CN113705924A - Intelligent diagnosis method and system for thermal control equipment - Google Patents
Intelligent diagnosis method and system for thermal control equipment Download PDFInfo
- Publication number
- CN113705924A CN113705924A CN202111043180.8A CN202111043180A CN113705924A CN 113705924 A CN113705924 A CN 113705924A CN 202111043180 A CN202111043180 A CN 202111043180A CN 113705924 A CN113705924 A CN 113705924A
- Authority
- CN
- China
- Prior art keywords
- diagnosis
- valve
- equipment
- information
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 103
- 238000012544 monitoring process Methods 0.000 claims abstract description 48
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims abstract description 37
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims description 49
- 238000012423 maintenance Methods 0.000 claims description 38
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 35
- 230000008859 change Effects 0.000 claims description 26
- 230000001105 regulatory effect Effects 0.000 claims description 25
- 230000001276 controlling effect Effects 0.000 claims description 20
- 238000007405 data analysis Methods 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 230000008030 elimination Effects 0.000 claims description 9
- 238000003379 elimination reaction Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000002405 diagnostic procedure Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000033228 biological regulation Effects 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 5
- 230000015556 catabolic process Effects 0.000 claims description 4
- 238000006731 degradation reaction Methods 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 5
- 238000011160 research Methods 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 abstract description 2
- 238000004092 self-diagnosis Methods 0.000 abstract description 2
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 22
- 230000009471 action Effects 0.000 description 12
- 229910021529 ammonia Inorganic materials 0.000 description 11
- 239000003921 oil Substances 0.000 description 11
- 239000003245 coal Substances 0.000 description 9
- 238000007726 management method Methods 0.000 description 9
- 239000000779 smoke Substances 0.000 description 9
- 238000009825 accumulation Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 6
- 239000010687 lubricating oil Substances 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000005507 spraying Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000006378 damage Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000002347 injection Methods 0.000 description 4
- 239000007924 injection Substances 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 238000004804 winding Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 230000008020 evaporation Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000000227 grinding Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 230000002087 whitening effect Effects 0.000 description 2
- 101800000246 Allatostatin-1 Proteins 0.000 description 1
- 102100036608 Aspartate aminotransferase, cytoplasmic Human genes 0.000 description 1
- 101100163949 Caenorhabditis elegans asp-3 gene Proteins 0.000 description 1
- 101500011070 Diploptera punctata Allatostatin-2 Proteins 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000012774 diagnostic algorithm Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000035876 healing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to an intelligent diagnosis method and system for thermal control equipment. The method comprises the following steps: acquiring state information of equipment to be monitored, and extracting characteristic information based on the state information; and generating a diagnosis result of the equipment to be monitored by adopting an analysis diagnosis model according to the state information and the characteristic information. According to the intelligent power plant fault early-warning system, the DCS related data are collected, the logic algorithm is intelligently analyzed and optimized, the thermal control secondary equipment fault early-sensing and warning are achieved through the research of the thermal control equipment state monitoring method, the fault hidden danger point is automatically diagnosed, the abnormal hidden danger existing in the thermal control secondary equipment fault early-warning can be effectively predicted and warned, the positive significance is provided for the current improvement of the operation reliability, the safety and the economy of a power generating set, and the positive demonstration effect is provided for the realization of self-diagnosis and self-healing of an intelligent power plant in the future.
Description
Technical Field
The invention relates to the technical field of thermal control equipment diagnosis, in particular to an intelligent diagnosis method and system for thermal control equipment.
Background
At present, the overhaul work of most power plants in China is mainly based on regular overhaul and fault overhaul, under-overhaul, over-overhaul, under-overhaul or fire-fighting type rush-repair easily occurs, the state of equipment is limited to the monitoring of characterization faults, and the equipment can be monitored after obvious faults occur. In recent years, intensive research and implementation of condition maintenance have been carried out on primary equipment such as three main engines and important auxiliary machines, and very significant effects have been obtained. By adopting intelligent technical means such as various precise instruments, expert knowledge base algorithms and the like, the state of the running equipment is monitored, the running state of the equipment is controlled timely and clearly, and the service life of the equipment, the prediction of a maintenance plan and a targeted maintenance decision can be provided.
However, the existing equipment for state monitoring is mostly primary equipment for a host, an important auxiliary machine and the like, and for thermal control secondary measurement equipment, an effective state monitoring and maintenance system is lacked, if hidden dangers cannot be found in real time, once a fault occurs, the influence is often large, and even non-stop of a unit or the important auxiliary machine occurs.
And, the thermal control equipment maintenance at the present stage mainly depends on the regular verification of the instrument and the fault maintenance of the equipment. And (4) checking the instrument periodically according to the requirement of the instrument verification regulation so as to ensure that the measurement precision in the next service cycle meets the service requirement. The period of periodic verification is generally synchronized to the host device's build time. And for devices which cannot be regularly checked, such as an electric actuator, an electromagnetic valve and the like, troubleshooting is performed, namely, troubleshooting is performed after a fault occurs. Through maintenance, the equipment is removed from failure in advance or faults are eliminated, and the equipment is ensured to run reliably in the next maintenance period. The focus of current thermal control maintenance is on handling existing and potential failures of the equipment.
At present, the accuracy and stability of pressure and differential pressure transmitters are higher and higher, and the structural design of the transmitters does not consider frequent disassembly and assembly. The method of dismantling the transmitter back to the standard room for periodic verification may damage the appearance of the transmitter and damage the combination valve, and if the transmitter is not installed for the first time after being reinstalled, leakage may occur. Most of the faults of the thermal control device can be or are processed at ordinary times, and the faults which can occur are unpredictable. Therefore, when the unit is repaired in size, the target or task for eliminating the potential fault of the thermal control equipment is not provided, if the thermal control equipment is still required to be repaired in size according to the main equipment repair rule, the thermal control equipment is dismounted in a large scale and overhauled in a large scale, and in addition, part of the repair process levels are not standardized, the thermal control equipment which is originally stably operated returns to the early fault high-occurrence period or shortens the service life, but the fault rate of the equipment in operation is increased, the daily maintenance and temporary repair work is increased, and meanwhile, the abnormal elimination of the thermal control equipment can be accelerated.
Past scheduled maintenance and individual conditions of a part of equipment simply require a total overhaul, resulting in a worse state of the overhaul of a part of equipment. For example: the electric actuator is matched with precise mechanical equipment, parts are easy to damage due to large disassembly, sealing damage and shell deformation, and the phenomenon that some equipment is damaged but repaired sometimes happens without being damaged. Furthermore, when some electronic devices are re-installed, the original wiring process is destroyed, and the electronic devices are mutually dislocated or damaged in the assembling and disassembling process, so that the control system which can be normally used before overhaul cannot be used after overhaul.
Therefore, the intelligent diagnosis method or system for the thermal control equipment, which can realize the early sensing and alarming of the thermal control secondary equipment fault and automatically diagnose the hidden trouble point, is provided, and becomes a technical problem to be solved urgently in the field.
Disclosure of Invention
The invention aims to provide an intelligent diagnosis method and system for thermal control equipment, so as to realize early sensing and alarming of faults of thermal control secondary equipment, automatically diagnose potential fault points and further effectively improve the operation reliability and safety of a generator set.
In order to achieve the purpose, the invention provides the following scheme:
a thermal control device intelligent diagnosis method comprises the following steps:
acquiring state information of equipment to be monitored, and extracting characteristic information based on the state information; the characteristic information is used for reflecting the state characteristics of the equipment to be monitored; the state information includes: the control method comprises the following steps of (1) controlling a valve command, controlling the opening degree of the valve, controlling the opening degree of an electric valve, controlling the opening degree of the electric valve, controlling an in-place signal, steam drum water level, feed water flow, main steam pressure and steam drum pressure; the state information comprises state information of a plurality of measuring points;
generating a diagnosis result of the equipment to be monitored by adopting an analysis and diagnosis model according to the state information and the characteristic information; the analysis and diagnosis model is a neural network model established based on historical state information and historical characteristic information of the monitoring equipment by adopting an expert diagnosis algorithm; the diagnosis result comprises a current fault diagnosis result and a predicted fault diagnosis result.
