A method and system for equipment reliability maintenance in smart power plants

Abstract

The present invention discloses a method for equipment reliability maintenance for smart power plants, which involves the technical field of equipment fault prediction and diagnosis, including: obtaining real-time equipment operation data, performing data quality analysis after cleaning the data; combining the cleaned data and equipment information to perform digital modeling of the equipment; the fault warning and diagnosis model determines and warns based on the digital model of the equipment and historical fault data. The equipment reliability maintenance method for smart power plants provided by the present invention monitors and warns the equipment, provides a scientific decision-making basis for the maintenance of key equipment, changes passive maintenance into predictive maintenance, and reduces the probability of human error; through the implementation of equipment fault warning and diagnosis, and equipment reliability evaluation, the equipment reliability is significantly improved, the maintenance cost is reduced, and the power generation efficiency is improved. The present invention achieves better results in reducing unplanned power outage time, reducing maintenance costs, and improving power generation efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment fault prediction and diagnosis, and in particular to an equipment reliability maintenance method and system for a smart power plant. Background Art

[0002] Faced with a development environment in which electricity demand growth is slowing and the proportion of new energy installed capacity is increasing, power companies need to accelerate the change of their extensive management model, shift from factor growth to innovation-driven growth, promote institutional innovation, management innovation, and technological innovation, and cultivate and form new growth advantages through innovation.

[0003] Zhuhai Electric Power uses the group company's production cloud as its basic platform, and utilizes the power plant's DCS industrial control system, SIS real-time monitoring system, various special sensors and other systems to automatically control the production system and collect data, build a comprehensive operation technology platform based on big data, and uniformly conduct intelligent analysis and management of data. It carries out four major application constructions: unified supervision of smart power plant fleets, performance analysis and optimization, equipment reliability maintenance, and safe production management. It improves the power plant's intelligent construction capabilities in terms of data services, governance, visual recognition, integrated linkage, unit performance analysis, expert guidance and mutual assistance, early warning, and decision-making model building.

[0004] At present, the number of unplanned downtime hours that can be achieved by the reliability maintenance method of equipment in power plants no longer meets the requirements of power plants. The pressure of equipment reliability management is high. Condenser titanium tube scaling, condensate pump inverter failure, water-cooled unit power switch short circuit, boiler high-pressure drum water level protection tripping abnormality and other incidents have occurred in the plant. As the equipment is used for a longer time, the maintenance cost increases and the frequency of failures increases. On-site operation mainly relies on the experience of operating personnel, and the technology is mainly passed on by master to apprentice. Faced with the actual situation of large personnel turnover, the possibility of human error is increased, affecting the safe and stable operation of the unit. Therefore, there is an urgent need for an equipment reliability maintenance method for smart power plants to reduce unplanned power outages, reduce maintenance costs, and provide technical support for operation and maintenance personnel. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is that the existing equipment reliability maintenance method has the problems of long unplanned power outage time, high probability of human error, high maintenance cost, and reduced power generation efficiency.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for equipment reliability maintenance of a smart power plant, comprising:

[0009] Obtain real-time equipment operation data, clean the data and perform data quality analysis;

[0010] Combine the cleaned data and equipment information to perform digital modeling of the equipment;

[0011] The fault warning and diagnosis model makes judgments and issues warnings based on the equipment digital model and historical fault data.

[0012] As a preferred solution of the equipment reliability maintenance method for a smart power plant described in the present invention, the data quality analysis includes dead value diagnosis, fluctuation diagnosis, threshold diagnosis, and gradient diagnosis.

[0013] As a preferred solution of the equipment reliability maintenance method for a smart power plant described in the present invention, the digital modeling of the equipment includes equipment type modeling, production process structure modeling, twin modeling, factory modeling, unit modeling, professional modeling, system modeling and equipment modeling.

[0014] As a preferred solution of the equipment reliability maintenance method for a smart power plant described in the present invention, the fault warning and diagnosis model includes a parameter warning model, an equipment evaluation model and a rule engine.

