CN115982642A - Thermal power station equipment fault early warning method and system based on artificial intelligence - Google Patents
Thermal power station equipment fault early warning method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN115982642A CN115982642A CN202211732505.8A CN202211732505A CN115982642A CN 115982642 A CN115982642 A CN 115982642A CN 202211732505 A CN202211732505 A CN 202211732505A CN 115982642 A CN115982642 A CN 115982642A
- Authority
- CN
- China
- Prior art keywords
- thermal power
- power station
- early warning
- model
- neural network
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application provides a thermal power station equipment fault early warning method and system based on artificial intelligence, and relates to the technical field of the power industry. The method comprises the following steps: the state parameters of the thermal power station equipment and the corresponding fault labels are transmitted to the DCS, and the equipment parameters of the DCS are transmitted to the data driving model through the unidirectional isolation network brake; screening at least one failed thermal power station equipment state parameter from the thermal power station equipment state parameters and the corresponding fault labels as a data sample; and (3) combining the data sample and the data driving model, training the model by using an artificial intelligence method to finish the training operation of the initial neural network model, and obtaining a final neural network early warning model. The accuracy of equipment state assessment can be improved through the neural network early warning model, the equipment fault can be guaranteed to be predicted in advance more possibly, operation and maintenance personnel can find the equipment fault in time conveniently, and hidden dangers are eliminated in advance.
Description
Technical Field
The application relates to the technical field of power industry, in particular to a thermal power station equipment fault early warning method and system based on artificial intelligence.
Background
The structure of automation equipment is becoming more and more complex, so that the problem of equipment failure is inevitable, and in terms of the power generation industry, thermal power still accounts for a large proportion on installed capacity worldwide at present, and whether thermal power unit equipment operates normally or not is directly related to the production safety and economic benefits of power generation enterprises. At present, the traditional operation monitoring mode of the thermal power station mainly depends on constant value alarm, and the fluctuation range and the degradation trend of equipment data are observed less. Before equipment fails, the deviation phenomenon of part of state parameters can not be found, and when the equipment fails, the failure condition is judged and evaluated by the experience and subjectivity of operators.
A part of fault alarm systems judge whether faults exist by utilizing a simple criterion set manually, and the previous running state data of the equipment is ignored. Although some schemes utilize historical data to enhance fault early warning, reference to system operation mechanism relation is lacked in early warning, and accuracy needs to be improved. On the premise, the hidden danger of the equipment cannot be found in time, and early warning cannot be obtained, so that the hidden danger becomes a potential safety hazard. On the other hand, most system functions are only limited to early warning, and the functions of further early warning, diagnosis and fault handling are lacked, so that a closed-loop process from fault discovery to fault elimination cannot be formed. In addition, the complexity and relevance of the equipment structure cause equipment faults to be associated, and the maintenance work is more complicated if the human intervention is delayed.
Disclosure of Invention
The utility model aims to provide a thermal power station equipment trouble early warning method based on artificial intelligence, it can improve the accuracy of equipment state aassessment through neural network early warning model, has guaranteed that equipment trouble can be more probably judged in advance, and the operation and maintenance personnel of being convenient for in time discover, eliminates hidden danger in advance.
Another object of the present application is to provide a thermal power station equipment fault early warning system based on artificial intelligence, which can operate a thermal power station equipment fault early warning method based on artificial intelligence.
The embodiment of the application is realized as follows:
on the first hand, the embodiment of the application provides a thermal power station equipment fault early warning method based on artificial intelligence, which comprises the steps that state parameters of thermal power station equipment and corresponding fault labels are transmitted to a DCS, and equipment parameters of the DCS are transmitted to a data driving model through a one-way isolation network gate; screening at least one failed thermal power station equipment state parameter from the thermal power station equipment state parameters and the corresponding fault labels as a data sample; and (3) combining the data sample and the data driving model, and training the model by using an artificial intelligence method to finish the training operation of the initial neural network model so as to obtain a final neural network early warning model.
In some embodiments of the present application, the state parameters of the thermal power plant device and the corresponding fault tags are transmitted to the DCS system, and the transmission of the device parameters of the DCS system to the data driving model through the unidirectional isolation gatekeeper includes: the state parameter of the thermal power station equipment monitors the working state of the thermal power station equipment through various monitoring equipment arranged on the thermal power station equipment, and sends collected and monitored data to a data driving model in real time, wherein the various monitoring equipment comprises a flame monitor, a gas pressure sensor, a gas analyzer, an exhaust device, an ignition oil gun and a light intensity detector.