Preferably, the generating a diagnosis result of the device to be monitored by using an analysis and diagnosis model according to the state information and the feature information further includes:
performing data analysis on the historical state information to remove irrelevant nuisance alarm information or false alarm information;
establishing a fault model according to the correlation relationship of the process systems;
setting a limit condition according to the fault model;
determining a boundary condition according to the limit condition;
determining a data anomaly point based on the boundary condition and the historical state information;
predicting the fault type and the fault characteristic based on the data abnormal point by adopting a grey prediction method; the historical state information, the fault type and the fault characteristics are stored in an expert diagnosis knowledge base;
and training a neural network model by adopting data information stored in an expert diagnosis knowledge base to obtain the analysis diagnosis model.
Preferably, the data analysis comprises: preprocessing, relevance identification and noise elimination.
Preferably, the method further comprises the following steps:
and generating a maintenance decision according to the diagnosis result.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
according to the intelligent diagnosis method for the thermal control equipment, which is provided by the invention, through collecting DCS related data, intelligently analyzing and optimizing a logic algorithm and researching a state monitoring method of the thermal control equipment, the fault of the thermal control secondary equipment is sensed and alarmed in advance, fault hidden danger points are automatically diagnosed, abnormal hidden dangers existing in the thermal control secondary equipment can be effectively predicted and alarmed in advance, the intelligent diagnosis method has positive significance for currently improving the operation reliability, safety and economical efficiency of a generator set, and has a positive demonstration effect on realizing self diagnosis and self healing of an intelligent power plant in the future.
Corresponding to the intelligent diagnosis method for the thermal control equipment, the invention also provides the following specific implementation system:
wherein, a thermal control equipment intelligent diagnosis system includes:
the information acquisition module is used for acquiring the state information of the equipment to be monitored and extracting characteristic information based on the state information; the characteristic information is used for reflecting the state characteristics of the equipment to be monitored; the state information includes: the control method comprises the following steps of (1) controlling a valve command, controlling the opening degree of the valve, controlling the opening degree of an electric valve, controlling the opening degree of the electric valve, controlling an in-place signal, steam drum water level, feed water flow, main steam pressure and steam drum pressure; the state information comprises state information of a plurality of measuring points;
the diagnosis module is used for generating a diagnosis result of the equipment to be monitored by adopting an analysis diagnosis model according to the state information and the characteristic information; the analysis and diagnosis model is a neural network model established based on historical state information and historical characteristic information of the monitoring equipment by adopting an expert diagnosis algorithm; the diagnosis result comprises a current fault diagnosis result and a predicted fault diagnosis result.
Preferably, the method further comprises the following steps:
the rejecting module is used for carrying out data analysis on the historical state information to reject irrelevant nuisance alarm information or false alarm information; the data analysis comprises: preprocessing, relevance identification and noise elimination;
the model building module is used for building a fault model according to the correlation relationship of the process systems;
the limit condition setting module is used for setting a limit condition according to the fault model;
the boundary condition determining module is used for determining a boundary condition according to the limit value condition;
a data anomaly determination module for determining a data anomaly based on the boundary condition and the historical state information;
the prediction module is used for predicting the fault type and the fault characteristic based on the data abnormal point by adopting a gray prediction method; the historical state information, the fault type and the fault characteristics are stored in an expert diagnosis knowledge base;
and the model training module is used for training the neural network model by adopting the data information stored in the expert diagnosis knowledge base to obtain the analysis and diagnosis model.
Preferably, the method further comprises the following steps:
and the maintenance decision generation module is used for generating a maintenance decision according to the diagnosis result.
Another thermal control device intelligent diagnostic system includes:
the monitoring module of the measuring point, is used for reading the measuring point, monitoring the change situation of the measuring point and extracting the measuring point information, and is used for judging whether the measuring point is normal or not by combining the analysis and diagnosis model and the big data comprehensive analysis, indicating whether the value is correct or not, carrying out alarm grade classification and invalid alarm suppression on the fault information, and pushing out abnormal fault information after screening and cleaning the data; the measuring point information comprises change rate, signal mutation, signal fluctuation, process range overrun and similar unbalance information;
the valve monitoring module is used for monitoring and analyzing the performance state of the valve mechanism in real time according to the equipment measuring point analysis information, the equipment measuring point set value, the equipment measuring point process value, the process parameters of the equipment measuring points and the incidence relation among the equipment measuring points; the valve mechanism includes: the device comprises an electric door, a pneumatic door, a hydraulic door and an actuating mechanism;
the valve-regulating servo valve monitoring module is used for acquiring DCS signals, analyzing the flow characteristics of the steam turbine valve regulating according to relevant process parameters and in combination with an expert model, diagnosing the regulating state of the valve, analyzing and judging the jamming and leakage faults of the servo valve and pushing parameter modification suggestions; the associated process parameters include: valve instructions, feedback information, steam flow, regulation stage pressure, and load changes;
and the AST solenoid valve diagnosis module is used for analyzing whether the solenoid valve coil has faults and leakage or not based on the solenoid valve current, the coil surface temperature and the oil pressure measuring points, and is also used for analyzing the solenoid valve degradation characteristic so as to carry out fault early warning and service life evaluation on the solenoid valve.
The technical effect achieved by the intelligent diagnosis system for the thermal control equipment provided by the invention is the same as that achieved by the intelligent diagnosis method for the thermal control equipment, so that the detailed description is omitted.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of an intelligent diagnosis method for a thermal control device provided by the invention;
fig. 2 is an overall flowchart framework diagram for implementing an intelligent diagnostic method for a thermal control device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an intelligent diagnostic system for a thermal control device according to the present invention;
FIG. 4 is a functional architecture diagram for implementing an intelligent diagnostic method for a thermal control device according to an embodiment of the present invention;
fig. 5 is a network architecture diagram for implementing an intelligent diagnostic method for a thermal control device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide an intelligent diagnosis method and system for thermal control equipment, so as to realize early sensing and alarming of faults of thermal control secondary equipment, automatically diagnose potential fault points and further effectively improve the operation reliability and safety of a generator set.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, an intelligent diagnosis method for a thermal control device includes:
step 100: and acquiring the state information of the equipment to be monitored, and extracting characteristic information based on the state information. The characteristic information is information for reflecting the state characteristics of the equipment to be monitored. The state information includes: the system comprises a valve adjusting instruction, a valve adjusting opening degree, an electric valve instruction, an electric valve opening degree, a switch in-place signal, a steam drum water level, a water supply flow, a main steam pressure and a steam drum pressure. The status information includes status information for a plurality of stations.
In this step, for each failure mode of the device, a proper technical means is selected to monitor the state information of the device, and information capable of reflecting the state characteristics of the device is extracted. Device condition monitoring can be divided into four basic steps: determining a tested device or system, determining a monitoring signal, extracting device characteristic information and storing data.
The method is characterized in that a tested device or system is determined according to the importance and relevance of the device, a system and a device related to protection, interlocking and automation are preferentially selected, and classified monitoring is carried out according to the importance degree of the device, for example, a steam drum water level three-impulse automatic adjusting system is one of the most main adjusting systems of a power plant, related water supply adjusting valves, steam drum water levels, water supply flow and main steam flow transmitters are used as key monitoring devices, and related inlet and outlet electric valves, water supply pressure transmitters and the like of the system are used as secondary key devices and are also included in a monitoring range, so that the safety and the stability of the whole system can be monitored.
After the system and the equipment are determined, main monitoring signals of the system, such as a water supply adjusting valve, an electric door instruction, an opening degree, a switch in-place signal, a steam drum water level, a water supply flow, a main steam pressure, a steam drum pressure and the like, need to be determined.
