Coal-fired unit operation reliability real-time scoring method, system, equipment and medium

Abstract

The invention discloses a coal-fired unit operation reliability real-time scoring method, system and equipment and a medium, and relates to the technical field of coal-fired unit operation monitoring and evaluation, the method comprises the steps of obtaining real-time operation data of a power plant coal-fired unit, the coal-fired unit including the unit, the specialty, the system and the equipment from top to bottom; defining an early warning level in the digital twin modeling platform, setting a deduction weight of the early warning level, and establishing a virtual power plant hierarchical structure corresponding to the physical power plant; establishing an early warning model under each device in the virtual power plant hierarchical structure, and outputting an early warning result; calculating the real-time early warning quantity of each early warning level of the system and the real-time score of the system; and according to the system real-time score and the score proportion, calculating a professional real-time score and a unit real-time score, and performing display. The early warning score deduction model is established through the intelligent early warning model, the reliability scoring model is constructed in a layered mode, the operation reliability of the unit is scored in real time, and the service life of the unit is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of coal-fired unit operation monitoring and evaluation, in particular to a method, system, equipment and medium for real-time scoring of coal-fired unit operation reliability. Background Art

[0002] As an important part of power production, the operational reliability of coal-fired units is crucial to the stable operation of the power system and the continuity of power supply. After the "dual carbon" goal was proposed, the daily peak-shaving range of thermal power units continued to expand, and power generation auxiliary services such as deep peak-shaving, start-stop peak-shaving, and frequency regulation auxiliary services became the norm; at the same time, the requirements for energy conservation and emission reduction, environmental protection control, etc. of the units are becoming higher and higher, and the daily operation volume of operators has increased significantly, and the reliability of unit operation has decreased accordingly.

[0003] The traditional coal-fired unit operation reliability assessment relies on regular inspections by operators and real-time parameter monitoring of DCS, which is still insufficient in the real-time assessment of unit operation reliability. Therefore, the present invention proposes a real-time scoring method for coal-fired unit operation reliability, which can monitor the unit operation status in real time and score the operation reliability in real time according to the unit early warning situation, aiming to improve the operation reliability of coal-fired units. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is: how to solve the problem that the traditional coal-fired unit operation reliability assessment relies on regular inspections by operators and real-time parameter monitoring by DCS, and there are still deficiencies in the real-time assessment of unit operation reliability.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a real-time scoring method for the operation reliability of coal-fired units, comprising: obtaining real-time operation data of coal-fired units in power plants, wherein the actual levels of the coal-fired units from top to bottom include units, professions, systems and equipment; defining warning levels in a digital twin modeling platform, setting deduction weights for warning levels, and establishing a virtual power plant hierarchical structure corresponding to the physical power plant; building a warning model under each device in the virtual power plant hierarchical structure, and outputting warning results; calculating the number of real-time warnings at each warning level of the system and the real-time score of the system; and calculating the real-time score of the profession and the real-time score of the unit according to the real-time score of the system and the score ratio, and displaying them.

[0007] As a preferred scheme of the real-time scoring method for the operation reliability of coal-fired units described in the present invention, the real-time operation data of the coal-fired units in the power plant includes collecting the unit-level, system-level and equipment-level operating parameters of the coal-fired units through the power plant's time series database or plant-level monitoring information system, and performing data preprocessing.

[0008] As an optimal solution of the real-time scoring method for the operation reliability of coal-fired units described in the present invention, wherein: the definition of warning level includes setting multiple warning levels according to the actual warning situation of the power plant; the virtual power plant hierarchical structure includes building the same digital twin device tree on the digital twin modeling platform according to the actual hierarchical units, disciplines, systems, and equipment from top to bottom of the power plant, to achieve a one-to-one mapping of each level of the physical power plant and the virtual power plant, each unit contains multiple disciplines, each discipline contains multiple systems, and each system contains multiple devices.

[0009] As a preferred solution of the real-time scoring method for the operation reliability of coal-fired units described in the present invention, the building of the early warning model includes building an intelligent early warning model logic under each device, wherein each device has multiple intelligent early warning models. After the logic of each intelligent early warning model is built, the corresponding monitoring points are selected in the digital twin modeling platform for binding according to the input parameters of the model. After the monitoring point binding is completed, according to the actual early warning content, a level is selected from the defined early warning levels for configuration; after completing all the configurations of the early warning model, the early warning model is published for real-time monitoring. Each early warning model output has two results. If the model logic does not meet the conditions and no early warning is triggered, the model output value is 0. If the model logic meets the conditions and triggers the early warning, the model output value is 1, and an intelligent early warning is generated.