[0015] As a preferred scheme of the equipment reliability maintenance method for smart power plants described in the present invention, the parameter warning models include a thrust bearing temperature exceeding the standard warning model, a compressor surge warning model, a reheat steam temperature difference excessive warning model, and a high-pressure steam drum electric control valve jam warning model.

[0016] As a preferred solution of the equipment reliability maintenance method for a smart power plant described in the present invention, the early warning includes:

[0017] If the temperature difference between the inner and outer walls of the high-pressure regulating valve is greater than 80°C, or the temperature difference between the upper and lower inner walls of the medium-pressure steam inlet is greater than 80°C, or the temperature difference between the inner and outer walls of the upper flange on the left is greater than 80°C, or the temperature difference between the inner and outer walls of the upper flange on the right is greater than 80°C, or the temperature difference increase rate is ≥30°C / h, then the thrust bearing temperature exceeds the standard warning condition;

[0018] If the cover vibration of the steam turbine is greater than 50 μm or the cover vibration is between 40-50 μm and the rising rate is ≥30 μm / h or the condenser pump vibration value of the condenser is greater than 4.5 mm / s, the compressor surge warning condition is met;

[0019] If the second-stage extraction hydraulic valve is opened and the opening is greater than 20%, the desuperheating water regulating valve is closed, and the steam temperature difference before and after the desuperheater is greater than 100°C, the reheat steam temperature difference excessive warning condition is met;

[0020] If the opening on the condenser side of the TCA cooler is less than 5% and the deviation between the fitting value and the actual value of the opening on the boiler side of the TCA cooler is greater than 10%, or the flow rate after the recirculation valve is greater than 0, one pump is running, and the outlet flow rate of the feed pump is greater than 40t / h, then the high-pressure steam drum electric regulating valve is jammed. Warning conditions.

[0021] As a preferred solution of the equipment reliability maintenance method for a smart power plant described in the present invention, the diagnosis includes:

[0022] If there is a warning of thrust bearing temperature exceeding the standard, and no control is performed, and the temperature difference drops below 80°C, the degradation level of the equipment is calculated, and the remaining usable time of the equipment and parts is calculated. It is diagnosed as the water in the turbine cylinder is not drained, the load changes too quickly, and the difference between the steam entering the cylinder and the cylinder temperature is too large. The temperature difference does not drop below 80°C, which is diagnosed as a hot spot couple failure. Check its safety and replace the faulty parts. Calculate the remaining usable time of the remaining parts;

[0023] If the compressor surge warning appears, but no control is performed, and the turbine cover vibration drops below 50μm, the degradation level of the equipment is calculated, and the remaining usable time of the equipment and parts is calculated. It is diagnosed that the turbine cranking time is insufficient, the cover vibration has not dropped below 50μm, or the condenser pump vibration value of the condenser is greater than 4.5mm / s. It is diagnosed that the turbine end cover fastening screws are loose, the bearing is heated unevenly, or the condenser pump causes resonance at the natural frequency. It is necessary to perform parts maintenance on the turbine, replace the bearing, replace the condenser pump bearing, and calculate the remaining usable time of the remaining parts;

[0024] If there is a warning of excessive temperature difference of reheat steam, it is diagnosed as wear of the internal valve core of the steam turbine low-pressure heating desuperheater valve, aging of the inner seal of the valve, and loose sealing. Check its safety and replace the faulty parts, and calculate the remaining usable time of the remaining parts;

[0025] If there is a warning of high-pressure drum electric regulating valve jamming, the opening changes below 5%, and the deviation between the fitting value and the actual value of the opening on the boiler side of the TCA cooler can be reduced to 10%, it is diagnosed as valve jamming or the control valve opening setting and feedback are inconsistent. Lubrication treatment is performed, the remaining available time of the valve is calculated, and the valve opening control system is repaired. If normal operation cannot be restored, the TCA cooler condenser and feed water pump are diagnosed as the valve core of the gas turbine TCA cooler valve is detached or the internal valve core of the feed water pump valve is worn, the inner seal of the valve is aged, and the seal is not tight;

[0026] After diagnosing the cause of the fault, the power plant personnel are promptly reminded through real-time alarms. The unprocessed information that is still in alarm is displayed on the agent alarm interface, which is divided into rule alarms, model alarms, DCS, TCS, settlement, fire protection, temperature and humidity. The operation and maintenance personnel handle the agent alarms according to the actual alarm situation.