The feature extraction is to define what feature phenomena a device or parameter has as abnormal, otherwise as normal, and use this as the judgment condition. Such as upper and lower limits, rate of change, tracking offset, signal in place, etc. For example, the following steps are carried out: and if the deviation between the given gate instruction and the feedback is less than 2.5%, judging that the tracking is abnormal when the deviation exceeds the given gate instruction and the feedback. The on-position signal is required during the normal operation of the water supply electric door, and if the off-position signal appears or does not exist, the signal is judged to be abnormal in position. If the water supply flow is generally designed to be an average value of two transmitters, the deviation between the two water supply flows exceeds 5t/h, and the abnormality is judged. The characteristic extraction of the parameters is realized by setting relevant characteristic conditions for each parameter as a judgment basis to be implanted into the system.
And finally, all the data enter a memory, so that historical information query, trend generation and abnormal reason tracing of the data are realized.
Step 101: and generating a diagnosis result of the equipment to be monitored by adopting an analysis diagnosis model according to the state information and the characteristic information. The analysis and diagnosis model is a neural network model established based on historical state information and historical characteristic information of the monitoring equipment by adopting an expert diagnosis algorithm. The diagnosis result includes a current fault diagnosis result and a predicted fault diagnosis result.
In step 101, according to the equipment state monitoring data and the characteristic information, various expert diagnostic algorithms are adopted to establish an analysis and diagnosis model, perform data analysis, state comparison, prediction evaluation and fault diagnosis on the state and the service life of the equipment, and identify the existing and upcoming defects of the equipment, so as to determine the faults of the equipment. The prediction is usually carried out by a time sequence method, a regression analysis method, a fuzzy prediction method, a gray prediction method, an artificial neural network method and the like.
The specific implementation of the data analysis is as follows:
and analyzing the data state by analyzing historical data such as the state parameters of the unit, the parameters of each control loop in the operation of the unit and the like. The data are classified through several analysis modes of preprocessing, relevance identification and noise elimination, and the measured point is abnormal, misrepresented or comprehensively abnormal. When in use, one or more analysis modes are adopted according to different scenes:
A. analysis pretreatment: whether the equipment or the measuring point is abnormal is judged by monitoring data of a single parameter or comprehensively comparing a plurality of process parameters: (1) general analysis: when the abnormal visual diagnosis of a single parameter, such as signal loss, signal mutation, indication value overrun and the like, occurs, the abnormal condition of the measuring point or the parameter can be directly diagnosed. (2) Intelligent analysis: the system is analyzed through a plurality of parameters, for example, if the outlet pressure of the closed water pump is low in short time when the closed water pump runs, the current of the closed water pump is normal and the inlet pressure of the closed water pump is normal, the closed water pump outlet pressure sensor is judged to be possibly abnormal or caused by interference, and the fault is recorded as a measuring point fault. (3) Statistical analysis: and analyzing data such as signal periodicity, signal frequency, system working condition characteristics and the like through big data to find abnormality and give an alarm in advance. For example, the outlet pressure of the closed pump frequently triggers a short alarm to judge that the sensor is abnormal and needs to be maintained and checked.
B. And (3) correlation identification: whether the measuring points are normal or not is judged by identifying the correlation influence of the start-stop state of the relevant process system on the monitoring data, namely, a trigger linkage relation is generated when certain parameters are put into operation or tripped. For example, a coal mill needs a lubricating oil pump to operate to guarantee oil pressure, and only the lubricating oil pump is triggered to trip when the tripping of the lubricating oil pump and the abnormity of the lubricating oil pressure are simultaneously met, because the tripping of the lubricating oil pump can directly cause the abnormity of the lubricating oil pressure.
C. Noise elimination: and identifying and rejecting irrelevant nuisance alarm or false alarm information so as to improve the accuracy and effectiveness of point detection diagnosis. (1) And (3) delayed triggering: and after the signal reaches the alarm condition, triggering the alarm by delaying for a period of time. For example, when the coal mill is started, the current signal is particularly large in a short time and exceeds a normal running state, but the starting process of the coal mill is normal, the coal mill can be started in a staggered manner through short time delay, and the current alarm of the coal mill is reduced. Alarms can also be reduced in this way when the signal changes due to interference. (2) Setting filtering or dead zone reduction alarm: when the signal fluctuates frequently near the alarm value, the change frequency can be weakened in a filtering mode, so that the signal is smooth and can be correspondingly reduced when the alarm is triggered. And a certain dead zone is also set, so that the occurrence of frequent alarm can be reduced. (3) And (3) condition alarming: the signal is required to reach a certain condition to alarm. For example, signal diagnostics such as temperature, vibration, etc., associated with the coal mill body can only be triggered when the coal mill is operating. The alarm needs to be suppressed, the alarm can be given only after the coal mill is operated, and the alarm is not given when the coal mill is not operated.
The specific implementation mode of the state comparison is as follows:
through the data analysis, the abnormal and invalid alarms of the measuring points are identified and removed, then a standard model and a fault model are established according to the correlation relationship of the process system, and the abnormal points are determined through the comparison with the actual parameters.
A. According to the correlation among the data in the process system, a modal correlation algorithm is constructed, and the parameter change and the data representation are specified, digitalized and modeled.
Taking the air-flue system as an example, when leakage exists in the economizer or the air preheater, the heat control measuring point changes obviously, the smoke temperature at the inlet and the outlet of the economizer and the smoke temperature or the exhaust smoke temperature at the inlet and the outlet of the air preheater continuously decrease, the decreasing rate exceeds 5 ℃/min, the water supply flow shows an increasing trend, but the unit load, the boiler evaporation capacity, the air supply and induction and the grinding state are not changed. And constructing different leakage fault models according to different temperature change trends of the leakage points.
B. And finding out boundary conditions according to a data association algorithm.
And setting a reasonable limit condition as a boundary condition for judging the unqualified point according to the change trend of the fault model. For example, when the load of the unit changes within a rated range, the drop rate of the smoke temperature at the inlet and outlet of the economizer, the smoke temperature at the inlet and outlet of the air preheater or the smoke temperature of the smoke exceeds 5 ℃/min, and the boundary condition of the algorithm is determined when the measured value of the water supply flow is larger than the measured value of the last acquisition period and is higher than the main steam flow change value.
The specific implementation of the prediction evaluation is as follows:
and (3) comparing the real-time data with the boundary conditions, finding out data deterioration and failure points, and predicting the type and the characteristic of the fault by using a gray prediction method.
The grey system prediction model GM (1,1) and the establishment of the metabolism model thereof have wide uncertainty problems, the system with uncertain connotation or extension is called a grey system in the invention, and the prediction problem is a key problem in the uncertain system.
The thermal control equipment fault generation and development process has uncertain factors, so the invention can regard the thermal control equipment fault generation and development process as a grey system. Grey theory the principle for fault prediction is to regard the predicted system as a grey system, and use the existing known information to deduce the characteristics, state and development trend of the unknown information containing fault mode, and make prediction and decision for the development of future fault, i.e. the whitening process of a grey process. Modeling is the materialization and quantitative representation of the relationship between the factors in the system.
