed, vibration and temperature data in real time and pre-process the data; In data preprocessing, the speed measurement results are corrected by vibration data and temperature data, which is expressed as, oh c,i =ω i ×(1-C vi )×(1-C ti ) Among them, ω c,i Indicates the corrected speed value of measuring point i, ω i Represents the original speed measurement value of measuring point i, C vi Indicates the correction coefficient of the measuring point i based on the vibration data, a i represents the vibration acceleration at measuring point i, a max Indicates the maximum allowable value of vibration acceleration, C ti Indicates the correction coefficient of the temperature data at the measuring point i, ΔT i Represents the temperature change at measuring point i, ΔT max Indicates the maximum allowable value of temperature change; Construct the speed fusion analysis model, expressed as, Among them, ω f Indicates the final rotation speed value after fusion, w i represents the weight of the measuring point i, ω c,i It indicates the corrected speed value of measuring point i, n indicates the number of measuring points, and i indicates the number of measuring points; When f >Minimum operating speed threshold and the circuit breaker is in the closed state, the unit is judged to be in the operating state, otherwise the unit is judged to be in the shutdown state.

3. The model-driven non-stop unit supervision method according to claim 1 or 2, characterized in that: The shutdown type of the unit is determined by logic one, logic two, logic three and logic four; If logic 1, logic 2, logic 3 and logic 4 all meet the preset standards, it is judged as a planned outage; If logic 4 meets the preset standard, but any of logic 1, logic 2 and logic 3 does not meet the preset standard, it is judged as an unplanned outage; The first logic is to determine the rate of decrease of the operating pressure of the unit during normal load reduction; The second logic is to determine the load permissible state of the unit for normal shutdown; The third logic is to determine the allowable load reduction rate of the unit for normal load reduction; The fourth logic is to determine the tripping state of the unit.

4. The model-driven non-stop supervision method for a unit according to claim 1 or 2, characterized in that: The operating pressure drop rate for judging the normal load reduction of the unit includes: Obtain the main steam pressure value on the boiler side from the SIS database; Calculate the rate of pressure drop of the main steam pressure on the boiler side within 30 minutes; If the rate of pressure drop is ≤0 and the absolute value of the rate of pressure drop is ≤ the power plant operation pressure drop rate; The judgment logic 1 meets the preset standard. If any condition is not met, the judgment logic 1 does not meet the preset standard.

5. The model-driven non-stop monitoring method for a unit as claimed in claim 4, characterized in that: The load permissible state of judging the normal shutdown of the unit includes: The unit load value is obtained from the SIS database, and the average value of the computer unit load for 10 minutes is calculated. When the average value is less than 15% of the rated load, it is judged that logic 2 meets the preset standard, otherwise it is judged that logic 2 does not meet the preset standard.

6. The model-driven non-stop supervision method for a unit as claimed in claim 5, characterized in that: The allowable load reduction rate for judging the normal load reduction of the unit includes: Obtain unit load values ​​from the SIS database; The rate at which the computer group load is reduced within 30 minutes; if the rate of load reduction is ≤0 and the absolute value of the rate of load reduction is ≤ the power plant operation load reduction rate; the judgment logic three meets the preset standard, if any condition is not met, the judgment logic three does not meet the preset standard.

7. The model-driven non-stop supervision method for a unit according to claim 5 or 6, characterized in that: The step of judging the tripping state of the unit includes: The turbine trip signal and the boiler main fuel trip signal are read from the SIS database. If both the turbine trip signal and the boiler main fuel trip signal indicate tripping, it is judged that logic four meets the preset standard, otherwise it is judged that logic four does not meet the preset standard.

8. The model-driven non-stop supervision method for a unit as claimed in claim 5 or 6, characterized in that: The construction of the unit shutdown record includes: When the unit is detected to be shut down or running, the shutdown or running record is pushed to the unit shutdown ledger; The time when the start-stop supervision model is triggered is recorded as the start time of the unit status; The status of the unit switches between the running status and the shutdown status. When switching to the next status, the start time of the next status is the end time of the previous status; The duration of the recorded unit status is the end time of the previous status minus the start time of the unit status; If the unit status is not switched, the duration is the current time minus the start time of the unit status; When a planned outage or unplanned outage is detected, the outage record will be marked as planned outage or unplanned outage; When an unplanned shutdown of a unit is detected, the unit shutdown ledger information will be automatically reported through the interface.

9. A model-driven unit non-stop monitoring system, characterized by: include, A data acquisition module (100) is used to determine the closing state of the generator outlet circuit breaker and obtain turbine speed information; A start-stop supervision module (200) is used to construct a start-stop supervision model for the unit and determine the unit operation state; the unit operation state includes an operation state and a shutdown state; as well as, A shutdown monitoring module (300) is used to determine the shutdown type of the unit and to construct a shutdown record of the unit based on the shutdown type of the unit; Determining the closing state of the generator outlet circuit breaker includes analyzing the operating conditions of the circuit breaker through multi-physics field simulation technology, arranging sensors at key locations prone to abnormalities during operation, and monitoring stress data, temperature data, and electromagnetic field data in real time; Analyze the external environment of the circuit breaker, place sensors in areas susceptible to environmental noise and electromagnetic interference, and monitor environmental noise data and electromagnetic interference data; Arrange measurement points in the vicinity of the circuit breaker to detect common mode noise and vibration data in the electrical system; The data of different measuring points are normalized and the closing state evaluation model is constructed, which is expressed as: s h =σ+α×E×ΔT Among them, σ h represents the total thermal stress, σ represents the basic stress, α represents the thermal expansion coefficient of the material, E represents the Young's modulus, ΔT represents the temperature change, σ m represents electromagnetic stress, B1 represents the internal electromagnetic field strength, μ0 represents the magnetic permeability in vacuum, σ t represents the total stress, P n represents the noise power density, L n Indicates the intensity of environmental noise, Z a Represents acoustic impedance, P m represents the electromagnetic interference power density, B2 represents the external electromagnetic interference intensity, Z e Represents electrical impedance, P x Represents the total power density of external interference, E h Represents the system health state energy, V c represents the common mode noise voltage, a v represents vibration acceleration, m represents the mass of the circuit breaker, I ev represents the comprehensive evaluation index, σ max Indicates the maximum allowable stress, P x_max Indicates the maximum permissible interference power density, E h_max It represents the maximum allowable health state energy; If I ev >Preset state judgment threshold, judge that the circuit breaker is in the closed state, if I ev ≤ the preset status judgment threshold, judging that the circuit breaker is in the disconnected state.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the model-driven unit non-stop supervision method described in any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the model-driven unit non-stop supervision method described in any one of claims 1 to 8 are implemented.

Images