WO2023207190A1 - Fault early warning system and method for fossil fuel power plant, electronic device, and storage medium - Google Patents

Abstract

The present application provides a fault early warning system and method for a fossil fuel power plant, an electronic device, and a storage medium. The system comprises a data acquisition module, a data management module and a model building module; the data acquisition module is used for acquiring operation data of each piece of power equipment in a current fossil fuel power plant unit; the data management module is used for analyzing the operation data so as to screen, in the operation data, for model data required for building fault early warning models for different power equipment, and determining operation characteristic information of the power equipment; the model building module is used for building fault early warning models corresponding to the power equipment according to the model data and the operation characteristic information of the power equipment, so as to carry out fault early warning on the current fossil fuel power plant on the basis of the fault early warning models.

Description

A thermal power plant fault early warning system, method, electronic device and storage medium

Cross-references to related applications

This application requires the priority of the Chinese patent application submitted to the China Patent Office on April 29, 2022, with the application number 202210474490.3 and the invention title "A thermal power plant fault early warning system, method, electronic equipment and storage medium", all of which The contents are incorporated into this application by reference.

Technical field

This application relates to the technical field of thermal power plant safety management, and in particular to a thermal power plant fault early warning system, method, electronic equipment and storage medium.

Background technique

Currently, Distributed Control System (DCS) is widely used in various industries such as electric power, metallurgy, and petrochemicals due to its versatility, multi-layer classification, and reliability. In traditional thermal power plants, the control of each power equipment is mainly based on DCS distributed control.

In the existing technology, the DCS system usually performs key display or interlocking protection actions on the host computer when the abnormal measuring point reaches the alarm level or protection level. Although the safety alarm of the thermal power plant unit is achieved, it cannot guarantee the stable operation of the unit. sex.

Contents of the invention

The purpose of this application is to provide a thermal power plant fault early warning system, method, electronic equipment and storage medium to solve the problem that the existing technology cannot guarantee the stability of the operation of thermal power plant units.

The first aspect of this application provides a thermal power plant fault early warning system, including: a data acquisition module, a data management module and a model building module;

The data collection module is used to obtain the operating data of each power equipment in the current thermal power plant unit, and write the operating data into the data management module;

The data management module is used to analyze the received operating data, to screen the model data required to construct different power equipment fault warning models in the operating data, and to determine the operating characteristic information of each of the power equipment, Send the model data and operating characteristic information of each power equipment to the model building module;

The model building module is used to construct a fault warning model corresponding to each of the power equipment according to the model data and the operating characteristic information of each of the power equipment, so as to conduct a warning on the current thermal power plant based on each of the fault warning models. Failure warning.

Optionally, the data collection module is specifically used for:

Obtain the measurement data of each electric equipment from the measuring instrument of each electric equipment in the current thermal power plant unit;

Obtain the monitoring data of each of the power equipment from the DCS system of the current thermal power plant;

The measurement data and monitoring data are summarized to obtain the operation data of each power equipment.

Optionally, the data management module is specifically used for:

Perform working condition analysis on the received operating data to distinguish the operating data of each of the power equipment under different working conditions;

For any of the power equipment, the operating data under the target operating conditions are determined as the model data required to build the power equipment fault early warning model.

Optionally, the data management module is specifically used for:

Compare the similarities between the operating characteristic information of multiple units of the same type as the current thermal power plant unit to obtain the basic operating characteristic information of the current thermal power plant unit;

Determine the operation characteristic information of each electric power equipment according to the operation data of each electric equipment in the current thermal power plant unit and the basic operation characteristic information;

Wherein, the operation data includes the operation data during the infrastructure construction period and the operation data during the operation period of the electric power equipment.

Optionally, the model building module is specifically used for:

For any of the power equipment, construct an initial fault warning model corresponding to the power equipment based on the interaction between different operating indicators represented by the operating characteristic information of the power equipment;

Using the model data required by the power equipment fault warning model, the initial fault warning model is trained to obtain a fault warning model of the power equipment.

Optionally, also includes:

An optimization module, used to obtain abnormal data generated during the application process of the fault warning model, and update the operating data and operating characteristic information in the data management module according to the application blind spots of the fault warning model represented by the abnormal data; The fault warning model is optimized according to the update status of the operating data and operating characteristic information in the data management module.