Now, taking the application of the gray prediction method in the denitration system as an example, the application of the gray prediction in the state diagnosis of the thermal control equipment is described. Firstly, recording the ammonia injection flow corresponding to the opening degree of the denitration damper according to the early historical data of the denitration system, then recording the ammonia injection flow corresponding to the opening degree of the denitration damper according to the latest historical data of the denitration system, and performing once accumulation generation on an irregular and recyclable non-original sequence to obtain
x(1)＝{x(1)，x(1)(2)，……x(1)(n)}
The accumulation generation has probability significance, the actual problem shows that the accumulation generation has statistical significance, and the accumulation regularity is obtained by exploring the connotation of the original information, so that the relevance of the original information is maintained. The general form is:
x(0)(k)+az(1)(k)＝u
if remember x(0)＝{x(0)(k) 1,2, … … n, and x is the original data sequence(1)Is x(0)A sequence is generated by a single accumulation of, i.e. the total amount of the system's accumulation, and x(1)＝{x(1)(k)|k＝1,2,……n}。z(1)Is x(1)Is equally weighted to generate a sequence, and z (1)1,2, … … n, where z (k) k is equal to(1)(k)＝0.5x(1)(k)-0.5x(1)(k-1), k ═ 1,2, … … n, and the generation sequence was fitted with a first order univariate differential equation to give a dynamic model in the form of grey whitening:
Wherein a and u are obtained by a least square method, thereby calculating a prediction formula. And comparing the calculated value with the actual value of the prediction model, and diagnosing the linearity of the valve and the wear characteristic of the valve body, so that the expected service life of the valve can be calculated, and maintenance personnel are reminded to maintain and overhaul the equipment according to the expected service life. Through the calculation and analysis, the result processed by the gray prediction method is very consistent with the actual situation, and the prediction model has dynamic property and can perform online real-time monitoring on the adjustment valve of the denitration system.
The specific implementation process of the fault diagnosis is as follows:
the fault diagnosis is based on an expert diagnosis knowledge base, the knowledge base integrates regulations and accident cases of various types of units of 200-1000 MW in China, and covers an accident reason diagnosis and treatment measure method obtained by summarizing a plurality of electric power deep operation, thermal control and debugging experts for decades of field work experience, and the method is integrated in a platform in a software mode. And when the correlation algorithm model is established, triggering the corresponding diagnosis processing algorithm to determine the corresponding fault.
Fault diagnosis of, for example, a denitration ammonia injection flow meter: the denitration ammonia supply regulating valve is stable, the deviation value of the command and feedback tracking is less than 1%, the change of NOX and the change of the opening degree of the regulating valve accord with the change rule, the ammonia spraying flowmeter has no change trend and short-time sudden change, and the temperature of the ammonia supply pipeline is displayed at-10 ℃. According to operation and maintenance experience, the reason that the flowmeter is abnormally frozen due to the low temperature in winter can be judged, and the treatment measures are to additionally install heat tracing and heat preservation and remove the washing flowmeter. And integrating the model into the platform, and pushing reason analysis and processing suggestions when the working condition change conforms to the model state.
Wherein, the equipment state evaluation:
and evaluating the state of the equipment according to the equipment state prediction result, the abnormal emergency level, the current running state and maintenance plan of the unit, the expert experience of running and maintenance, the deep analysis reason and the solution measure. And (4) comprehensively pushing out the equipment maintenance strategy by combining information sources such as maintenance standard items, technical improvement items and defects.
The system consists of four parts of an equipment ledger, defect management, overhaul management and regular work. The equipment ledger is used as a data source of the system, and all parameters are presented in the equipment ledger, so that data can be added and inquired conveniently. The equipment abnormity alarm and the diagnosis prediction result are presented in a system homepage in a grading acousto-optic alarm mode, and operators are reminded to pay attention to the treatment in time. And simultaneously summarizing to defect management, recording, circulating and closing the defects, closing the loops in the system after timely processing under the process condition, and automatically verifying and processing the related equipment and the process parameters by the system. And if the processing condition is not met temporarily, combining the emergency level of the diagnosis result and the regular work and maintenance plan of the process system, pushing a reasonable maintenance strategy and maintenance plan in maintenance management and regular work, and performing closed-loop tracking supervision on the defects.
Based on the above, in order to further improve the accuracy of detection, before the step 101, the intelligent diagnosis method for thermal control equipment provided by the present invention further includes:
step 102: and performing data analysis on the historical state information to remove irrelevant nuisance alarm information or false alarm information. The data analysis comprises the following steps: preprocessing, relevance identification and noise elimination.
Step 103: and establishing a fault model according to the correlation relationship of the process systems.
Step 104: and setting limit conditions according to the fault model.
Step 105: the boundary condition is determined in accordance with the limit condition.
Step 106: data anomaly points are determined based on the boundary conditions and historical state information.
Step 107: and predicting the fault type and the fault characteristic based on the abnormal data points by adopting a gray prediction method. Historical status information, fault type, and fault characteristics are stored in an expert diagnostic knowledge base.
Step 108: and training the neural network model by adopting data information stored in the expert diagnosis knowledge base to obtain an analysis diagnosis model.
After the diagnosis result is determined, the intelligent diagnosis method for the thermal control equipment can also generate a maintenance decision according to the diagnosis result. Specifically, the application display of the result contents such as abnormity diagnosis alarm, maintenance decision, optimization guidance and the like is carried out at the PC terminal, and a mobile phone webpage version is supported, so that operation and maintenance personnel can conveniently master the health state of equipment in time, manage and control the production process and remotely monitor by management personnel.
According to the above, the overall implementation flow of the intelligent diagnosis method for the thermal control device provided by the invention is shown in fig. 2.
Corresponding to the intelligent diagnosis method for the thermal control equipment, the invention also provides the following specific implementation system:
as shown in fig. 3, an intelligent diagnostic system for thermal control equipment includes: an information acquisition module 1 and a diagnostic module 2.
The information acquisition module 1 is configured to acquire state information of a device to be monitored, and extract feature information based on the state information. The characteristic information is information for reflecting the state characteristics of the equipment to be monitored. The state information includes: the system comprises a valve adjusting instruction, a valve adjusting opening degree, an electric valve instruction, an electric valve opening degree, a switch in-place signal, a steam drum water level, a water supply flow, a main steam pressure and a steam drum pressure. The status information includes status information for a plurality of stations.
The diagnosis module 2 is used for generating a diagnosis result of the equipment to be monitored by adopting an analysis diagnosis model according to the state information and the characteristic information. The analysis and diagnosis model is a neural network model established based on historical state information and historical characteristic information of the monitoring equipment by adopting an expert diagnosis algorithm. The diagnosis result includes a current fault diagnosis result and a predicted fault diagnosis result.
In order to further improve the detection accuracy, the intelligent diagnostic system for the thermal control device provided by the invention preferably further comprises: the device comprises a rejection module, a model building module, a limit condition setting module, a boundary condition determining module, a data anomaly point determining module, a prediction module and a model training module.
The rejecting module is used for carrying out data analysis on the historical state information to reject irrelevant nuisance alarm information or false alarm information. The data analysis comprises the following steps: preprocessing, relevance identification and noise elimination.
The model building module is used for building a fault model according to the correlation relationship of the process systems.
And the limit condition setting module is used for setting limit conditions according to the fault model.
The boundary condition determining module is used for determining the boundary condition according to the limit value condition.
The data anomaly determination module is used for determining a data anomaly based on the boundary condition and the historical state information.
The prediction module is used for predicting the fault type and the fault characteristic based on the abnormal data points by adopting a gray prediction method. Historical status information, fault type, and fault characteristics are stored in an expert diagnostic knowledge base.
The model training module is used for training the neural network model by adopting the data information stored in the expert diagnosis knowledge base to obtain an analysis diagnosis model.
After the diagnosis result is determined, in order to generate a maintenance decision according to the diagnosis result, the method further comprises the following steps: and a maintenance decision generation module. And the maintenance decision generation module is used for generating a maintenance decision according to the diagnosis result.
Based on the architectures shown in fig. 4 and 5, the intelligent diagnosis of the thermal control device implemented by the invention is divided into four parts according to the technical route: data monitoring, diagnostic analysis, technical management and comprehensive display.
DCS data is collected in a production area in an OPC communication protocol mode, a measuring sensor is additionally arranged in a cabinet, data is collected in an RS485 communication mode, and an Ethernet is accessed to an application server for data diagnosis and application. Platform information is displayed in three areas through a firewall and a unidirectional isolation gatekeeper.