[0010] As a preferred solution of the real-time scoring method for the operation reliability of coal-fired units of the present invention, the number of real-time warnings at each warning level of the system includes the sum of the number of real-time warnings at the current warning level of equipment No. 1 to No. n in the system, expressed as:

[0011]

[0012] in, is the number of real-time warnings at the current warning level of the system, is the current warning level of the system, is the number of devices in the system, For the system 1 to The real-time scoring of the system includes setting the total score of the system, and calculating the real-time scoring of the system in real time according to the number of real-time warnings and the deduction weight of each warning level under the system, which is expressed as:

[0013]

[0014] in, Score the system in real time. is the total score of the set system, is the number of real-time warnings at the current warning level of the system, is the deduction weight of the current warning level, Deduct points for the warning of the current warning level of the system. For the system 1 to The sum of warning points for each warning level, is the number of warning levels.

[0015] As a preferred solution of the real-time scoring method for the operation reliability of coal-fired units of the present invention, the real-time scoring of the profession includes setting the score proportion of each system under each profession, and calculating the real-time score of the profession according to the real-time score and score proportion of each system, which is expressed as:

[0016]

[0017] in, Real-time rating for professionalism, Score the system in real time. is the set system score ratio, is the score of the system under the current proportion, For professional 1 to The sum of the scores under the current system proportion is the real-time score of this major. is the number of systems under the profession; the sum of the score proportions of each system under each profession is 1; the real-time score of the unit includes setting the score proportions of each profession under each unit, and according to the real-time score and score proportion of each profession, the real-time score of the real-time computer group is expressed as:

[0018]

[0019] in, Provide real-time rating for the crew. Real-time rating for professionalism, is the set professional score ratio, is the score of the current proportion of the major, For the unit, 1 to The sum of the scores under the current professional proportion is the real-time score of the team. It is the total number of specialties under the unit; the sum of the score proportions of each specialty under each unit is 1.

[0020] As a preferred solution of the real-time scoring method for the operation reliability of coal-fired units described in the present invention, the display includes setting different color displays for different score intervals, and obtaining the current operation reliability status of each unit, specialty and system in real time according to the color and score, and focusing on monitoring, adjusting and inspecting the systems with low scores.

[0021] Another object of the present invention is to provide a system for a real-time scoring method for coal-fired unit operation reliability, which can solve the problem of real-time scoring of coal-fired unit operation reliability by constructing a coal-fired unit operation reliability scoring system.

[0022] To solve the above technical problems, the present invention provides the following technical solutions: a real-time scoring system for the operation reliability of coal-fired units, including a data acquisition module for obtaining real-time operation data of coal-fired units in power plants, wherein the actual levels of the coal-fired units from top to bottom include units, professions, systems and equipment; a hierarchical structure construction module for defining warning levels in a digital twin modeling platform, setting deduction weights for warning levels, and establishing a virtual power plant hierarchical structure corresponding to a physical power plant; an equipment warning module for building a warning model under each device in the virtual power plant hierarchical structure and outputting warning results; a system warning scoring module for calculating the number of real-time warnings and the real-time score of the system at each warning level; and a scoring module for calculating the real-time score of the profession and the real-time score of the unit according to the real-time score of the system and the score proportion, and displaying them.

[0023] 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 method for real-time scoring of operating reliability of coal-fired units when executing the computer program.

[0024] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for real-time scoring of operating reliability of a coal-fired unit.