In some embodiments of the present application, the above further includes: the device parameters of the DCS are transmitted to the SIS through the first one-way isolation network gate, the device data of the SIS are transmitted to the data driving model through the second one-way isolation network gate, the DCS is a distributed control system of the thermal power station unit, and the SIS acquires the thermal power station unit data from the DCS so as to facilitate system state monitoring.
In some embodiments of the present application, the screening, from the state parameters of the thermal power plant devices and the corresponding fault tags, the state parameters of at least one thermal power plant device with a fault as the data sample includes: and taking the state parameters of the thermal power station equipment as data samples of the initial neural network model, and calculating the initial neural network model to obtain output data.
In some embodiments of the present application, the above training the model by using an artificial intelligence method to complete the training operation of the initial neural network model in combination with the data sample and the data driving model, and obtaining the final neural network early warning model includes: aiming at a thermal power station equipment fault early warning task, designing an initial neural network model, training the initial neural network model based on a training sample, correcting weight parameters in the initial neural network model by adopting a back propagation deviation method according to the result of output data, testing the trained neural network model based on a test sample, and obtaining a final neural network early warning model according to the test result.
In some embodiments of the present application, the above further includes: and continuously training the trained neural network model based on the test sample to obtain the accuracy rate after each round of training, and when the number of training rounds is equal to the preset number of rounds, if the accuracy rate after each round of training in the preset number of rounds is lower than the highest accuracy rate of the trained neural network model in the training sample, taking the trained neural network model as a final neural network early warning model.
In some embodiments of the present application, the above further includes: and based on the evaluation result of the neural network early warning model, early warning of the fault state of the equipment is carried out, fault early warning information is output, fault diagnosis is carried out based on the data driving model, fault intervention is carried out by outputting the fault diagnosis information, and an intervention instruction is output.
In a second aspect, an embodiment of the application provides an artificial intelligence-based thermal power station equipment fault early warning system, which includes a data acquisition and transmission module, and is used for transmitting state parameters of thermal power station equipment and corresponding fault labels to a DCS system, and transmitting equipment parameters of the DCS system to a data driving model through a unidirectional isolation network gate;
the data screening module is used for screening at least one failed thermal power station equipment state parameter from the thermal power station equipment state parameters and the corresponding fault labels to serve as a data sample;
and the fault early warning module is used for combining the data sample and the data driving model, training the model by using an artificial intelligence method to finish the training operation of the initial neural network model, and obtaining a final neural network early warning model.
In some embodiments of the present application, the above includes: at least one memory for storing computer instructions; at least one processor in communication with the memory, wherein the at least one processor, when executing the computer instructions, causes the system to: the system comprises a data acquisition and transmission module, a data screening module and a fault early warning module.
In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method such as any one of artificial intelligence-based thermal power plant equipment fault early warning methods.
Compared with the prior art, the embodiment of the application has at least the following advantages or beneficial effects:
parameter characteristics under different working conditions are learned through equipment operation data, a neural network early warning model is established based on system process characteristics, the accuracy of equipment state evaluation is improved, equipment faults can be more possibly predicted in advance, operation and maintenance personnel can find the faults in time conveniently, and hidden dangers are eliminated in advance; meanwhile, after fault early warning, equipment faults are diagnosed maliciously, and an intervention operation instruction is given, so that the unit operation efficiency is improved, a series of consequences caused by fault occurrence are reduced, namely, the equipment safety is ensured, unnecessary maintenance cost is reduced, and the purposes of cost reduction and efficiency improvement are achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic diagram illustrating steps of a thermal power station equipment fault early warning method based on artificial intelligence according to an embodiment of the present application;
fig. 2 is a schematic diagram of a thermal power station equipment fault early warning system module based on artificial intelligence according to an embodiment of the present disclosure;
fig. 3 is an electronic device according to an embodiment of the present disclosure.
Icon: 10-a data acquisition and transmission module; 20-a data screening module; 30-a fault pre-warning module; 101-a memory; 102-a processor; 103-a communication interface.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. 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 application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures.
It should be noted that the term "comprises/comprising" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The embodiments described below and the individual features of the embodiments can be combined with one another without conflict.