The platform supports intelligent comprehensive management, and automatically pushes states and gives an abnormal alarm at a system platform client to form a quick response closed-loop management system.
Based on the overall implementation architecture, the invention provides another intelligent diagnosis system for thermal control equipment, which comprises:
and the measuring point monitoring module is used for reading measuring points, monitoring the change condition of the measuring points, extracting measuring point information, judging whether the measuring points are normal or not and whether the indication values are correct or not by combining an analysis diagnosis model and big data comprehensive analysis, performing alarm grade classification and invalid alarm suppression on fault information, screening and cleaning data, and then pushing abnormal fault information. The measuring point information comprises change rate, signal mutation, signal fluctuation, process range overrun and similar unbalance information.
And the valve monitoring module is used for monitoring and analyzing the performance state of the valve mechanism in real time according to the equipment measuring point analysis information, the equipment measuring point set value, the equipment measuring point process value, the process parameters of the equipment measuring points and the incidence relation among the equipment measuring points. The valve mechanism includes: electric door, pneumatic door, hydraulic door and actuating mechanism. The functions of the executing mechanism, such as non-action, action delay, large instruction feedback deviation, poor linearity, frequent swing, abnormal feedback state, zero position, over-limit fullness and the like after receiving an operating instruction are diagnosed, fault conditions such as jamming, nonlinear sudden change and the like are automatically judged, an alarm is pushed to a human-computer interface of the upper computer, early warning is carried out in advance, measures are taken in time, and accidents are avoided. For example, an ammonia spraying adjusting valve of a denitration system is modeled and analyzed through an instruction, feedback, ammonia spraying flow, adjusting valve linearity, an actual adjusting valve action dead zone, whether the valve swings or not, outlet NOX variable quantity, adjusting parameters and adjusting results of the adjusting valve, and the reason of the adjusting valve fault is judged.
And the valve-regulating servo valve monitoring module is used for acquiring DCS signals, analyzing the flow characteristics of the steam turbine valve regulating according to associated process parameters and in combination with an expert model, diagnosing the regulating state of the valve, analyzing and judging the jamming and leakage faults of the servo valve and pushing parameter modification suggestions. The associated process parameters include: valve commands, feedback information, and steam flow, regulation stage pressure, load changes. The performance of the steam turbine governor is related to the safety and stability of the unit, and the jam condition of the servo valve is often easy to occur due to the complex structure of the governor and higher requirement on oil quality. The setting of the door adjusting parameters is not accurate enough, and the conditions of poor adjusting and tracking, door adjusting swing and the like easily occur.
And the AST solenoid valve diagnosis module is used for analyzing whether the solenoid valve coil has faults and leakage or not based on the solenoid valve current, the coil surface temperature and the oil pressure measuring points, and is also used for analyzing the solenoid valve degradation characteristic so as to carry out fault early warning and service life evaluation on the solenoid valve.
Wherein, 1) the general study and judgment logic in the measuring point monitoring module is as follows:
A. bad pixel study and judgment logic: and (4) judging that the measuring point is a bad quality point and recommending verification, wherein the lower limit of the measuring point is lower than 1.25% of the range and the upper limit of the measuring point is higher than 1.25% of the range.
For example (main steam pressure measurement):
the main steam pressure measuring point inputs 4-20mA signals for analog quantity, the range of the measuring range is 0-25MPa, and when the monitored signals are less than 3.8mA, namely the picture display is less than-0.3125 MPa, the main steam pressure measuring point gives a fault alarm to troubleshoot faults of measuring elements or DCS card machine channels.
B. The overrun study and judgment logic: the threshold value smaller than the thermal control protection fixed value is set, the alarm is triggered in advance of the DCS, and the alarm value is generally set to be 90 percent of the alarm value.
For example (induced draft fan bearing temperature):
the temperature of a bearing of the induced draft fan is normally 90 ℃, alarm is set to 81 ℃ in the system, and personnel are reminded of paying attention to abnormal temperature rise.
C. Mutation judging logic: and monitoring the temperature change rate of the temperature measuring point, wherein the temperature change rate is more than 8 ℃/second, and the measuring point measurement is judged to be unreliable and needs to be checked.
For example (intermediate pressure cylinder exhaust temperature):
the exhaust steam temperature of the intermediate pressure cylinder is normally 283 ℃, the exhaust steam falls after suddenly rising to 350 ℃, the abnormal measuring point is judged, and the wiring, the clamping, the shielding and the like of the measuring point need to be checked.
D. Measuring point fluctuation studying and judging logic: the range of repeated fluctuation within 60 seconds is measured and exceeds 5 ℃.
Examples (oil return temperature):
and (4) detecting the trend of the oil return temperature to have a fluctuation phenomenon, wherein the maximum fluctuation interval is more than 5 ℃/min, judging that the measuring point is abnormal, and checking wiring, clamping pieces, shielding and the like of the measuring point.
E. The logic for judging the unbalance of a single device of the same kind is as follows: the deviation of the same type of measuring points of a single device exceeds 20 percent.
For example (circulating water pump motor winding temperature):
the temperature of a motor winding of the circulating water pump is about 84 ℃ normal, the maximum value, the minimum value and the average value are taken from 6 measuring points, when the (maximum value-minimum value)/average value is more than 20%, the same type of unbalance is judged, the deviation between the maximum value and the minimum value and the average value is compared, the unbalance deviation of which measuring point occurs is determined, the factors of wiring, elements and clamping pieces of the measuring point need to be checked, if the values are all normal, the fact that the deviation exists is diagnosed, and the main equipment needs to be checked.
F. The logic for judging the unbalance of a plurality of similar devices is as follows: the deviation among the measuring points of the same type of a plurality of devices exceeds 50 percent.
For example (three circulating water pump motor winding temperatures):
the method comprises the following steps that A \ B \ C three circulating water pumps all operate, the temperature of a motor winding is normal about 84 ℃, the maximum value, the minimum value and the average value are taken from 18 measuring points, when the (maximum value-minimum value)/average value is larger than 50%, the same type of imbalance of a plurality of devices is judged, the deviation between the maximum value and the minimum value and the average value is compared, the unbalance deviation of which measuring point is determined, wiring, elements and clamping elements of the measuring point need to be checked, if the values are normal, the fact that the deviation exists is diagnosed, and main equipment needs to be checked.
The above judging logic is a general algorithm, is suitable for all measuring points, and can freely set a specific threshold value according to the process conditions of the measuring points.
2) The process coupling studying and judging logic in the measuring point monitoring module is as follows:
A. the change rate judging logic: and (4) the associated process environment and parameters are not changed, the continuous change rate of the measuring point is more than or equal to 5 ℃/min, and the abnormal measurement of the measuring point is judged and needs to be checked.
Examples (exhaust gas temperature):
the load of the unit, the evaporation capacity of the boiler, the air supply and induction and the grinding state are unchanged, the exhaust gas temperature is continuously reduced at the rate of 5 ℃/min, the water supply flow shows an increasing trend, the exhaust gas temperature is judged to be abnormal, and other related measuring points in the system are inquired: the smoke temperature at the inlet and outlet of the economizer and the smoke temperature at the inlet and outlet of the air preheater can judge that the upper-layer economizer or the air preheater has leakage when the regional continuous descending trend occurs.
B. And (3) measuring point indication value study and judgment logic: and checking the standard indicating value interval of each parameter under each working condition according to the relevant standards, the operation regulations and the design documents of the power plant in the power industry. And if the working condition is not abnormally changed, the individual parameter exceeds the limit, and the indication value of the measuring point is judged to be abnormal.
Examples (main steam temperature):
taking a 680MW unit as an example, when the load of a boiler is 100%, the temperature of main steam at the outlet of the boiler and at the side of a steam turbine is controlled within 600 +/-4 ℃, when the load is unchanged, the temperature at any side is abnormally increased or reduced, the temperature at the other side is unchanged, and when the deviation at the two sides is more than 10 ℃, the changed temperature gives an abnormal alarm to remind a measuring point and process inspection.