[0027] Another object of the present invention is to provide an equipment reliability maintenance system for a smart power plant, which can monitor and warn equipment through real-time data changes, thereby solving the technical problems of the existing equipment reliability maintenance system, such as long unplanned power outages, high probability of human error, and high maintenance costs.

[0028] In order to solve the above technical problems, the present invention provides the following technical solutions: an equipment reliability maintenance system for a smart power plant, comprising: a data cleaning module, an equipment digitization module, a fault early warning and diagnosis module and an alarm module,

[0029] The data processing module is a device that filters access data and is used to perform dead value diagnosis, fluctuation diagnosis, threshold diagnosis, and gradient diagnosis, and provides reliable real-time equipment operation data and historical equipment failure data for the equipment digitization module;

[0030] The equipment digitization module is a device that digitizes equipment information and operating status into virtual equipment, and is used to build equipment type modeling, production process structure modeling, twin modeling, factory modeling, unit modeling, professional modeling, system modeling, and equipment modeling;

[0031] The fault warning and diagnosis module is a device that predicts whether the equipment is faulty and analyzes the cause of the fault and the treatment method. It analyzes the equipment degradation level and the cause of the equipment failure based on the real-time status data of the equipment, historical fault data and the rule engine;

[0032] The alarm module is an alarm device used to inform the operation and maintenance personnel of the faulty equipment information and the cause of the fault, and to display the unprocessed and still alarming information on the agent alarm interface.

[0033] As a preferred solution of the small current grounding line selection method based on the network command system described in the present invention, wherein: a computer device includes a memory and a processor, the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements a method for equipment reliability maintenance for a smart power plant.

[0034] As a preferred solution of the small current grounding line selection method based on the network command system described in the present invention, it includes: a computer-readable storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, a method for equipment reliability maintenance for a smart power plant is implemented.

[0035] Beneficial effects of the present invention: The equipment reliability maintenance method for a smart power plant provided by the present invention monitors and warns the equipment, provides a scientific decision-making basis for the maintenance of key equipment, changes passive maintenance into predictive maintenance, and reduces the probability of human error; through the implementation of equipment fault warning and diagnosis, and equipment reliability evaluation, equipment reliability is significantly improved, maintenance costs are reduced, and power generation efficiency is improved. The present invention achieves better results in reducing unplanned power outages, reducing maintenance costs, and improving power generation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0037] Figure 1 An overall flow chart of an equipment reliability maintenance method for a smart power plant provided by one embodiment of the present invention.

[0038] Figure 2 An overall flow chart of an equipment reliability maintenance system for a smart power plant provided in accordance with the second embodiment of the present invention. DETAILED DESCRIPTION

[0039] 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.

[0040] 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.

[0041] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0042] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0043] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0044] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0045] Example 1

[0046] Reference Figure 1 , which is an embodiment of the present invention, provides a device reliability maintenance method for a smart power plant, comprising:

[0047] S1: Obtain real-time equipment operation data, clean the data, and perform data quality analysis.

[0048] Furthermore, data quality analysis includes: dead value diagnosis, fluctuation diagnosis, threshold diagnosis, and gradient diagnosis.

[0049] It should be noted that data cleaning realizes effective filtering of system access data, improves data quality, and ensures the effectiveness and accuracy of fault alarms.

[0050] It should also be noted that the dead value diagnosis is when the parameter has not changed within the specified time or number of acquisitions, and is judged as a dead point abnormality; the threshold diagnosis is when the parameter exceeds the effective range and is judged as invalid range data; the fluctuation diagnosis is when the parameter fluctuation range exceeds the set value within the specified time or number of acquisitions, and is judged as excessive fluctuation; the gradient judgment is when the parameter changes faster than the set value within the specified time or number of acquisitions, and is judged as too fast fluctuation.

[0051] S2: Combine the cleaned data and equipment information to perform digital modeling of the equipment.