[0025] The beneficial effects of the present invention are as follows: the real-time scoring method for the operation reliability of coal-fired units provided by the present invention can timely detect abnormalities and potential faults in the operation of coal-fired units by real-time monitoring of the operation status of coal-fired units, and remind operators to take corresponding measures through the early warning mechanism, thereby effectively preventing equipment failures and improving the overall operation reliability of the units. Through real-time monitoring and early warning, this method helps to avoid sudden shutdowns or accidents caused by failures of coal-fired units, ensure the safe and stable operation of the power grid, and reduce the risk of casualties caused by equipment failures. An early warning deduction model is established through an intelligent early warning model, and a "unit-professional-system" reliability scoring model is constructed in layers to score the operation reliability of the unit in real time, providing operators with intuitive reliability evaluation results, which helps to formulate more accurate and efficient maintenance plans, reduce unnecessary maintenance costs, and extend the service life of the unit. The integration of intelligent early warning and comprehensive evaluation algorithms realizes the intelligent evaluation and management of the operation reliability of coal-fired units. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] 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 labor.

[0027] Figure 1 This is a flow chart of a method for real-time scoring of operating reliability of a coal-fired unit provided in the first embodiment of the present invention.

[0028] Figure 2 This is a structural diagram of a real-time scoring system for coal-fired unit operation reliability provided in the third embodiment of the present invention.

[0029] Figure 3 This is a diagram of an operation reliability scoring grading interface for a real-time scoring method for operation reliability of a coal-fired unit provided in the fifth embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the above-mentioned objects, 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 accompanying drawings.

[0031] 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.

[0032] Example 1

[0033] Reference Figure 1 , which is the first embodiment of the present invention, and this embodiment provides a real-time scoring method for the operation reliability of coal-fired units, including: obtaining real-time operation data of coal-fired units in power plants, wherein the actual levels of the coal-fired units from top to bottom include units, professions, systems and equipment; defining warning levels in a digital twin modeling platform, setting deduction weights for warning levels, and establishing a virtual power plant hierarchical structure corresponding to a physical power plant; building a warning model under each device in the virtual power plant hierarchical structure, and outputting warning results; calculating the number of real-time warnings at each warning level of the system and the real-time score of the system; calculating the real-time score of the profession and the real-time score of the unit according to the real-time score of the system and the score proportion, and displaying them.

[0034] S1. Data collection: Obtain real-time operation data of coal-fired units in power plants through the time series database of power plant production and operation or the plant-level monitoring information system (SIS).

[0035] Obtain real-time operating data of coal-fired units in power plants.

[0036] The actual hierarchy of coal-fired units from top to bottom includes units, disciplines, systems and equipment.

[0037] The real-time operation data of power plant units, disciplines, systems and equipment are obtained through the time series database of power plant production and operation or the time series database of the plant-level supervisory information system (SIS) for use in various intelligent early warning models.

[0038] S2. Digital twin modeling: Define the warning level in the digital twin modeling platform, set the deduction weight of the warning level, and establish a virtual power plant hierarchical structure corresponding to the physical power plant to achieve a one-to-one mapping between the physical power plant and the virtual power plant.

[0039] Define the warning level in the digital twin modeling platform, set the deduction weight of the warning level, and establish a virtual power plant hierarchical structure corresponding to the physical power plant.

[0040] Flexible warning level definitions can be made in the digital twin modeling platform. Warning levels can be defined based on the actual operating conditions and specific needs of the power plant and used for warning level configuration of each intelligent warning model.

[0041] According to the actual hierarchy of the power plant from top to bottom, unit-professional-system-equipment, the same digital twin device tree is built on the digital twin modeling platform to achieve a one-to-one mapping of each level of the physical power plant and the virtual power plant. Each "unit" contains multiple "professionals", each "professional" contains multiple "systems", and each "system" contains multiple "equipment".

[0042] S3. Early warning model construction and release: Build an early warning model under each device in the virtual power plant hierarchy and output the early warning results. Real-time monitoring and intelligent early warning are achieved through measurement point binding, early warning level configuration and fault knowledge base association.

[0043] Build an early warning model under each device in the virtual power plant hierarchy and output the early warning results.

[0044] According to the existing model list and model logic description, build the intelligent early warning model logic under each "device". Each "device" has multiple intelligent early warning models.

[0045] After the logic of each intelligent early warning model is built, the corresponding monitoring points are selected in the platform for binding according to the input parameters of the model.

[0046] After completing the measurement point binding, according to the actual warning content, select a level from the defined warning levels for configuration. At the same time, you can configure the phenomenon, cause and treatment measures of the fault to achieve the association between the warning and fault knowledge base.