1) The specific research and judgment logic of the valve monitoring module is as follows:
A. and gate linear interval judgment logic: the valve receives a command of 0, but the feedback of the valve is greater than 5%, or the command of the valve is 100, the feedback of the valve is less than 95%, and the valve needs to be re-adjusted. The valve frequently swings repeatedly in the adjusting process, and the dead zone of the valve needs to be amplified. The linearity judgment of the regulating valve in the frequently used range judges whether the linear interval of the regulating valve is reasonable and normal or not through measuring points (such as flow, pressure, differential pressure and the like) before and after the regulating valve.
For example (denitration a side injection ammonia flow control valve):
the deviation between the instruction and the feedback of the valve of the flow regulating valve is more than 5 percent, and the regulating valve needs to be reset. After the valve of the flow regulating valve acts, the actual ammonia spraying flow does not change obviously or the ammonia spraying flow changes in a step shape, so that the valve is not good in linearity, and the valve needs to be overhauled and the valve core needs to be checked. The valve of the flow regulating valve repeatedly and frequently swings in the adjusting process, the action process of the regulating valve needs to be checked, the valve is likely to vibrate, and the regulating valve needs to be adjusted and adjusted again.
B. Valve action judgment logic: and judging that the feedback is abnormal when the valve is not opened, the valve opening feedback signal is 1, the valve is not closed, and the valve closing feedback signal is 1. The valve is in an open state, no protection action and no operation of operators exist, the valve opening feedback disappears, the valve state fault is judged, and the valve needs to be checked and maintained.
After the valve is opened, the valve opening feedback signal is 0 after the valve stroke time is exceeded, and the valve opening failure is judged.
And (3) judging that the valve linearity is poor when the valve switching time exceeds the actual valve switching travel time or the tracking deviation exceeds 5%.
Examples (condensate pump outlet electric gate):
the normal condensate pump export electrically operated gate action process does, and the electrically operated gate is the closed state, and DCS sends out behind the opening command, closes the feedback and disappears, and the electrically operated gate action, after 20 seconds's action stroke, the electrically operated gate is opened the feedback and is normal, and whole electrically operated gate action is normal. The fault diagnosis process comprises the following steps: the electric door is in a closed state, after the DCS sends an opening instruction, closing feedback does not disappear, the time is delayed for 30 seconds, and the electric door fault and the electric door jam are judged. The electric door is in a closed state, after the DCS sends an opening instruction, closing feedback disappears, but after 30 seconds of delay, no signal is fed back by the electric door opening feedback, and the electric door fault, the electric door jam or the over-torque are judged. When the system normally operates, the door is in an open state, the electric door does not receive any instruction of an operator or an interlocking automatic closing instruction, the opening feedback of the electric door disappears, the electric door is judged to be in a fault, and the electric door needs to be checked.
The functions realized by the regulating valve servo valve monitoring module (namely the steam turbine regulating valve monitoring module) are as follows:
(1) collecting DCS signals, analyzing the flow characteristics of a steam turbine regulating valve according to valve instructions, feedback, steam flow, regulating stage pressure, load change and other relevant process parameters by combining an expert model, diagnosing the regulating state of the valve, analyzing and judging jamming and leakage faults of a servo valve, and pushing parameter modification suggestions.
(2) A voltage detector or software is additionally arranged to obtain a driving voltage value and a voltage feedback value of the servo valve, and a model (namely an empirical model of the servo valve) after the servo valve is debugged normally is established. In the unit operation process, the measured values of the actual driving voltage and the actual voltage are compared with the servo valve experience model to generate an alarm signal, the whole servo loop is early warned of the fault in advance, then the servo card or the servo valve is checked, and the hidden danger of a servo control system is eliminated in advance.
The control valve is monitored by integrating the information through judging the feedback of the control valve after the control valve command acts and comparing the driving voltage model with the indexes such as the opening position linearity and the magnetic discharge curve of the control valve which are frequently and repeatedly required to be adjusted.
The specific logic is as follows:
and the valve opening judgment logic is that the instruction received by the valve is 0, the feedback of the valve is more than 5 percent, or the instruction of the valve is 100, the feedback of the valve is less than 95 percent, and the valve needs to be re-adjusted.
Dead zone judgment logic: the valve repeatedly and frequently swings in the adjusting process, the fluctuation of the valve up and down exceeds +/-2 percent in a short time (the specific time is different due to a process system), and the dead zone of the valve needs to be amplified.
And linear judgment logic: the linearity judgment of the regulating valve in the frequently used range judges whether the linear interval of the regulating valve is reasonable and normal or not through measuring points (such as flow, pressure, differential pressure and the like) before and after the regulating valve.
The AST electromagnetic valve is an important protection device of the steam turbine, and the power supply stability and the electromagnetic valve state of the AST electromagnetic valve directly influence the safety of a unit.
Install the current detector additional at AST solenoid valve coil power, real-time supervision electric current compares with the standard current value when the solenoid valve normally works, and when certain electric current disappears or the deviation appears with the standard current value, the corresponding solenoid valve of propelling movement loses the electricity or the deviation is reported to the police.
And extracting an AST oil pressure measuring point and an ASP oil pressure measuring point, analyzing the action condition of the solenoid valve according to the incidence relation between the oil pressure change and the action of the solenoid valve, pushing an abnormal alarm, displaying a half pressure of 7MPa of the system pressure by the ASP pressure in normal state, and displaying 14MPA by the AST pressure when AST1 and ASP 3 act. When AST2, 4 is active, ASP pressure shows 0 MPA. After the brake is hung, the oil pressure is quickly discharged, and the internal throttling of the electromagnetic valve body has a blocking phenomenon.
A patch type temperature measuring block is additionally arranged on a solenoid valve coil to monitor the surface temperature of the coil, and an alarm is given when the coil is abnormally raised.
And (3) integrating the current of the solenoid valve, the surface temperature of the coil and related oil pressure measuring points, analyzing the fault, leakage and the like of the solenoid valve coil, analyzing the degradation characteristic of the solenoid valve, and performing fault early warning and service life evaluation on the solenoid valve.
In addition, the diagnostic system can be further divided into the following five functional modules according to the device types: (1) the monitoring device comprises a measuring point monitoring module, (2) a valve monitoring module, (3) a valve adjusting servo valve monitoring module, (4) a bypass valve monitoring module and (5) an AST electromagnetic valve diagnosis module.
Each module comprises a general algorithm and a comprehensive model algorithm, and each module carries out diagnosis and analysis according to a technical route of a state monitoring technology, a state prediction technology, equipment state evaluation and result pushing display.
Compared with the prior art, the technical scheme provided by the invention has the following advantages:
1. the thermal control state maintenance platform is adopted to monitor, monitor and analyze thermal control equipment, the health condition of the thermal equipment can be effectively mastered, equipment faults are diagnosed and pushed, and a correct maintenance strategy is made. Three-area office network and mobile phone webpage version platform make the professional can discover equipment anomaly the first time, and respond in time.
2. Through the technical management means, the diagnosis analysis, the statistical analysis and the filing of the equipment are combined, so that the daily work of the thermal control is more standard, scientific, convenient and fine. The technical supervision function realizes automatic report and statistics, reduces the literal workload of thermal control personnel and improves the labor efficiency.