Example 1
Referring to fig. 1, fig. 1 is a schematic diagram illustrating steps of a thermal power plant equipment fault early warning method based on artificial intelligence according to an embodiment of the present application, and the steps are as follows:
step S100, transmitting the state parameters of the thermal power station equipment and the corresponding fault labels to a DCS, and transmitting the equipment parameters of the DCS to a data driving model through a one-way isolation network gate;
in some embodiments, a thermal power plant apparatus may include a flame monitor disposed within a furnace of a thermal power plant boiler; the gas pressure sensor is arranged in the hearth; one end of the gas analyzer is arranged at one end of a flue of the thermal power station boiler, which is close to the hearth; the air exhaust equipment is communicated with the hearth; the ignition oil gun is arranged on one side of the hearth; the laser generator and the light intensity detector are respectively arranged on two sides in the flue, the laser generator and the light intensity detector are arranged oppositely, and the light intensity detector can receive laser emitted by the laser generator and measure light intensity; the DCS is a distributed control system of the thermal power station unit; the first unidirectional isolation network gate is safety protection equipment among network equipment, and ensures the unidirectional transmission safety of data; the SIS acquires thermal power station unit data from the DCS, so that the system state monitoring is facilitated; the second unidirectional isolation gatekeeper is safety protection equipment among network equipment, ensures the unidirectional transmission safety of data, and transmits the state parameters of thermal power station equipment and corresponding fault tags to the data driving model through the communication module.
Step S110, screening at least one state parameter of the thermal power station equipment with faults from the state parameters of the thermal power station equipment and the corresponding fault labels as a data sample;
in some embodiments, state parameters and corresponding fault labels of thermal power plant equipment are obtained; and creating a data set sample library, connecting the data set sample library with a data driving model, and screening the state parameters of a plurality of thermal power station devices with faults from the state parameters of the thermal power station devices and the corresponding fault labels to serve as data samples.
And step S120, combining the data samples and the data driving model, and training the model by using an artificial intelligence method to finish the training operation of the initial neural network model to obtain a final neural network early warning model.
In some embodiments, the data set sample library screens the failure state parameters as data samples, training and testing an initial neural network model based on the data samples to obtain a final neural network early warning model, inputting the obtained real-time equipment state parameters into the final neural network early warning model to obtain a failure prediction result, realizing omnibearing monitoring of thermal power station equipment, and having high prediction result precision. As a preferred scheme, the data samples comprise training samples and testing samples, the data samples are input into the initial neural network model to complete the training operation of the initial neural network model, and the obtaining of the final neural network early warning model comprises the following steps: aiming at a thermal power station equipment fault early warning task, designing an initial neural network model; training the initial neural network model based on the training samples; and testing the trained neural network model based on the test sample, and obtaining a final neural network early warning model according to a test result. And the final neural network early warning model predicts the equipment state under the real-time working condition, compares the equipment state with actual data, and gives an alarm once deviation occurs. And training the final neural network early warning model by using real-time and historical fault state data of the equipment to perform equipment fault diagnosis and intervention operation.
Example 2
And S200, monitoring the working state of the thermal power station equipment through various monitoring equipment arranged on the thermal power station equipment according to the state parameters of the thermal power station equipment, and transmitting the acquired and monitored data to a data driving model in real time, wherein the various monitoring equipment comprises a flame monitor, a gas pressure sensor, a gas analyzer, an exhaust device, an ignition oil gun and a light intensity detector.
And step S210, transmitting the equipment parameters of the DCS to the SIS through the first unidirectional isolation network gate, and transmitting the equipment data of the SIS to the data driving model through the second unidirectional isolation network gate, wherein the DCS is a distributed control system of the thermal power station unit, and the SIS acquires the thermal power station unit data from the DCS so as to facilitate system state monitoring.
And step S220, taking the state parameters of the thermal power station equipment as data samples of the initial neural network model, and calculating the initial neural network model to obtain output data.
Step S230, aiming at a thermal power station equipment fault early warning task, designing an initial neural network model, training the initial neural network model based on a training sample, correcting weight parameters in the initial neural network model by adopting a back propagation deviation method according to the result of output data, testing the trained neural network model based on a test sample, and obtaining a final neural network early warning model according to the test result.
And S240, continuously training the trained neural network model based on the test sample to obtain the accuracy rate after each round of training, and when the number of training rounds is equal to the preset number of rounds, if the accuracy rate after each round of training in the preset number of rounds is lower than the highest accuracy rate of the trained neural network model in the training sample, taking the trained neural network model as a final neural network early warning model.