[0052] Furthermore, digital modeling of equipment includes equipment type modeling, production process structure modeling, twin modeling, factory modeling, unit modeling, professional modeling, system modeling and equipment modeling.

[0053] It should be noted that equipment type modeling is the definition of a certain type of equipment functional structure, including equipment attributes, structure diagrams, components, monitoring parameters, vibration parameters, diagnostic analysis models, and evaluation index configuration. The main function of equipment type modeling is model standardization management and model reuse. For example, by defining the high-pressure feedwater pump equipment type model, the platform can quickly instantiate it into #2 turbine high-pressure feedwater pump and #4 turbine high-pressure feedwater pump.

[0054] It should also be noted that the production process structure modeling is used to construct the hierarchical relationships among units, specialties, systems, systems, and equipment of different power generation process types, such as the gas turbine generator set model and the waste heat generator set model. As templates for specific power plant entity units, this embodiment is used to complete the rapid construction of the #1 gas turbine generator set, #2 steam turbine generator set, #3 gas turbine generator set, and #5 steam turbine generator set of Zhuhai Power Plant.

[0055] Furthermore, twin modeling is responsible for building a structured digital model that includes characteristic parameters, operating conditions, mechanism diagnosis, parameter warning, equipment status evaluation, etc. of the unit equipment based on the basic template of the equipment type model and production process structure model.

[0056] It should be noted that the factory modeling creates a model of the power plant under the system gas and electricity group node. When an alarm is triggered, the location of the equipment can be displayed, and its connected equipment can be displayed in the node to issue early warnings to other equipment to prevent chain failures.

[0057] It should also be noted that unit modeling is based on unit level, maintenance condition mode, fault diagnosis model, comprehensive evaluation model and other key information to display the fault level. If multiple equipment failures occur, higher-level units are prioritized for maintenance or overhaul.

[0058] Furthermore, professional modeling is based on the professional level to maintain major models such as fault diagnosis model and comprehensive evaluation model.

[0059] It should be noted that system modeling is the digital modeling of process systems such as gas turbine systems, waste heat boiler systems, steam turbine systems, and electrical systems. It specifically includes the configuration of system operating conditions, system fault diagnosis models, system comprehensive evaluation models, and operation reports.

[0060] It should also be noted that equipment modeling is based on the equipment level, maintaining key information such as basic equipment configuration, diagnostic analysis, vibration analysis, indicator analysis, diagnostic reports, and operation reports, and conducting detailed analysis of individual equipment.

[0061] S3: The fault warning and diagnosis model makes judgments and issues warnings based on the equipment digital model and historical fault data.

[0062] Furthermore, the fault warning and diagnosis model includes: parameter warning model, equipment evaluation model and rule engine.

[0063] It should be noted that the parameter warning models include: thrust bearing temperature exceeding standard warning model, compressor surge warning model, reheat steam temperature difference excessive warning model, and high-pressure steam drum electric control valve jamming warning model.

[0064] It should also be noted that early warning includes:

[0065] If the temperature difference between the inner and outer walls of the high-pressure regulating valve is greater than 80°C, or the temperature difference between the upper and lower inner walls of the medium-pressure steam inlet is greater than 80°C, or the temperature difference between the inner and outer walls of the upper flange on the left is greater than 80°C, or the temperature difference between the inner and outer walls of the upper flange on the right is greater than 80°C, or the temperature difference increase rate is ≥30°C / h, then the thrust bearing temperature exceeds the standard warning condition; if the cover vibration of the steam turbine is greater than 50μm, or the cover vibration is between 40-50μm and the increase rate is ≥30μm / h, or the vibration value of the condenser pump of the condenser is greater than 4.5mm / s, then the compressor surge warning condition is met ; If the second-stage steam extraction hydraulic valve is opened and the opening is greater than 20%, the desuperheating water regulating valve is closed, and the steam temperature difference before and after the desuperheater is greater than 100°C, then the reheat steam temperature difference excessive warning condition is met; if the opening on the condenser side of the TCA cooler is <5% and the deviation between the fitting value and the actual value of the opening on the boiler side of the TCA cooler is >10% or the flow after the recirculation valve is >0, one pump is running, and the feed pump outlet flow is >40t / h, then the high-pressure steam drum series electric regulating valve is stuck. Warning condition.