In conclusion, the thermal control state maintenance platform carries out comprehensive diagnosis and early warning on various production process indexes and flow states of the whole plant through monitoring and analyzing thermal control equipment, can find equipment abnormality in time, and can provide control state information and adjustment guidance for operation and maintenance personnel.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. An intelligent diagnosis method for thermal control equipment is characterized by comprising the following steps:
acquiring state information of equipment to be monitored, and extracting characteristic information based on the state information; the characteristic information is used for reflecting the state characteristics of the equipment to be monitored; the state information includes: the control method comprises the following steps of (1) controlling a valve command, controlling the opening degree of the valve, controlling the opening degree of an electric valve, controlling the opening degree of the electric valve, controlling an in-place signal, steam drum water level, feed water flow, main steam pressure and steam drum pressure; the state information comprises state information of a plurality of measuring points;
generating a diagnosis result of the equipment to be monitored by adopting an analysis and diagnosis model according to the state information and the characteristic information; the analysis and diagnosis model is a neural network model established based on historical state information and historical characteristic information of the monitoring equipment by adopting an expert diagnosis algorithm; the diagnosis result comprises a current fault diagnosis result and a predicted fault diagnosis result.
2. The intelligent diagnosis method for the thermal control equipment according to claim 1, wherein the generating of the diagnosis result of the equipment to be monitored by using the analysis and diagnosis model according to the state information and the characteristic information further comprises:
performing data analysis on the historical state information to remove irrelevant nuisance alarm information or false alarm information;
establishing a fault model according to the correlation relationship of the process systems;
setting a limit condition according to the fault model;
determining a boundary condition according to the limit condition;
determining a data anomaly point based on the boundary condition and the historical state information;
predicting the fault type and the fault characteristic based on the data abnormal point by adopting a grey prediction method; the historical state information, the fault type and the fault characteristics are stored in an expert diagnosis knowledge base;
and training a neural network model by adopting data information stored in an expert diagnosis knowledge base to obtain the analysis diagnosis model.
3. The intelligent diagnostic method for thermal control equipment according to claim 2, wherein the data analysis comprises: preprocessing, relevance identification and noise elimination.
4. The intelligent diagnostic method for the thermal control equipment according to claim 1, further comprising:
and generating a maintenance decision according to the diagnosis result.
5. A thermal control device intelligent diagnostic system, comprising:
the information acquisition module is used for acquiring the state information of the equipment to be monitored and extracting characteristic information based on the state information; the characteristic information is used for reflecting the state characteristics of the equipment to be monitored; the state information includes: the control method comprises the following steps of (1) controlling a valve command, controlling the opening degree of the valve, controlling the opening degree of an electric valve, controlling the opening degree of the electric valve, controlling an in-place signal, steam drum water level, feed water flow, main steam pressure and steam drum pressure; the state information comprises state information of a plurality of measuring points;
the diagnosis module is used for generating a diagnosis result of the equipment to be monitored by adopting an analysis diagnosis model according to the state information and the characteristic information; the analysis and diagnosis model is a neural network model established based on historical state information and historical characteristic information of the monitoring equipment by adopting an expert diagnosis algorithm; the diagnosis result comprises a current fault diagnosis result and a predicted fault diagnosis result.
6. The intelligent diagnostic method for the thermal control equipment according to claim 5, further comprising:
the rejecting module is used for carrying out data analysis on the historical state information to reject irrelevant nuisance alarm information or false alarm information; the data analysis comprises: preprocessing, relevance identification and noise elimination;
the model building module is used for building a fault model according to the correlation relationship of the process systems;
the limit condition setting module is used for setting a limit condition according to the fault model;
the boundary condition determining module is used for determining a boundary condition according to the limit value condition;
a data anomaly determination module for determining a data anomaly based on the boundary condition and the historical state information;
the prediction module is used for predicting the fault type and the fault characteristic based on the data abnormal point by adopting a gray prediction method; the historical state information, the fault type and the fault characteristics are stored in an expert diagnosis knowledge base;
and the model training module is used for training the neural network model by adopting the data information stored in the expert diagnosis knowledge base to obtain the analysis and diagnosis model.
7. The intelligent diagnostic method for the thermal control equipment according to claim 1, further comprising:
and the maintenance decision generation module is used for generating a maintenance decision according to the diagnosis result.
8. A thermal control device intelligent diagnostic system, comprising:
the monitoring module of the measuring point, is used for reading the measuring point, monitoring the change situation of the measuring point and extracting the measuring point information, and is used for judging whether the measuring point is normal or not by combining the analysis and diagnosis model and the big data comprehensive analysis, indicating whether the value is correct or not, carrying out alarm grade classification and invalid alarm suppression on the fault information, and pushing out abnormal fault information after screening and cleaning the data; the measuring point information comprises change rate, signal mutation, signal fluctuation, process range overrun and similar unbalance information;
the valve monitoring module is used for monitoring and analyzing the performance state of the valve mechanism in real time according to the equipment measuring point analysis information, the equipment measuring point set value, the equipment measuring point process value, the process parameters of the equipment measuring points and the incidence relation among the equipment measuring points; the valve mechanism includes: the device comprises an electric door, a pneumatic door, a hydraulic door and an actuating mechanism;
the valve-regulating servo valve monitoring module is used for acquiring DCS signals, analyzing the flow characteristics of the steam turbine valve regulating according to relevant process parameters and in combination with an expert model, diagnosing the regulating state of the valve, analyzing and judging the jamming and leakage faults of the servo valve and pushing parameter modification suggestions; the associated process parameters include: valve instructions, feedback information, steam flow, regulation stage pressure, and load changes;
and the AST solenoid valve diagnosis module is used for analyzing whether the solenoid valve coil has faults and leakage or not based on the solenoid valve current, the coil surface temperature and the oil pressure measuring points, and is also used for analyzing the solenoid valve degradation characteristic so as to carry out fault early warning and service life evaluation on the solenoid valve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111043180.8A CN113705924B (en) | 2021-09-07 | 2021-09-07 | Intelligent diagnosis method and system for thermal control equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111043180.8A CN113705924B (en) | 2021-09-07 | 2021-09-07 | Intelligent diagnosis method and system for thermal control equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113705924A true CN113705924A (en) | 2021-11-26 |
| CN113705924B CN113705924B (en) | 2023-10-13 |
Family
ID=78660762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111043180.8A Active CN113705924B (en) | 2021-09-07 | 2021-09-07 | Intelligent diagnosis method and system for thermal control equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705924B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114186666A (en) * | 2021-11-29 | 2022-03-15 | 中电华创(苏州)电力技术研究有限公司 | Generator coil temperature anomaly monitoring method based on self-standardization encoding and decoding |