And S250, performing equipment fault state early warning based on the evaluation result of the neural network early warning model, outputting fault early warning information, performing fault diagnosis based on the data driving model, outputting fault diagnosis information for fault intervention, and outputting an intervention instruction.
In some embodiments, after real-time and historical data is obtained, the model is trained by using an artificial intelligence method (deep neural network, automatic machine learning, knowledge map, etc.) to form a final neural network early warning model; acquiring real-time data, analyzing and evaluating the equipment state to form an evaluation result, and outputting the evaluation result to a fault early warning module; the fault early warning module acquires real-time data from the real-time data acquisition module, performs equipment fault state early warning based on the evaluation results of the data driving model module and the mechanism driving model module, and outputs early warning information; and the fault diagnosis module acquires fault early warning information, performs fault diagnosis based on the equipment fault model module and outputs diagnosis information.
The initial neural network model comprises a plurality of convolution layers, a plurality of Relu activation functions, a global average pooling layer and two full-connection layers; the plurality of convolution layers are connected in sequence, and a Relu activation function is connected behind each convolution layer; connecting a global average pooling layer after the last convolutional layer; connecting two full-connection layers behind the global average pooling layer, wherein the two full-connection layers comprise a first full-connection layer and a final full-connection layer; and the final full-connection layer is an output layer of the neural network model, a Dropout operation is added to the final full-connection layer by using a softmax function, and the final full-connection layer outputs a fault prediction result.
Specifically, the convolutional neural network model comprises a plurality of convolutional layers, a global average pooling layer and two full-connection layers; the convolution layers are connected in sequence, a Relu activation function is used after each convolution layer, a global average pooling layer is used after the last convolution layer, two full-connection layers are connected after the global average pooling, the two full-connection layers comprise a first full-connection layer and a final full-connection layer, the final full-connection layer is an output layer of the neural network model, and the number of neurons output by the final full-connection layer, namely the classification number, is equal to the number of types of organisms in the final biological image data set. Finally, the full-connection layer uses a softmax function to perform multi-classification, the recognition accuracy is improved, dropout operation is added, and the accuracy is prevented from being influenced by over-fitting output.
Example 3
Referring to fig. 2, fig. 2 is a schematic diagram of a thermal power plant equipment fault early warning system module based on artificial intelligence according to an embodiment of the present application, which is as follows:
the data acquisition and transmission module 10 is used for transmitting the state parameters of the thermal power station equipment and the corresponding fault tags to the DCS, and transmitting the equipment parameters of the DCS to the data driving model through the unidirectional isolation network brake;
the data screening module 20 is configured to screen at least one failed thermal power station device state parameter from the thermal power station device state parameters and the corresponding fault tags as a data sample;
and the fault early warning module 30 is used for combining the data samples and the data driving model, training the model by using an artificial intelligence method to complete the training operation of the initial neural network model, and obtaining a final neural network early warning model.
As shown in fig. 3, an embodiment of the present application provides an electronic device, which includes a memory 101 for storing one or more programs; a processor 102. The one or more programs, when executed by the processor 102, implement the method of any of the first aspects as described above.
Also included is a communication interface 103, and the memory 101, processor 102 and communication interface 103 are electrically connected to each other, directly or indirectly, to enable transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules, and the processor 102 executes the software programs and modules stored in the memory 101 to thereby execute various functional applications and data processing. The communication interface 103 may be used for communicating signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a Random Access Memory 101 (RAM), a Read Only Memory 101 (ROM), a Programmable Read Only Memory 101 (PROM), an Erasable Read Only Memory 101 (EPROM), an electrically Erasable Read Only Memory 101 (EEPROM), and the like.
The processor 102 may be an integrated circuit chip having signal processing capabilities. The Processor 102 may be a general-purpose Processor 102, including a Central Processing Unit (CPU) 102, a Network Processor 102 (NP), and the like; but may also be a Digital Signal processor 102 (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware components.