Optionally, the fault warning model at least includes a reverse osmosis membrane fouling model specialized in chemical water, a steam-driven feedwater pump insufficient output model specialized in steam turbines, a flue resistance abnormality model specialized in boilers, and an abnormal unit index warning model.

The second aspect of this application provides a thermal power plant fault early warning method, including:

Obtain the operating data of each electrical equipment in the current thermal power plant unit;

Analyze the operating data to screen the model data required to construct different power equipment fault warning models in the operating data, and determine the operating characteristic information of each of the power equipment;

According to the model data and the operating characteristic information of each of the power equipment, a fault early warning model corresponding to each of the power equipment is constructed, so as to perform a fault early warning on the current thermal power plant based on each of the fault early warning models.

A third aspect of the present application provides an electronic device, including: at least one processor and a memory;

The memory stores computer execution instructions;

The at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the method described in the above second aspect and various possible designs of the second aspect.

A fourth aspect of the present application provides a computer-readable storage medium. Computer-executable instructions are stored in the computer-readable storage medium. When the processor executes the computer-executable instructions, the above second aspect and the second aspect are realized. approach in terms of various possible designs.

The technical solution of this application has the following advantages:

This application provides a thermal power plant fault early warning system, method, electronic equipment and storage medium. The system includes: a data acquisition module, a data management module and a model building module; the data acquisition module is used to obtain each power equipment in the current thermal power plant unit. operating data, and writes the operating data into the data management module; the data management module is used to analyze the received operating data to screen the model data required to build different power equipment fault warning models in the operating data, and determine the The operating characteristic information of the equipment sends the model data and the operating characteristic information of each power equipment to the model building module; the model building module is used to build a fault warning model corresponding to each power equipment based on the model data and the operating feature information of each power equipment. Provide fault early warning for current thermal power plants based on each fault early warning model. The system provided by the above solution builds a fault warning model for each power equipment in the current thermal power plant unit by combining the operating characteristic information of each power equipment, and uses the fault warning model to discover faults in the power equipment in advance before the DCS system alarms. Timely troubleshooting ensures the stability of unit operation.

Description of the drawings

In order to more clearly explain the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments of the present application or the prior art. Obviously, the drawings in the following description Regarding some of the embodiments of this application, those of ordinary skill in the art can also obtain other embodiments and drawings based on these drawings.

Figure 1 is a schematic structural diagram of a thermal power plant fault early warning system provided by an embodiment of the present application.

Figure 2 is a schematic flowchart of a thermal power plant fault early warning method provided by an embodiment of the present application.

FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

Through the above-mentioned drawings, clear embodiments of the present application have been shown, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the present application to those skilled in the art with reference to specific embodiments.

Detailed ways

In order to make the purpose, 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 in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments These are part of the embodiments of this application, but not all of them. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

Furthermore, the terms “first”, “second”, etc. are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. In the description of the following embodiments, "plurality" means two or more, unless otherwise explicitly and specifically limited.

In the existing technology, when certain power systems or equipment in thermal power plants operate in an abnormal state during operation, professionals must promptly discover and accurately determine the cause of the failure based on professional knowledge, and further allow the operators to promptly adjust the abnormal power The working status of the system or equipment can restore the power system or equipment to normal working conditions. Otherwise, the DCS system will perform key display or interlock protection actions on the host computer when the abnormal measuring point reaches the alarm level or protection level respectively. In the actual operation of the site, due to the accumulation of professional theoretical knowledge contained in the thermal power generation unit and the accumulation of operating faults in the power system or equipment, the complexity of each power system or equipment has increased, and at the same time, the nonlinearity and coupling between the operating conditions of the power system or equipment are high. , The inertia is so large that it is basically impossible to achieve all aspects of the requirements for predicting hidden faults by professionals. When the early symptoms of power system or equipment failure cannot be discovered in time, under the influence of the spread of abnormal working conditions, it will affect the safe, economical and stable operation of the unit. When the problem is serious, it may even cause irreversible damage to the power system or equipment, and the non-compliance of the unit. Normal shutdown.