[0066] Furthermore, the temperature difference between the inner and outer walls of the high-pressure regulating valve, the temperature difference between the upper and lower inner walls of the medium-pressure steam inlet, and the temperature difference between the inner and outer walls of the upper flange should all be lower than 80°C. The temperature difference of conventional steam turbines is generally set lower than 50°C, because for every 10°C increase in temperature difference, the radial clearance of the lower part of the regulating stage decreases by about 0.1mm. The radial clearance of the diaphragm seal of the high-pressure steam turbine is relatively small, generally 0.4-0.7mm, so the temperature difference of the cylinder wall is usually stipulated not to exceed 50°C, but our invention selects the three parts for calculation, which are thicker, 3-4 times the cylinder wall, and can withstand a higher temperature difference. The temperature of these three positions is easier to measure, and it is more dangerous to place the thermometer in the cylinder wall. Therefore, these three parts are selected. When the temperature difference exceeds 80°C, the thermal expansion of the inner side is large and the thermal expansion of the outer side is small, then each cross section along the axial direction of the cylinder will produce bending deformation, with the two ends bending outward and the middle bending inward. Because the vertical rigidity of the cylinder is small, under the action of this deformation force, the horizontal parts at both ends of the cylinder are stretched and become horizontal elliptical, and the flange is open inward. After being in this extruded state for a long time, when the cylinder body returns to a cold state, an inward opening will appear on the cylinder joint surface, causing equipment damage. If the equipment heats up too quickly, exceeding 30℃ / h, the flange gasket green shell paper will not be able to fully fit the equipment, affecting its insulation effect.

[0067] It should be noted that turbine cover vibration generally occurs when the warm-up time is insufficient, the speed is increased or the load is too fast, resulting in uneven heating of the cylinder. If it exceeds 50μm or the cover vibration is close to 50μm but the speed is ≥30μm / h, there may be problems with cylinder deformation or misaligned center. If the vibration value of the condenser pump of the condenser is greater than 4.5mm / s, there must be resonance, which will cause the operating frequency of the equipment to change. If the condenser pump support is not reinforced at this time, the condenser pump will be displaced, causing danger.

[0068] It should also be noted that when the second-stage steam extraction hydraulic valve is open and the opening degree is greater than 20%, it represents the heating supply status. Normally, when no cooling water is put into use, the temperature difference before and after the desuperheater is below 100. When it exceeds 100 and is maintained for a long time, it indicates internal leakage.

[0069] Furthermore, when the side opening is less than 5%, the condenser side of the TCA cooler is fully closed, and the historical data of the flow rate of TCA to the boiler side is used to predict the valve opening. Under normal operating conditions, the deviation between the actual value of the valve opening and the fitted value does not exceed 10%.

[0070] It should be noted that if the outlet flow rate of the water supply pump is greater than 40t / h, it indicates normal operation. During normal operation, there is no internal leakage. However, if there is flow in the recirculation valve, it means that the recirculation valve is not tightened or has fallen off. When this phenomenon occurs, the equipment needs to be directly repaired. The flow rate of the recirculation valve is not large, and there is little or no water in the pump. The heat generated by the sliding friction of the centrifugal impeller cannot be completely carried away by the water, causing the temperature in the pump to rise, the water to vaporize, and cavitation to form, causing serious damage to the equipment and impeller.

[0071] Further, the diagnosis includes:

[0072] If there is a warning that the thrust bearing temperature exceeds the standard and no adjustment is made, and the temperature difference drops below 80°C, the degradation level of the equipment is calculated, as well as the remaining usable time of the equipment and components. It is diagnosed as a hot spot couple failure, excessive load changes, and too large a difference between the steam entering the cylinder and the cylinder body temperature. The temperature difference does not drop below 80°C, and is diagnosed as a safety failure. The faulty parts are checked and replaced, and the remaining usable time of the remaining components is calculated.