[0047] After completing all the configurations of the early warning model, the early warning model is released. The released early warning model is immediately online and starts real-time monitoring. Each early warning model output has two results. When the model logic does not meet the conditions and no early warning is triggered, the model output value is 0; if the model logic meets the conditions and triggers the early warning, the model output value is 1, generating an intelligent early warning.

[0048] According to the actual operation status and specific needs of the power plant, the deduction weight for each warning level is set in the digital twin modeling platform.

[0049] S4. Calculation of the number of real-time warnings and system scores: Calculate the number of real-time warnings for each warning level of the system, and calculate the system score in real time based on the number of warnings and the deduction weight.

[0050] Calculate the number of real-time warnings and the real-time score of the system for each warning level.

[0051] Calculate the number of real-time warnings for each warning level under the "system" in real time, expressed as,

[0052] (1)

[0053] in, is the number of real-time warnings at the current warning level of the "system", is the current warning level of the "system", The sum of the real-time warning numbers of the current warning levels of devices 1 to n under this "system".

[0054] The total score of the system is set according to the actual operation status and specific needs of the power plant, and then the real-time score of the "system" is calculated in real time according to the number of real-time warnings and the deduction weights of each warning level under the "system".

[0055] (2)

[0056] in, Score the system in real time. is the total score of the set system, is the number of real-time warnings at the current warning level of the system, is the deduction weight of the current warning level, Deduct points for the warning of the current warning level of the system. For the system 1 to The sum of the warning points of the warning level (i.e. the system warning points), is the number of warning levels.

[0057] S5. Calculation and display of crew, professional and system scores: Based on the system score and score ratio, the real-time score of the professional and crew is calculated and displayed through the front-end interface.

[0058] According to the system's real-time score and score ratio, the professional's real-time score and the crew's real-time score are calculated and displayed.

[0059] According to the actual operation and specific needs of the power plant, the score ratio of each "system" under each "professional" is set, and then the real-time score of the "professional" is calculated in real time according to the real-time score and score ratio of each "system", which is expressed as:

[0060] (3)

[0061] in, Give a real-time rating for "Professional". Score the system in real time. is the set “system” score ratio, is the score of the current proportion of "system". For "Professional", click 1 to The sum of the scores under the current system proportion (i.e. the real-time score of this major), The number of "systems" under "majors". The sum of the scores of each "system" under each "major" should be equal to 1.

[0062] According to the actual operation and specific needs of the power plant, the score ratio of each "professional" under each "unit" is set, and then the real-time score of the "unit" is calculated in real time according to the real-time score and score ratio of each "professional", which is expressed as:

[0063] (4)

[0064] in, Score the crew in real time. Give a real-time rating for "Professional". is the percentage of "professional" score set, is the score of "Professional" under the current proportion. For "Unit", click 1 to Sum the scores of the current professional proportion (i.e. the real-time score of the group), The total number of "professions" under "crews". The sum of the score proportions of each "profession" under each "crew" should be equal to 1.

[0065] S6. Through colors and scores, operators and managers can understand the current operating reliability status of each level of the power plant in real time, and conduct targeted monitoring, adjustments and inspections to avoid equipment failures and accidents.

[0066] The real-time calculated scores of units, disciplines and systems are displayed on the front-end interface. Different colors can be set for different score intervals according to the actual operation status and specific needs of the power plant. Operators and managers can obtain the current operating reliability status of each unit, discipline and system in real time based on the color and score, and focus on monitoring, adjusting and inspecting systems with low status scores to avoid equipment failures and accidents.

[0067] Example 2

[0068] The second embodiment of the present invention is different from the previous embodiment in that it provides a specific application of a real-time scoring method for the operating reliability of a coal-fired unit.

[0069] Real-time data collection, preprocessing and storage: The operating data of power plant units, systems and equipment are obtained through the time series database of power plant production and operation or the time series database of the plant-level supervisory information system (SIS), and data collection protocol analysis, edge computing and device access are implemented at the edge layer based on the Internet of Things platform.

[0070] Intelligent early warning system construction: Through the digital twin modeling platform, according to the actual organizational level of the physical power plant, the three-level distributed modeling method of "unit-professional-system" is adopted to achieve a one-to-one mapping of the organizational levels of the physical power plant and the virtual power plant. The intelligent early warning system covers the three major disciplines of power plant boilers, steam turbines, and electrical, and 40 systems. An intelligent early warning model is established for each system.