In the embodiments provided in the present application, it should be understood that the disclosed method and system can be implemented in other ways. The method and system embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In another aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by the processor 102, implements the method according to any one of the first aspect described above. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory 101 (ROM), a Random Access Memory 101 (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In summary, the thermal power station equipment fault early warning method and system based on artificial intelligence provided by the embodiment of the application learn parameter characteristics under different working conditions through equipment operation data, establish a neural network early warning model based on system process characteristics, improve the accuracy of equipment state assessment, ensure that equipment faults can be predicted in advance more possibly, facilitate timely discovery of operation and maintenance personnel, and eliminate hidden dangers in advance; meanwhile, after fault early warning, equipment faults are diagnosed maliciously, an intervention operation instruction is given, the running efficiency of a unit is improved, a series of consequences caused by fault occurrence are reduced, the equipment safety is ensured, unnecessary maintenance cost is reduced, and the purposes of cost reduction and efficiency improvement are achieved.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. A thermal power station equipment fault early warning method based on artificial intelligence is characterized by comprising the following steps:
the state parameters of the thermal power station equipment and the corresponding fault labels are transmitted to the DCS, and the equipment parameters of the DCS are transmitted to the data driving model through the unidirectional isolation network brake;
screening at least one failed thermal power station equipment state parameter from the thermal power station equipment state parameters and the corresponding fault labels as a data sample;
and (3) combining the data sample and the data driving model, training the model by using an artificial intelligence method to finish the training operation of the initial neural network model, and obtaining a final neural network early warning model.
2. The artificial intelligence-based thermal power station equipment fault early warning method as claimed in claim 1, wherein the state parameters of the thermal power station equipment and the corresponding fault labels are transmitted to a DCS system, and the transmission of the equipment parameters of the DCS system to the data driving model through a unidirectional isolation network gate comprises:
the state parameters of the thermal power station equipment monitor the working state of the thermal power station equipment through various monitoring equipment arranged on the thermal power station equipment, and send collected and monitored data to a data driving model in real time, wherein the various monitoring equipment comprises a flame monitor, a gas pressure sensor, a gas analyzer, an exhaust device, an ignition oil gun and a light intensity detector.
3. The thermal power station equipment fault early warning method based on artificial intelligence as claimed in claim 2, characterized by further comprising:
the device parameters of the DCS are transmitted to the SIS through the first one-way isolation network gate, the device data of the SIS are transmitted to the data driving model through the second one-way isolation network gate, the DCS is a distributed control system of the thermal power station unit, and the SIS acquires the thermal power station unit data from the DCS so as to facilitate system state monitoring.
4. The thermal power station equipment fault early warning method based on artificial intelligence as claimed in claim 1, wherein the step of screening at least one faulty thermal power station equipment state parameter from the thermal power station equipment state parameters and the corresponding fault labels as a data sample comprises:
and taking the state parameters of the thermal power station equipment as data samples of the initial neural network model, and calculating the initial neural network model to obtain output data.
5. The thermal power station equipment fault early warning method based on artificial intelligence as claimed in claim 1, wherein the combining the data sample and the data driving model, using the artificial intelligence method training model to complete the training operation of the initial neural network model, and obtaining the final neural network early warning model comprises:
aiming at a thermal power station equipment fault early warning task, designing an initial neural network model, training the initial neural network model based on a training sample, correcting weight parameters in the initial neural network model by adopting a back propagation deviation method according to the result of output data, testing the trained neural network model based on a test sample, and obtaining a final neural network early warning model according to the test result.
6. The thermal power station equipment fault early warning method based on artificial intelligence as claimed in claim 5, characterized by further comprising:
and continuously training the trained neural network model based on the test sample to obtain the accuracy rate after each round of training, and when the number of training rounds is equal to the preset number of rounds, if the accuracy rate after each round of training in the preset number of rounds is lower than the highest accuracy rate of the trained neural network model in the training sample, taking the trained neural network model as a final neural network early warning model.
7. The thermal power station equipment fault early warning method based on artificial intelligence as claimed in claim 6, characterized by further comprising:
and based on the evaluation result of the neural network early warning model, early warning of the fault state of the equipment is carried out, fault early warning information is output, fault diagnosis is carried out based on the data driving model, fault intervention is carried out by outputting the fault diagnosis information, and an intervention instruction is output.