[0073] If a compressor surge warning occurs and no control is performed, and the turbine cover vibration drops below 50μm, the degradation level of the equipment is calculated, as well as the remaining usable time of the equipment and components. It is diagnosed as insufficient turbine cranking time, cover vibration not dropping below 50μm, or condenser pump vibration value greater than 4.5mm / s. It is diagnosed as loose turbine cover fastening screws, uneven heating of bearings, or resonance of the condenser pump at its natural frequency. The turbine needs to be maintained with replacement bearings and condenser pump bearings, and the remaining usable time of the remaining components is calculated.

[0074] If a warning of excessive reheat steam temperature difference appears, diagnose that the internal valve core of the steam turbine low-pressure heating desuperheater valve is worn, the inner seal of the valve is aged, and the seal is not tight. Check its safety and replace the faulty parts, and calculate the remaining usable time of the remaining parts.

[0075] If there is a warning of jamming of the high-pressure steam drum electric regulating valve, the opening changes below 5%, and the deviation between the fitting value and the actual value of the opening on the boiler side of the TCA cooler can be reduced to 10%, it is diagnosed as valve jamming or the control valve opening setting and feedback are inconsistent. Lubrication treatment is performed, the remaining available time of the valve is calculated, and the valve opening control system is repaired. If normal operation cannot be restored, the TCA cooler condenser and feed water pump are diagnosed as the valve core of the gas turbine TCA cooler valve is detached or the internal valve core of the feed water pump valve is worn, the inner seal of the valve is aged, and the seal is not tight.

[0076] It should be noted that after diagnosing the cause of the fault, the power plant personnel are promptly reminded through real-time alarms, and the unprocessed information that is still in alarm is displayed on the agent alarm interface, which is divided into rule alarms, model alarms, DCS, TCS, settlement, fire protection, temperature and humidity. The operation and maintenance personnel handle the agent alarms according to the actual alarm situation.

[0077] Example 2

[0078] An embodiment of the present invention provides a method for maintaining equipment reliability in a smart power plant. To verify the beneficial effects of the present invention, scientific demonstration is performed through economic benefit calculation and practical application.

[0079] As shown in the table, this is a comparison table of the trial effects of the present invention in Zhuhai Power Plant. It was put into trial operation on December 10, 2021, and the data is as of May 31 of the following year.

[0080] By implementing equipment reliability maintenance, fault warning and diagnosis, optimizing system operating parameters, shortening start-up and shutdown time, and reducing comprehensive gas consumption. As of May 31, the comprehensive gas consumption rate was 0.1966m3 / KWh, lower than last year's gas consumption level of 0.1977m3 / KWh; calculated based on the same power generation, it is equivalent to a reduction of 684,000 cubic meters in gas consumption and a 0.14% increase in power generation efficiency.

[0081] Equipment reliability maintenance, combining early warning equipment with historical fault information to provide scientific decision-making basis for key equipment maintenance, changing passive maintenance to predictive maintenance; online intelligent and offline knowledge base diagnosis for 5 types of pump equipment to effectively prevent the expansion of equipment failures. It is estimated that the daily inspection and maintenance costs will be reduced by 4.242 million yuan throughout the year (including 206,000 yuan in direct maintenance costs and 4.036 million yuan in indirect benefits). The daily maintenance expenditure for the whole year of 2021 is 40.843 million yuan, which is expected to decrease by 10.4% in 2022 compared with 2021.

[0082] Through the implementation of equipment fault early warning and diagnosis, and equipment reliability assessment, equipment reliability has been significantly improved, and the number of non-stop hours of the two units has dropped significantly. In 2021, the two units of Zhuhai Power Plant had a total of 130.667 non-stop hours throughout the year, and a total of 3.1 hours of non-stop hours as of May 31 this year. In the same period last year, the total non-stop hours was 41.47 hours, a year-on-year decrease of 92.5%.

[0083] Table 1 Comparison of trial results of Zhuhai Power Plant

[0084]

[0085] 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.

[0086] Example 3

[0087] Reference Figure 2 , which is an embodiment of the present invention, provides an equipment reliability maintenance system for a smart power plant, including: a data cleaning module, an equipment digitization module, a fault warning and diagnosis module, and an alarm module.