[0071] In the model canvas, the early warning model is constructed by "drag and drop", which supports the calling of multiple function algorithms and logical operation rules. After completing the configuration of the model logic rules, the indicator parameters are associated with the real-time measurement points in the time series database, and batch import and export are supported. After the measurement points are bound, the model canvas supports online verification and real-time viewing of output results.

[0072] After the early warning model logic is built, the alarm level (level 1, 2, and 3) of the intelligent early warning model is defined. At the same time, the phenomenon, cause, and treatment measures of the fault can be configured to realize the association between the early warning model and the fault knowledge base. After all the configurations of the early warning model are completed, the early warning model is released. The released early warning model is immediately online and begins monitoring. Each early warning model output has two results. When the model logic does not meet the conditions and the early warning is not triggered, the model output value is 0; if the model logic meets the conditions to trigger the early warning, the model output value is 1.

[0073] Use the "drag and drop" method in the model canvas to build the early warning deduction model for each system. First, output all the intelligent early warning models at the system level in the canvas (0 or 1), and add the first, second, and third levels according to the alarm level of the intelligent early warning model, and then multiply by the weight corresponding to each alarm level. The first alarm weight is 3, the second alarm weight is 2, and the third alarm weight is 1. The deductions for the three alarm levels are obtained respectively, and then the deductions for the three alarm levels are added together to obtain the intelligent early warning deductions for the system level in real time.

[0074] In the model canvas, the scoring model is constructed by "drag and drop" according to the "unit-professional-system-parameter" layering. According to the operating procedures and actual conditions on site, different weights are set for professions and systems according to the importance of affecting the operation of the unit. The sum of all system weights under each profession is equal to 1, and the sum of all professional weights under each unit is equal to 1. The system score is equal to 100 points minus the system warning deduction and system deviation deduction. The professional score is equal to the score of each system under the profession multiplied by their respective weights and then added together. The unit score is equal to the score of each professional under the unit multiplied by their respective weights and then added together. The real-time computer group operation reliability score.

[0075] Example 3

[0076] Reference Figure 2 , which is the third embodiment of the present invention, is different from the first two embodiments in that it provides a real-time scoring system for the operation reliability of coal-fired units, including:

[0077] The data acquisition module 100 is used to obtain real-time operating data of the coal-fired units in the power plant, and the actual levels of the coal-fired units from top to bottom include units, specialties, systems and equipment.

[0078] The hierarchical structure building module 200 is used to define the warning level in the digital twin modeling platform, set the deduction weight of the warning level, and establish a virtual power plant hierarchical structure corresponding to the physical power plant.

[0079] The equipment warning module 300 is used to build a warning model under each equipment in the virtual power plant hierarchy and output the warning result.

[0080] The system warning scoring module 400 is used to calculate the number of real-time warnings and the real-time score of the system at each warning level of the system.

[0081] The scoring module 500 is used to calculate the real-time score of the profession and the real-time score of the crew according to the real-time score of the system and the score ratio, and display them.

[0082] Example 4

[0083] An embodiment of the present invention is different from the first three embodiments in that:

[0084] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0085] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (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 apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes 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 apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0086] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), 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.

[0087] 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, a plurality of 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 their combination: 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.

[0088] Example 5

[0089] Reference Figure 3 , which is the fifth embodiment of the present invention, and is different from the previous three embodiments in that it is used to verify and illustrate the technical effects adopted in the present invention in order to verify the real effects of this method.

[0090] A certain plant transmits the DCS measurement point signal generated in Zone 1 to the time series database of the plant-level supervisory information system (SIS) in Zone 3 through a data link, and then transmits the measurement point information and data in the plant-level supervisory information system time series database to the time series database of the intelligent early warning system through a data link to obtain complete measurement point data. Then, an intelligent early warning system was built on a set of units on the digital twin platform, including 1,175 intelligent early warning models. Based on the intelligent early warning system, 468 operation reliability scoring models were constructed, realizing the "unit-professional-system" hierarchical scoring, providing early warning information and operation reliability evaluation results to operators in real time.

[0091] A factory transmits the DCS measurement point signal generated in zone one to the time series database of the plant-level supervisory information system (SIS) in zone three through a data link, and then transmits the measurement point information and data in the time series database of the plant-level supervisory information system to the time series database of the intelligent early warning system through a data link to obtain complete measurement point data.