In response to the above problems, embodiments of the present application provide a thermal power plant fault early warning system, method, electronic device and storage medium. The system includes: a data acquisition module, a data management module and a model construction module; the data acquisition module is used to obtain the current thermal power plant The operating data of each power equipment in the unit is written into the data management module; the data management module is used to analyze the received operating data to filter out the models required to build different power equipment fault warning models in the operating data. data, and determine the operating characteristic information of each power equipment, and send the model data and the operating characteristic information of each power equipment to the model building module; the model building module is used to construct each power equipment based on the model data and the operating feature information of each power equipment. The corresponding fault early warning model is used to provide fault early warning for the current thermal power plant based on each fault early warning model. The system provided by the above solution builds a fault warning model for each power equipment in the current thermal power plant unit by combining the operating characteristic information of each power equipment, and uses the fault warning model to discover faults in the power equipment in advance before the DCS system alarms. Timely troubleshooting ensures the stability of unit operation.

The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

Embodiments of the present application provide a thermal power plant fault early warning system, which is used to provide fault early warning for power equipment in the thermal power plant units.

Figure 1 is a schematic structural diagram of a thermal power plant fault early warning system provided by an embodiment of the present application. As shown in the figure, the system 10 includes: a data collection module 101, a data management module 102 and a model building module 103.

Among them, the data acquisition module is used to obtain the operating data of each power equipment in the current thermal power plant unit, and write the operating data into the data management module; the data management module is used to analyze the received operating data to filter the operating data Model data required to build different power equipment fault early warning models, and determine the operating characteristic information of each power equipment, and send the model data and operating characteristic information of each power equipment to the model building module; the model building module is used to build the model based on the model data and each power equipment. Based on the operating characteristic information of power equipment, a fault early warning model corresponding to each power equipment is constructed to provide fault early warning for the current thermal power plant based on each fault early warning model.

It should be noted that power equipment mainly includes steam turbines and boilers, etc., and the operating data of power equipment includes a number of operating indicators of the power equipment at this time, such as main feed water flow, total coal volume, total air volume, etc.

Specifically, the operation data of each power equipment in the current thermal power plant unit can be obtained as comprehensively as possible based on the data acquisition module. Since the collected operation data are of various types and are not easy to be directly analyzed and processed, the data acquisition module sends the operation data to Data management module. The data management module analyzes and processes the obtained operating data according to the construction requirements of fault warning models of different power equipment, and finally obtains the model data required to build fault warning models of different power equipment. At the same time, due to the coupling between the operating data of power equipment, such as the total air volume and total coal volume, which will affect the combustion effect in the furnace, the data management module will combine the relevant knowledge of thermal power generation and calculate the operating data of each power equipment based on the operating data of each power equipment. , determine the operating characteristic information of each power equipment. Optionally, the data management module sends the model data and operating characteristic information of each power equipment to the model construction module so that it can build a fault warning model for each power equipment.

Optionally, after performing a fault early warning on the current thermal power plant based on the above fault early warning model and generating a fault early warning signal for the current thermal power plant, the fault early warning signal is pushed to the PC or mobile terminal of professional engineers and operators to remind them. It conducts corresponding fault management work in a timely manner.

Optionally, in order to further improve the fault management efficiency of professional engineers and operators, the fault warning model can push corresponding fault management plans according to the cause of the fault while pushing the fault warning signal. After the power equipment with early warning is restored to normal operating conditions from the fault warning state, new unit operating data will be formed and reflected in the data stream in real time, as a new round of fault warning cycle begins.

Since thermal power plants are divided into five majors: steam turbine, boiler, electrical, thermal control and power plant chemistry, the fault early warning model provided by the embodiment of this application at least includes a reverse osmosis membrane fouling model for chemical water and a steam-driven feed water pump output for steam turbines. Deficiency model, boiler professional flue resistance abnormality model and unit index abnormality early warning model.