[0088] The data processing module is a device that filters the access data and is used for dead value diagnosis, fluctuation diagnosis, threshold diagnosis, and gradient diagnosis, and provides reliable real-time equipment operation data and historical equipment failure data for the equipment digitization module; the equipment digitization module is a device that digitizes equipment information and operation status into virtual equipment, and is used to build equipment type modeling, production process structure modeling, twin modeling, factory modeling, unit modeling, professional modeling, system modeling, and equipment modeling; the fault warning and diagnosis module is a device that predicts whether the equipment is faulty and analyzes the cause of the fault and the treatment method. It analyzes the equipment degradation level and the cause of the equipment failure based on the real-time status data of the equipment, historical fault data, and the rule engine; the alarm module is an alarm device that is used to inform the operation and maintenance personnel of the faulty equipment information and the cause of the fault, and displays the unprocessed information that is still alarming on the agent alarm interface.

[0089] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it 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 and includes 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 method 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. Various media that can store program codes.

[0090] 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.

[0091] 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.

[0092] 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.

Claims

1. A method for equipment reliability maintenance for a smart power plant, characterized in that: include: Obtain real-time equipment operation data, clean the data and perform data quality analysis; Combine the cleaned data and equipment information to perform digital modeling of the equipment; The fault warning and diagnosis model makes judgments and issues warnings based on the equipment digital model and historical fault data; The warning includes that if the temperature difference between the inner and outer walls of the high-pressure regulating valve is greater than 80°C, or the temperature difference between the upper and lower inner walls of the medium-pressure steam inlet is greater than 80°C, or the temperature difference between the inner and outer walls of the upper flange on the left is greater than 80°C, or the temperature difference between the inner and outer walls of the upper flange on the right is greater than 80°C, or the temperature difference increase rate is ≥30°C / h, then the thrust bearing temperature exceeds the standard warning condition; If the cover vibration of the steam turbine is greater than 50 μm or the cover vibration is between 40-50 μm and the rising rate is ≥30 μm / h or the condenser pump vibration value of the condenser is greater than 4.5 mm / s, the compressor surge warning condition is met; If the second-stage extraction hydraulic valve is opened and the opening is greater than 20%, the desuperheating water regulating valve is closed, and the steam temperature difference before and after the desuperheater is greater than 100°C, the reheat steam temperature difference excessive warning condition is met; If the opening degree on the condenser side of the TCA cooler is less than 5% and the deviation between the fitting value and the actual value on the boiler side of the TCA cooler is greater than 10%, or the flow rate after the recirculation valve is greater than 0, one pump is running, and the outlet flow rate of the feedwater pump is greater than 40t / h, then the high-pressure drum electric regulating valve jam warning condition is met; The second stage steam extraction hydraulic valve is open and the opening is greater than 20%, which means the heating is in operation. Normally, when no desuperheating water is put into operation, the temperature difference before and after the desuperheater is below 100. When it exceeds 100 and is maintained for a long time, it indicates internal leakage. When the side opening is less than 5%, the condenser side of the TCA cooler is fully closed. The historical data of the flow rate from the TCA to the boiler side is used to predict the valve opening. Under normal operating conditions, the deviation between the actual value of the control valve opening and the fitting value does not exceed 10%; If the outlet flow of the water pump is greater than 40t / h, it indicates normal operation. In normal operation, there is no internal leakage. However, if there is flow in the recirculation valve, it means that the recirculation valve is not tightened or has fallen off. When this phenomenon occurs, the equipment needs to be directly repaired. The diagnosis includes, If there is a warning of thrust bearing temperature exceeding the standard, and no control is performed, and the temperature difference drops below 80°C, the degradation level of the equipment is calculated, and the remaining usable time of the equipment and parts is calculated. It is diagnosed as the water in the turbine cylinder is not drained, the load changes too quickly, and the difference between the steam entering the cylinder and the cylinder temperature is too large. The temperature difference does not drop below 80°C, which is diagnosed as a hot spot couple failure. Check its safety and replace the faulty parts. Calculate the remaining usable time of the remaining parts; If the compressor surge warning appears, but no control is performed, and the turbine cover vibration drops below 50μm, the degradation level of the equipment is calculated, and the remaining usable time of the equipment and parts is calculated. It is diagnosed that the turbine cranking time is insufficient, the cover vibration has not dropped below 50μm, or the condenser pump vibration value of the condenser is greater than 4.5mm / s. It is diagnosed that the turbine end cover fastening screws are loose, the bearing is heated unevenly, or the condenser pump causes resonance at the natural frequency. It is necessary to perform parts maintenance on the turbine, replace the bearing, replace the condenser pump bearing, and calculate the remaining usable time of the remaining parts; If there is a warning of excessive temperature difference of reheat steam, it is diagnosed as wear of the internal valve core of the steam turbine low-pressure heating desuperheater valve, aging of the inner seal of the valve, and loose sealing. Check its safety and replace the faulty parts, and calculate the remaining usable time of the remaining parts; If there is a warning of high-pressure drum electric regulating valve jamming, the opening changes below 5%, and the deviation between the fitting value and the actual value of the opening on the boiler side of the TCA cooler can be reduced to 10%, it is diagnosed as valve jamming or the control valve opening setting and feedback are inconsistent. Lubrication treatment is performed, the remaining available time of the valve is calculated, and the valve opening control system is repaired. If normal operation cannot be restored, the TCA cooler condenser and feed water pump are diagnosed as the valve core of the gas turbine TCA cooler valve is detached or the internal valve core of the feed water pump valve is worn, the inner seal of the valve is aged, and the seal is not tight; After diagnosing the cause of the fault, the system promptly reminds the power plant personnel through real-time alarms, and displays the unprocessed and still alarming information on the agent alarm interface, which is divided into rule alarms, model alarms, DCS, TCS, settlement, fire protection, temperature and humidity. The operation and maintenance personnel handle the agent alarms according to the actual alarm situation.