[0092] According to the actual situation, three warning levels were defined in the digital twin platform: level one warning, level two warning, and level three warning. Then, an intelligent warning system was built on a set of units on the digital twin platform, including 1,175 intelligent warning models.

[0093] According to the survey of power plants and the operation requirements of power plants, the reliability level of each system is divided into four levels: reliable, good, general and unreliable. Among them, the first-level warning is less than or equal to 1, the second-level warning is less than or equal to 1, and the third-level warning is less than or equal to 1, and the system status is reliable; the first-level warning is less than or equal to 2, the second-level warning is less than or equal to 2, and the third-level warning is less than or equal to 2, and the system status is good; the first-level warning is less than or equal to 4, the second-level warning is less than or equal to 4, and the third-level warning is less than or equal to 4, and the system status is general; the first-level warning is greater than 4, the second-level warning is greater than or equal to 4, and the third-level warning is greater than 4, and the system status is general. Set the initial system score to 100 points. After the warning deduction and parameter deviation deduction, the score greater than or equal to 95 points is reliable, less than 95 and greater than 90 is good, less than 90 and greater than 80 is general, and less than 80 is unreliable. Following this rule, the weight of the first-level warning in each warning deduction is set to 3, the weight of the second-level warning is 2, and the weight of the third-level warning is 1.

[0094] According to the operating procedures and actual on-site conditions, the total system score is set to 100 points, and different scoring ratios are set for systems and disciplines according to their importance in affecting unit operations. The sum of all system weights under each discipline is equal to 1, and the sum of all professional weights under each unit is equal to 1.

[0095] Based on the intelligent early warning system, 468 operation reliability scoring models were built. The “unit-professional-system” hierarchical scoring was implemented to provide operation reliability evaluation results to operators in real time. Figure 3 As shown, steam turbine, electrical, boiler and environmental protection are majors. The systems under the steam turbine major include steam turbine body system, main engine lubricating oil system, EH oil system, main reheat steam and bypass discharge system, water supply system, condensate system, heater system and vacuum system, etc.; the systems under the electrical major include generator-transformer system and plant power system; the systems under the boiler major include pulverizing system, air and smoke system, steam-water system, boiler heating surface, denitrification system and boiler sulfur drain system, etc.; the systems under the environmental protection major include desulfurization system, and the systems are scored separately to obtain professional scores and unit scores.

[0096] The system score is equal to 100 points minus the system deduction points. The professional score is equal to the scores of each system under the profession multiplied by the proportion of each score and then added together. The unit score is equal to the scores of each profession under the unit multiplied by the proportion of each score and then added together. The real-time computer group operation reliability score.

[0097] If the score of the unit, specialty or system is greater than or equal to 95, it is reliable and the front-end displays green; if it is less than 95 and greater than or equal to 90, it is good and the front-end displays blue; if it is less than 90 and greater than or equal to 80, it is fair and the front-end displays orange; if it is less than 80, it is unreliable and the front-end displays red. Operators and managers can obtain the current operating reliability status of each system in real time based on the color and score, and focus on monitoring, adjusting and inspecting the systems with low status scores to avoid equipment failures and accidents.

[0098] 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 real-time scoring method for the operation reliability of a coal-fired unit, characterized by: include, Obtain real-time operation data of coal-fired units in power plants, where the actual hierarchy of coal-fired units from top to bottom includes units, disciplines, systems and equipment; Define the warning level in the digital twin modeling platform, set the deduction weight of the warning level, and establish a virtual power plant hierarchical structure corresponding to the physical power plant; Build an early warning model under each device in the virtual power plant hierarchy and output the early warning results; Calculate the number of real-time warnings and the real-time score of the system for each warning level; According to the system's real-time score and score ratio, the professional's real-time score and the crew's real-time score are calculated and displayed.

2. The method for real-time scoring of the operation reliability of a coal-fired unit according to claim 1, characterized in that: The real-time operation data of the coal-fired units in the power plant include: The unit-level, system-level and equipment-level operating parameters of the coal-fired units are collected through the power plant's time series database or plant-level monitoring information system, and data preprocessing is performed.

3. The real-time scoring method for the operation reliability of a coal-fired unit according to claim 1 or 2, characterized in that: The defined warning levels include: Set multiple warning levels according to the actual warning situation of the power plant; The virtual power plant hierarchical structure includes building the same digital twin device tree on the digital twin modeling platform according to the actual hierarchical units, disciplines, systems, and equipment of the power plant from top to bottom, so as to realize a one-to-one mapping of each level between the physical power plant and the virtual power plant. Each unit contains multiple disciplines, each discipline contains multiple systems, and each system contains multiple devices.

4. The real-time scoring method for the operation reliability of a coal-fired unit according to claim 1 or 2, characterized in that: The building of the early warning model includes: Build the intelligent early warning model logic under each device, where each device has multiple intelligent early warning models. After each intelligent early warning model logic is built, select the corresponding monitoring point in the digital twin modeling platform for binding according to the input parameters of the model. After the measurement point binding is completed, select a level from the defined warning levels for configuration according to the actual warning content; After completing all the configurations of the early warning model, the early warning model is published and real-time monitoring is performed. Each early warning model output has two results. If the model logic does not meet the conditions and no early warning is triggered, the model output value is 0. If the model logic meets the conditions and triggers an early warning, the model output value is 1, generating an intelligent early warning.

5. The method for real-time scoring of the operation reliability of a coal-fired unit according to claim 4, characterized in that: The number of real-time warnings for each warning level of the system, include, The sum of the real-time warning quantity of the current warning level of equipment 1 to n in the system is expressed as, in, is the number of real-time warnings at the current warning level of the system, is the current warning level of the system, is the number of devices in the system, For the system 1 to Sum the number of real-time warnings of the current warning level of the equipment; The system scores in real time, including: Set the total score of the system, and calculate the real-time score of the system in real time according to the number of real-time warnings and the deduction weight of each warning level under the system, expressed as, in, Score the system in real time. is the total score of the set system, is the number of real-time warnings at the current warning level of the system, is the deduction weight of the current warning level, Deduct points for the warning of the current warning level of the system. For the system 1 to The sum of warning points for each warning level, is the number of warning levels.

6. The method for real-time scoring of the operation reliability of a coal-fired unit according to claim 5, characterized in that: Real-time rating of the said profession, include, Set the score ratio of each system under each major, and calculate the real-time score of the major according to the real-time score and score ratio of each system, expressed as, in, Real-time rating for professionalism, Score the system in real time. is the set system score ratio, is the score of the system under the current proportion, For professional 1 to The sum of the scores under the current system proportion is the real-time score of this major. The number of systems under the major; The sum of the scores of each system under each major is 1; The real-time rating of the crew includes, Set the score proportion of each major under each group. According to the real-time score and score proportion of each major, the real-time score of the computer group is expressed as, in, Provide real-time rating for the crew. Real-time rating for professionalism, is the set professional score ratio, is the score of the current proportion of the major, For the unit, 1 to The sum of the scores under the current professional proportion is the real-time score of the team. The total number of specialties under the crew; The sum of the scores of each specialty under each unit is 1.

7. The real-time scoring method for the operation reliability of a coal-fired unit according to claim 5 or 6, characterized in that: The display includes, Different color displays are set for different score ranges. Based on the colors and scores, the current operating reliability status of each unit, specialty and system can be obtained in real time, and the systems with low scores can be monitored, adjusted and inspected in detail.

8. A real-time scoring system for the operation reliability of coal-fired units, characterized by: include, A data acquisition module (100) is used to obtain real-time operating data of coal-fired units in a power plant, wherein the actual levels of the coal-fired units from top to bottom include units, specialties, systems and equipment; A hierarchical structure building module (200) is used to define the warning level in the digital twin modeling platform, set the deduction weight of the warning level, and establish a virtual power plant hierarchical structure corresponding to the physical power plant; An equipment early warning module (300) is used to build an early warning model under each equipment in the virtual power plant hierarchy structure and output an early warning result; A system warning scoring module (400) is used to calculate the number of real-time warnings and the real-time score of the system at each warning level; and The scoring module (500) is used to calculate the real-time score of the major and the real-time score of the crew according to the real-time score of the system and the score ratio, and display them.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for real-time scoring of the operating reliability of a coal-fired unit are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method for real-time scoring of the operating reliability of a coal-fired unit are implemented.

Images