For example, for the reverse osmosis membrane fouling model, since the fouling situation of the reverse osmosis membrane is characterized by the pressure difference between sections, the inlet water flow, inlet water temperature, inlet water conductivity, high-pressure pump frequency, etc. can be selected as parameters, and through the reverse osmosis membrane The permeable membrane fouling model identifies the fouling trend process and provides corresponding early warning when severe fouling occurs in the reverse osmosis membrane during operation. For the model of insufficient output of the steam-driven feed water pump, since the insufficient output of the steam-driven feed water pump is represented by the main feed water flow of the unit, industrial extraction steam pressure, industrial extraction steam temperature, deaerator water level, deaerator pressure, steam pump inlet flow, Using the steam pump speed, condenser vacuum, etc. as parameters, the steam feed water pump output under the influence of multi-parameter variables is predicted through the steam feed water pump output shortage model, and compared with the real-time steam feed water pump output, when the steam feed water pump output appears Provide corresponding early warning when abnormality occurs. For the flue resistance abnormality model, the flue resistance abnormality will be characterized by the flue inlet pressure and the flue outlet pressure at a certain point, and the uncorrected total coal amount, flue gas oxygen content, total air volume, flue gas temperature, etc. are selected as parameters. The flue resistance abnormality model is used to predict the boiler flue resistance under the influence of multi-parameter variables, and the real-time flue resistance is compared to provide corresponding early warning when the resistance is abnormal. For the unit index abnormality early warning model, the unit index abnormality will be represented by the unit design parameters, and the actual parameters of the unit are selected as comparison parameters. The current unit operating status is determined in real time through the unit index abnormality early warning model, and the optimal unit operation index is evaluated based on the current operating conditions. The current operating status of the unit. When it is determined that the current operating status of the unit is abnormal, a corresponding early warning will be issued.

It should be noted that the fault warning model provided by the embodiments of the present application is not limited to the above-mentioned reverse osmosis membrane fouling model, steam-powered water pump insufficient output model, flue resistance abnormality model and unit index abnormality warning model. The specific warning model can be based on the actual warning model. requirements, and build a corresponding fault warning model.

On the basis of the above embodiments, as an implementable manner, in one embodiment, the data acquisition module is specifically used to obtain the measurement data of each electric equipment from the measuring instrument of each electric equipment in the current thermal power plant unit; Obtain the monitoring data of each power equipment from the DCS system of the current thermal power plant; summarize the measurement data and monitoring data to obtain the operation data of each power equipment.

It should be noted that if the measurement data of the power equipment is only obtained by the measuring instrument of the power equipment and the measurement data is used as the operating data of the power equipment, the integrity and comprehensiveness of the operating data may not be guaranteed. Therefore, the data acquisition module also Obtain monitoring data of power equipment from the monitoring data storage platform of the DCS system of the current thermal power plant.

Among them, there are some repeated data in the obtained measurement data and monitoring data, so the measurement data and monitoring data can be combined to obtain the operation data of the power equipment.

Specifically, the data collection module can use the big data traceability platform of the current thermal power plant to obtain the monitoring data of each power equipment from the DCS system of the current thermal power plant.

On the basis of the above embodiments, as an implementable manner, in one embodiment, the data management module is specifically used to perform operating condition analysis on the received operating data to distinguish the operating conditions of each of the power equipment in different situations. Operating data under working conditions; for any of the power equipment, determine the operating data under target working conditions as the model data required to build the power equipment fault early warning model.

It should be noted that the operating data obtained by the data acquisition module is all the operating data of the power equipment over many years, covering a variety of working conditions. If the fault warning model of the power equipment is constructed directly based on the obtained operating data, the fault will not be guaranteed. Accuracy of early warning models.

Specifically, the data management module performs working condition analysis on the currently received operating data of the power equipment, specifically according to a preset time interval, such as 1 minute or 5 minutes, etc., based on multiple items included in the operating data within the current time interval. Operating indicators determine the specific operating conditions of the power equipment within this time interval. By analogy, the operating data of the power equipment is divided into operating data under each operating condition, and then the operating data corresponding to at least one target operating condition is selected. as the model data of the electrical equipment.

For example, taking the reverse osmosis membrane as an example, by analyzing the operating conditions of the reverse osmosis membrane, the reverse osmosis membrane can be distinguished between flushing conditions, variable flow conditions, small flow conditions, large flow conditions, and maintenance conditions. operating conditions, chemical cleaning conditions and shutdown conditions. Combined with the early warning target requirements of the reverse osmosis membrane fouling model, if the large flow condition is defined as the target condition, the operating data corresponding to the large flow condition is extracted as the model data required to build the reverse osmosis membrane fouling model. If large flow conditions and small flow conditions are defined as target conditions at the same time, then the operating data corresponding to the large flow conditions are extracted as the model data required to build the first reverse osmosis membrane fouling model, and the corresponding operating data for the small flow conditions are extracted. The operating data is used as the model data required to construct the second reverse osmosis membrane fouling model. The first reverse osmosis membrane fouling model is applied under large flow conditions, and the second reverse osmosis membrane fouling model is applied under small flow conditions. Next, the first reverse osmosis membrane fouling model and the second reverse osmosis membrane fouling model can also be coupled into one reverse osmosis membrane fouling model.

Since the thermal power plant units involve a large number of electric equipment, the embodiments of this application do not explain other electric equipment one by one. The details can be adapted according to the actual application objects.

Specifically, in one embodiment, the data management module is specifically used to compare the similarities between the operating characteristic information of multiple units of the same type as the current thermal power plant unit, and obtain the basic operating characteristic information of the current thermal power plant unit; according to The current operating data and basic operating characteristic information of each power equipment in the thermal power plant unit determines the operating characteristic information of each power equipment.

It should be noted that since the data quality of the operating data received by the data management module cannot be guaranteed, after obtaining the operating data, the data management module will first perform pre-processing operations on the operating data, such as null value processing, noise reduction processing and regression. Unified processing, etc. Noise reduction processing can use differential transformation, logarithmic transformation, Fourier transform, wavelet transform, selected threshold noise reduction, artificial expert analysis, regression fitting and cluster analysis, etc. Normalization processing can use maximum and minimum value normalization. Methods such as unified, standard normalization, batch normalization and layer-by-layer normalization.

Among them, the differential change can be based on the function: △f(x _k )=f(x _k+1 )-f(x _k ); the logarithmic change can be based on the function: S=log _a N; the Fourier change can be based on function:

conduct.

Among them, normalization processing includes but is not limited to linear function normalization. The linear function linearizes the original data into the range of [0,1]. The linear function normalization formula is as follows:

Standard normalization. The standard normalization method normalizes the original data into a data set with a mean of 0 and a variance of 1. The normalization formula is as follows:

Robust normalization converts the original data distribution into a distribution with a median of 0 and an IQR of 1. The robust normalization formula is as follows: d′ _i = (d _i -median)/(quantile ₇₅ -quantile ₂₅ ) and other normalization methods.

Specifically, the common principles and operating characteristics of the current thermal power plant unit can be determined by comparing the similarities between the operating characteristic information of multiple units of other thermal power plants with the same type as the current thermal power plant unit, so as to obtain the current thermal power plant unit. basic operating characteristics information. Optionally, determine the independent operation characteristic information of the current thermal power plant unit based on the operation data of each power equipment in the current thermal power plant unit, and determine the current thermal power plant unit's basic operation characteristic information and independent operation characteristic information by combining it. Operating characteristic information of each power equipment in the power plant unit.

Among them, the operation data used to determine the independent operation characteristic information of the current thermal power plant unit includes the infrastructure period operation data and the operation period operation data of each power equipment in the unit to ensure the integrity of the operation data.

On the basis of the above embodiments, as an implementable manner, in one embodiment, the model building module is specifically used for any power equipment, according to one of the different operating indicators represented by the operating characteristic information of the power equipment. Based on the interactive relationship between them, an initial fault early warning model corresponding to the power equipment is constructed; using the model data required for the power equipment fault early warning model, the initial fault early warning model is trained to obtain the fault early warning model of the power equipment.

Among them, the fault warning model can be constructed based on k-nearest neighbor algorithm, naive Bayes algorithm, support vector machine, decision tree, k-means and various neural networks, etc. It can also be based on generative model algorithm, transfer learning model algorithm, joint Training model algorithms, semi-supervised support vector machines, algorithms based on graph theory, sequence structure algorithms and various neural networks are constructed. The specific construction method can be selected according to the actual situation, and is not limited by the embodiments of this application.

Specifically, after the initial fault warning model is trained, the test sample can be used to test it. If the test result indicates that the accuracy is greater than 95%, it is determined that the model training is completed, and the fault warning model of the power equipment is obtained. , otherwise, continue training.

Optionally, in one embodiment, the system also includes an optimization module for obtaining abnormal data generated during the application process of the fault warning model, and updating the data management module according to the application blind spots of the fault warning model represented by the abnormal data. operating data and operating characteristic information; optimize the fault warning model based on the update of operating data and operating characteristic information in the data management module.

It should be noted that each power equipment in the current thermal power plant units will undergo certain changes during operation. For example, after a certain power equipment undergoes manual maintenance, the interaction between different operating indicators changes, or new problems arise. The operating indicators of the current application lead to deviations or application blind spots in the fault warning model.

Specifically, based on the optimization module, the above-mentioned model building module and the data management module can interact. The data management module can serve as a judge of the model building module and comprehensively guide the model building process of the model building module to obtain corresponding fault warnings. Model. After the fault warning model is put into use, it can react on the data management module according to its specific application conditions.

Specifically, the optimization module can send the operating indicators obtained by the fault early warning model to the data management module according to the application blind spots of the fault early warning model represented by the abnormal data generated during the application process of the fault early warning model, where the operating indicators include new Operational indicators. The data management module updates the operating data and operating characteristic information based on the currently received operating indicators, re-determines the operating characteristic information of the power equipment, and further optimizes the fault warning model accordingly.

The thermal power plant fault early warning system provided by the embodiment of this application includes: a data acquisition module, a data management module and a model construction module; the data acquisition module is used to obtain the operating data of each power equipment in the current thermal power plant unit, and write the operating data Enter the data management module; the data management module is used to analyze the received operating data to filter the model data required to build different power equipment fault warning models in the operating data, and to determine the operating characteristic information of each power equipment, and convert the model data and the operating characteristic information of each power equipment are sent to the model building module; the model building module is used to construct a fault early warning model corresponding to each power equipment based on the model data and the operating characteristic information of each power equipment, so as to predict the current fire based on each fault early warning model. Power plants provide early warning of faults. The system provided by the above solution builds a fault warning model for each power equipment in the current thermal power plant unit by combining the operating characteristic information of each power equipment, and uses the fault warning model to discover faults in the power equipment in advance before the DCS system alarms. Timely troubleshooting ensures the stability of unit operation, reduces the spread of abnormal working conditions of power equipment, maintains safe, economical and stable operation that affects the unit, avoids irreversible damage to power equipment, and avoids abnormal shutdown of the unit.

Embodiments of the present application provide a thermal power plant fault early warning method, which is used to perform fault early warning for power equipment in the thermal power plant units. The execution subjects of the embodiments of this application are electronic devices, such as servers, desktop computers, notebook computers, tablet computers, and other electronic devices that can serve as a thermal power plant host computer to provide fault early warning for the power equipment in the thermal power plant unit.

Figure 2 is a schematic flow chart of the thermal power plant fault early warning method provided by the embodiment of the present application. As shown in the figure, the method includes:

Step 201: Obtain the operating data of each power equipment in the current thermal power plant unit;

Step 202: Analyze the operating data to screen the model data required to build different power equipment fault warning models in the operating data, and determine the operating characteristic information of each power equipment;

Step 203: Based on the model data and the operating characteristic information of each power equipment, a fault early warning model corresponding to each power equipment is constructed to provide a fault early warning for the current thermal power plant based on each fault early warning model.

Regarding the thermal power plant fault early warning method in this embodiment, the specific implementation of each step has been described in detail in the embodiment of the system, and will not be described in detail here.

The thermal power plant fault early warning method provided by the embodiment of the present application is an application method of the thermal power plant fault early warning system provided by the above embodiment. Its implementation method and principle are the same and will not be described again.

The embodiment of the present application provides an electronic device for executing the thermal power plant fault early warning method provided in the above embodiment.

FIG. 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As shown in the figure, the electronic device 30 includes: at least one processor 31 and a memory 32 .

The memory stores computer execution instructions; at least one processor executes the computer execution instructions stored in the memory, so that at least one processor executes the thermal power plant fault early warning method provided in the above embodiment.

An electronic device provided in an embodiment of the present application is used to execute the thermal power plant fault early warning method provided in the above embodiment. The implementation method and principle thereof can be found in the above embodiment, and will not be described again here.

Embodiments of the present application provide a computer-readable storage medium. Computer-executable instructions are stored in the computer-readable storage medium. When the processor executes the computer-executable instructions, the thermal power plant fault early warning provided by any of the above embodiments is realized. method.

The storage medium containing computer-executable instructions in the embodiments of the present application can be used to store the computer-executable instructions for the thermal power plant fault early warning method provided in the previous embodiments. The implementation method and principle thereof can be referred to the above-mentioned embodiments and will not be discussed here. Repeat.

In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components. can be combined or can be integrated into another system, or some features can be ignored, or not implemented. Another point is that the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces; the indirect coupling or communication connection of the system or unit can be electrical, mechanical or other forms of connection.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute the methods described in various embodiments of this application. Some steps. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code. .

Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In practical applications, the above-mentioned function allocation can also be completed by different functional modules as needed, that is, the internal structure of the system is divided into different functional modules to complete all or part of the functions of the above-described embodiments. For the specific working process of the system in the above-described embodiment, reference can be made to the corresponding process in the foregoing method embodiment, which will not be described again here.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or to equivalently replace some or all of the technical features; and these modifications or substitutions do not deviate from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present application. range.

Claims (10)

1. A thermal power plant fault early warning system, characterized by including: a data acquisition module, a data management module and a model construction module;

   The data collection module is used to obtain the operating data of each power equipment in the current thermal power plant unit, and write the operating data into the data management module;

   The data management module is used to analyze the received operating data, to screen the model data required to construct different power equipment fault warning models in the operating data, and to determine the operating characteristic information of each of the power equipment, Send the model data and operating characteristic information of each power equipment to the model building module;

   The model building module is used to construct a fault warning model corresponding to each of the power equipment according to the model data and the operating characteristic information of each of the power equipment, so as to conduct a warning on the current thermal power plant based on each of the fault warning models. Failure warning.
2. The system according to claim 1, characterized in that the data collection module is specifically used for:

   Obtain the measurement data of each electric equipment from the measuring instrument of each electric equipment in the current thermal power plant unit;

   Obtain the monitoring data of each of the power equipment from the DCS system of the current thermal power plant;

   The measurement data and monitoring data are summarized to obtain the operation data of each power equipment.
3. The system according to claim 1, characterized in that the data management module is specifically used for:

   Perform working condition analysis on the received operating data to distinguish the operating data of each of the power equipment under different working conditions;

   For any of the power equipment, the operating data under the target operating conditions are determined as the model data required to build the power equipment fault early warning model.
4. The system according to claim 1, characterized in that the data management module is specifically used for:

   Compare the similarities between the operating characteristic information of multiple units of the same type as the current thermal power plant unit to obtain the basic operating characteristic information of the current thermal power plant unit;

   According to the operation data of each electric equipment in the current thermal power plant unit and the basic operation characteristic information, determine the operation characteristic information of each electric equipment;

   Wherein, the operation data includes the operation data during the infrastructure construction period and the operation data during the operation period of the electric power equipment.
5. The system according to claim 1, characterized in that the model building module is specifically used for:

   For any of the power equipment, construct an initial fault warning model corresponding to the power equipment based on the interaction between different operating indicators represented by the operating characteristic information of the power equipment;

   Using the model data required by the power equipment fault warning model, the initial fault warning model is trained to obtain a fault warning model of the power equipment.
6. The system of claim 1, further comprising:

   An optimization module, used to obtain abnormal data generated during the application process of the fault warning model, and update the operating data and operating characteristic information in the data management module according to the application blind spots of the fault warning model represented by the abnormal data; The fault warning model is optimized according to the update status of the operating data and operating characteristic information in the data management module.
7. The system according to claim 1, characterized in that the fault warning model at least includes a reverse osmosis membrane fouling model specialized in chemical water, a steam-driven feed water pump insufficient output model specialized in steam turbines, and a flue resistance abnormality model specialized in boilers. and unit indicator anomaly early warning model.
8. A thermal power plant fault early warning method, which is characterized by including:

   Obtain the operating data of each electrical equipment in the current thermal power plant unit;

   Analyze the operating data to screen the model data required to construct different power equipment fault warning models in the operating data, and determine the operating characteristic information of each of the power equipment;

   According to the model data and the operating characteristic information of each of the power equipment, a fault early warning model corresponding to each of the power equipment is constructed, so as to perform a fault early warning on the current thermal power plant based on each of the fault early warning models.
9. An electronic device, characterized by including: at least one processor and memory;

   The memory stores computer execution instructions;

   The at least one processor executes computer-executable instructions stored in the memory, causing the at least one processor to perform the method of claim 8.
10. A computer-readable storage medium, characterized in that computer-executable instructions are stored in the computer-readable storage medium. When the processor executes the computer-executable instructions, the method as claimed in claim 8 is implemented.

Images