2. The equipment reliability maintenance method for a smart power plant according to claim 1, characterized in that: The data quality analysis includes dead value diagnosis, fluctuation diagnosis, threshold diagnosis and gradient diagnosis.

3. The equipment reliability maintenance method for a smart power plant according to claim 1, characterized in that: The digital modeling of equipment includes equipment type modeling, production process structure modeling, twin modeling, factory modeling, unit modeling, professional modeling, system modeling and equipment modeling.

4. The equipment reliability maintenance method for a smart power plant according to claim 3, characterized in that: The fault warning and diagnosis model includes a parameter warning model, an equipment evaluation model and a rule engine.

5. The equipment reliability maintenance method for a smart power plant according to claim 4, characterized in that: The parameter warning models include a thrust bearing temperature exceeding standard warning model, a compressor surge warning model, a reheat steam temperature difference excessive warning model, and a high-pressure steam drum electric control valve jam warning model.

6. A system using the equipment reliability maintenance method for a smart power plant according to any one of claims 1 to 5, characterized in that: Including data cleaning module, equipment digitization module, fault warning and diagnosis module and alarm module, The data processing module is a device that filters access data and is used to perform dead value diagnosis, fluctuation diagnosis, threshold diagnosis, and gradient diagnosis, and provides reliable real-time equipment operation data and historical equipment failure data for the equipment digitization module; The equipment digitization module is a device that digitizes equipment information and operating status into virtual equipment, and is used to build equipment type modeling, production process structure modeling, twin modeling, factory modeling, unit modeling, professional modeling, system modeling, and equipment modeling; The fault warning and diagnosis module is a device that predicts whether the equipment is faulty and analyzes the cause of the fault and the treatment method. It analyzes the equipment degradation level and the cause of the equipment failure based on the real-time status data of the equipment, historical fault data and the rule engine; The alarm module is an alarm device used to inform the operation and maintenance personnel of the faulty equipment information and the cause of the fault, and to display the unprocessed and still alarming information on the agent alarm interface.

7. 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 equipment reliability maintenance method for a smart power plant described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the equipment reliability maintenance method for a smart power plant according to any one of claims 1 to 5 is implemented.

Images