8. The utility model provides a thermal power station equipment trouble early warning system based on artificial intelligence which characterized in that includes:
the data acquisition and transmission module is used for transmitting the state parameters of the thermal power station equipment and the corresponding fault labels to the DCS, and the equipment parameters of the DCS are transmitted to the data driving model through the one-way isolation network gate;
the data screening module is used for screening at least one failed thermal power station equipment state parameter from the thermal power station equipment state parameters and the corresponding fault labels to serve as a data sample;
and the fault early warning module is used for combining the data sample and the data driving model, training the model by using an artificial intelligence method to finish the training operation of the initial neural network model, and obtaining a final neural network early warning model.
9. The thermal power plant equipment fault early warning system based on artificial intelligence as claimed in claim 8, characterized by comprising:
at least one memory for storing computer instructions;
at least one processor in communication with the memory, wherein the at least one processor, when executing the computer instructions, causes the system to perform: the device comprises a data acquisition and transmission module, a data screening module and a fault early warning module.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211732505.8A CN115982642A (en) | 2022-12-30 | 2022-12-30 | Thermal power station equipment fault early warning method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211732505.8A CN115982642A (en) | 2022-12-30 | 2022-12-30 | Thermal power station equipment fault early warning method and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115982642A true CN115982642A (en) | 2023-04-18 |
Family
ID=85967794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211732505.8A Pending CN115982642A (en) | 2022-12-30 | 2022-12-30 | Thermal power station equipment fault early warning method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115982642A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052233A (en) * | 2021-03-24 | 2021-06-29 | 中国大唐集团科学技术研究院有限公司中南电力试验研究院 | Thermal power station equipment fault early warning system and method based on big data and neural network |
| CN115167324A (en) * | 2022-08-22 | 2022-10-11 | 上海外高桥第三发电有限责任公司 | Thermal power station equipment fault early warning, diagnosis and intervention system and method |
-
2022
- 2022-12-30 CN CN202211732505.8A patent/CN115982642A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113052233A (en) * | 2021-03-24 | 2021-06-29 | 中国大唐集团科学技术研究院有限公司中南电力试验研究院 | Thermal power station equipment fault early warning system and method based on big data and neural network |
| CN115167324A (en) * | 2022-08-22 | 2022-10-11 | 上海外高桥第三发电有限责任公司 | Thermal power station equipment fault early warning, diagnosis and intervention system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086889B (en) | Terminal fault diagnosis method, device and system based on neural network | |
| US20080177683A1 (en) | Method and apparatus for mobile intelligence | |
| CN113935497A (en) | Intelligent operation and maintenance fault processing method, device and equipment and storage medium thereof | |
| US20110314331A1 (en) | Automated test and repair method and apparatus applicable to complex, distributed systems | |
| CN101989087A (en) | On-line real-time failure monitoring and diagnosing system device for industrial processing of residual oil | |
| WO2002071360A1 (en) | System, apparatus and method for diagnosing a flow system | |
| CN107423205B (en) | System fault early warning method and system for data leakage prevention system | |
| RU2431175C1 (en) | System for integral monitoring of operation of aircraft onboard equipment | |
| CN112668873A (en) | Mine safety situation analysis and prediction early warning method | |
| CN116308304A (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| EP3982225B1 (en) | Method and system for regime-based process optimization of industrial assets | |
| KR102328842B1 (en) | Facility management method and apparatus performing the same | |
| GB2558489A (en) | System and method for monitoring a turbomachine, with indicator merging for the synthesis of an alarm confirmation | |
| CN110765633A (en) | Intelligent management method and device for power device | |
| CN115982642A (en) | Thermal power station equipment fault early warning method and system based on artificial intelligence | |
| WO2019143595A1 (en) | Radio frequency sensor system incorporating machine learning system and method | |
| Liu et al. | Deep learning approach for sensor data prediction and sensor fault diagnosis in wind turbine blade | |
| CN105447518A (en) | Remote measurement data interpretation system based on K-means | |
| US20230325640A1 (en) | Artificial intelligence-based anomaly detection and prediction | |
| CN116863664A (en) | Real-time monitoring method and system for gas equipment | |
| CN117113135A (en) | Carbon emission anomaly monitoring and analyzing system capable of sorting and classifying anomaly data | |
| US20230376024A1 (en) | Device and Method for Identifying Anomalies in an Industrial System for Implementing a Production Process | |
| US20240160165A1 (en) | Method and System for Predicting Operation of a Technical Installation | |
| Ait-Alla et al. | Real-time fault detection for advanced maintenance of sustainable technical systems | |
| CN115167324A (en) | Thermal power station equipment fault early warning, diagnosis and intervention system and method |
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 |