| CN114294637A (en) * | 2022-01-04 | 2022-04-08 | 华润电力技术研究院有限公司 | Low-temperature economizer state monitoring system and method based on machine learning |
| CN114543898A (en) * | 2022-04-07 | 2022-05-27 | 国网河北省电力有限公司超高压分公司 | Non-invasive detection system for high-voltage circuit breaker operating mechanism |
| CN114757380A (en) * | 2022-04-29 | 2022-07-15 | 西安热工研究院有限公司 | Thermal power plant fault early warning system and method, electronic equipment and storage medium |
| CN115616997A (en) * | 2022-10-17 | 2023-01-17 | 华能威海发电有限责任公司 | Thermal control state monitoring and knowledge base fusion method and system |
| CN116976863A (en) * | 2023-09-20 | 2023-10-31 | 福建福清核电有限公司 | Internet-based proportional valve card data analysis system |
| CN117133109A (en) * | 2023-10-26 | 2023-11-28 | 广州瑞港消防设备有限公司 | Automatic alarm suppression system for energy storage container |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106586796A (en) * | 2016-11-15 | 2017-04-26 | 王蕊 | System and method for monitoring state of escalator |
| CN108008332A (en) * | 2017-11-29 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | A kind of new energy Remote testing device method for diagnosing faults based on data mining |
| CN108388950A (en) * | 2018-01-29 | 2018-08-10 | 杭州安脉盛智能技术有限公司 | Intelligent transformer O＆M method and system based on big data |
| KR20190072165A (en) * | 2017-12-15 | 2019-06-25 | 주식회사 에이스이앤티 | Fault diagnosis system of motor |
| US20190302713A1 (en) * | 2018-03-27 | 2019-10-03 | Terminus (Beijing) Technology Co., Ltd. | Method and device for automatically diagnosing and controlling apparatus in intelligent building |
| CN110442100A (en) * | 2019-08-06 | 2019-11-12 | 华能国际电力股份有限公司玉环电厂 | A kind of thermal control intelligent DCS diagnosis method for early warning and system |
| WO2020001077A1 (en) * | 2018-06-26 | 2020-01-02 | 卡斯柯信号有限公司 | Device fault diagnosis and intelligent early warning method applied to monitoring system |
| CN112817280A (en) * | 2020-12-04 | 2021-05-18 | 华能国际电力股份有限公司玉环电厂 | Implementation method for intelligent monitoring alarm system of thermal power plant |
| US20210208030A1 (en) * | 2020-01-02 | 2021-07-08 | Doosan Heavy Industries & Construction Co., Ltd. | Apparatus and method for diagnosing failure of plant |
-
2021
- 2021-09-07 CN CN202111043180.8A patent/CN113705924B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106586796A (en) * | 2016-11-15 | 2017-04-26 | 王蕊 | System and method for monitoring state of escalator |
| CN108008332A (en) * | 2017-11-29 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | A kind of new energy Remote testing device method for diagnosing faults based on data mining |
| KR20190072165A (en) * | 2017-12-15 | 2019-06-25 | 주식회사 에이스이앤티 | Fault diagnosis system of motor |
| CN108388950A (en) * | 2018-01-29 | 2018-08-10 | 杭州安脉盛智能技术有限公司 | Intelligent transformer O＆M method and system based on big data |
| US20190302713A1 (en) * | 2018-03-27 | 2019-10-03 | Terminus (Beijing) Technology Co., Ltd. | Method and device for automatically diagnosing and controlling apparatus in intelligent building |
| WO2020001077A1 (en) * | 2018-06-26 | 2020-01-02 | 卡斯柯信号有限公司 | Device fault diagnosis and intelligent early warning method applied to monitoring system |
| CN110442100A (en) * | 2019-08-06 | 2019-11-12 | 华能国际电力股份有限公司玉环电厂 | A kind of thermal control intelligent DCS diagnosis method for early warning and system |
| US20210208030A1 (en) * | 2020-01-02 | 2021-07-08 | Doosan Heavy Industries & Construction Co., Ltd. | Apparatus and method for diagnosing failure of plant |
| CN112817280A (en) * | 2020-12-04 | 2021-05-18 | 华能国际电力股份有限公司玉环电厂 | Implementation method for intelligent monitoring alarm system of thermal power plant |
Non-Patent Citations (1)
| Title |
|---|
| 沙德生;吴国民;芮小虎;何立荣;黄俊飞;: "火电厂设备智能化故障预警与诊断系统研究", 电力设备管理, no. 05, pages 37 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114186666A (en) * | 2021-11-29 | 2022-03-15 | 中电华创(苏州)电力技术研究有限公司 | Generator coil temperature anomaly monitoring method based on self-standardization encoding and decoding |
| CN114186666B (en) * | 2021-11-29 | 2023-10-13 | 中电华创(苏州)电力技术研究有限公司 | Generator coil temperature anomaly monitoring method based on self-standardized encoding and decoding |
| CN114294637A (en) * | 2022-01-04 | 2022-04-08 | 华润电力技术研究院有限公司 | Low-temperature economizer state monitoring system and method based on machine learning |
| CN114543898A (en) * | 2022-04-07 | 2022-05-27 | 国网河北省电力有限公司超高压分公司 | Non-invasive detection system for high-voltage circuit breaker operating mechanism |
| CN114543898B (en) * | 2022-04-07 | 2023-11-24 | 国网河北省电力有限公司超高压分公司 | Non-invasive detection system of high-voltage circuit breaker operating mechanism |
| CN114757380A (en) * | 2022-04-29 | 2022-07-15 | 西安热工研究院有限公司 | Thermal power plant fault early warning system and method, electronic equipment and storage medium |
| CN114757380B (en) * | 2022-04-29 | 2024-02-20 | 西安热工研究院有限公司 | Fault early warning system and method for thermal power plant, electronic equipment and storage medium |
| CN115616997A (en) * | 2022-10-17 | 2023-01-17 | 华能威海发电有限责任公司 | Thermal control state monitoring and knowledge base fusion method and system |
| CN116976863A (en) * | 2023-09-20 | 2023-10-31 | 福建福清核电有限公司 | Internet-based proportional valve card data analysis system |
| CN116976863B (en) * | 2023-09-20 | 2023-12-22 | 福建福清核电有限公司 | Internet-based proportional valve card data analysis system |
| CN117133109A (en) * | 2023-10-26 | 2023-11-28 | 广州瑞港消防设备有限公司 | Automatic alarm suppression system for energy storage container |
| CN117133109B (en) * | 2023-10-26 | 2024-02-13 | 广州瑞港消防设备有限公司 | Automatic alarm suppression system for energy storage container |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113705924B (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113705924B (en) | Intelligent diagnosis method and system for thermal control equipment | |
| CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
| CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
| CN110414155B (en) | Fan component temperature abnormity detection and alarm method with single measuring point | |
| RU2313815C2 (en) | Device and method for controlling technical plant, which contains a set of systems, in particular, electric power plant | |
| EP2193413B1 (en) | System for preserving and displaying process control data associated with an abnormal situation | |
| CN108154291B (en) | Power supply plant performance index evaluation method and system based on strategy library | |
| CN109947088A (en) | Equipment fault early-warning system based on model lifecycle management | |
| US6587737B2 (en) | Method for the monitoring of a plant | |
| KR101994465B1 (en) | Method for the computer-assisted monitoring of the operation of a technical system, particularly of an electrical energy-generating installation | |
| CN108803569A (en) | Station boiler diagnostic expert system and its method for diagnosing faults | |
| AU2014324846A1 (en) | Non-intrusive sensor system | |
| Zhang et al. | A fault early warning method for auxiliary equipment based on multivariate state estimation technique and sliding window similarity | |
| CN111929091A (en) | Equipment abnormality detection method and device, readable storage medium and electronic equipment | |
| CN102789676A (en) | Method for designing industrial alarm on basis of alarm evidence fusion | |
| WO2021127646A1 (en) | Device and method for monitoring a system | |
| CN111879522B (en) | Steam turbine operation monitoring and fault distinguishing method and system based on time sequence probability | |
| CN105302476B (en) | A kind of reliability data online acquisition for nuclear power plant equipment analyzes storage system and its storage method | |
| CN114091811A (en) | Maintenance decision system for circulating water pump of nuclear power plant and design method | |
| Liu et al. | A fault early warning and health status rating method for ensuring safe operation of rotating equipment | |
| CN114151291B (en) | Early fault monitoring method for wind turbine generator | |
| KR102512089B1 (en) | Automatic control device for deisel generator using artificial intelligence-based cognitive- control | |
| Athanasopoulou et al. | Intelligent system for identification and replacement of faulty sensor measurements in Thermal Power Plants (IPPAMAS: Part 1) | |
| CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning | |
| Zhang et al. | Research on decision-making process of condition-based maintenance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20211213 Address after: No.58 Haibu Road, Weihai Economic and Technological Development Zone, Shandong Province 264205 Applicant after: HUANENG WEIHAI POWER GENERATION Co.,Ltd. Applicant after: HUANENG SHANDONG POWER GENERATION Co.,Ltd. Applicant after: BEIJING BICOTEST TECH. CO.,LTD. Applicant after: CLP HUACHUANG POWER TECHNOLOGY RESEARCH Co.,Ltd. Address before: 100094 No.01, 5th floor, block a, 8 malianwa North Road, Haidian District, Beijing Applicant before: BEIJING BICOTEST TECH. CO.,LTD. Applicant before: CLP HUACHUANG POWER TECHNOLOGY RESEARCH Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |