CN115700324A - Tile temperature early warning method and device and electronic equipment - Google Patents
Tile temperature early warning method and device and electronic equipment Download PDFInfo
- Publication number
- CN115700324A CN115700324A CN202211267996.3A CN202211267996A CN115700324A CN 115700324 A CN115700324 A CN 115700324A CN 202211267996 A CN202211267996 A CN 202211267996A CN 115700324 A CN115700324 A CN 115700324A
- Authority
- CN
- China
- Prior art keywords
- temperature
- early warning
- tile
- threshold value
- data
- 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
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The embodiment of the invention discloses a method and a device for early warning of tile temperature and electronic equipment. According to the embodiment of the invention, influence factor data is obtained, wherein the influence factor data is data corresponding to each factor influencing the temperature of the tile shaft; inputting the influence factor data into a pre-trained deep learning neural network model, and outputting a watt-temperature predicted value; and early warning is carried out according to at least one group of the tile temperature predicted values. By the method, the early warning of the tile temperature can be effectively carried out, and the normal operation of the hydroelectric equipment is ensured.
Description
Technical Field
The invention relates to the technical field of hydroelectric power generation, in particular to a method and a device for early warning of tile temperature and electronic equipment.
Background
Hydroelectric power is a clean energy source, is renewable, pollution-free, low in operating cost and flexible in operation and scheduling, so that the hydroelectric power becomes an important component of an energy structure in China.
In the prior art, an online monitoring device is arranged in a hydropower station and used for monitoring the actual temperature of a bearing bush, and when the temperature of the bearing bush reaches a preset threshold value, early warning can be performed, but the method in the prior art only performs early warning on the temperature singly, for example, the temperature of the surface of the bearing bush is measured by using a temperature sensor, so that the comprehensive fault analysis and diagnosis are difficult to perform effectively, and when the actual temperature of the bearing bush reaches the preset threshold value, a worker can be late to remove risks after receiving the early warning, or a bearing burning accident can occur.
In conclusion, how to effectively give an early warning to the temperature of the tile and ensure the normal operation of hydroelectric equipment is a problem to be solved at present.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for early warning a wattage temperature, and an electronic device, which can effectively early warn the wattage temperature and ensure normal operation of a hydroelectric device.
In a first aspect, an embodiment of the present invention provides a tile temperature early warning method, where the method includes: acquiring influence factor data, wherein the influence factor data are data corresponding to all factors influencing the temperature of the tile shaft; inputting the influence factor data into a pre-trained deep learning neural network model, and outputting a tile temperature predicted value; and early warning is carried out according to at least one group of the tile temperature predicted values.
Optionally, the performing early warning according to the at least one group of the tile temperature predicted value specifically includes:
and responding to the fact that the tile temperature predicted value is larger than or equal to a first threshold value, and then carrying out height early warning.
Optionally, the performing early warning according to the at least one group of the tile temperature predicted value specifically includes:
in response to the tile temperature predicted value being less than a first threshold value and greater than or equal to a second threshold value, determining at least one subsequent set of the tile temperature predicted values;
and responding to at least one subsequent group of the watt-temperature predicted values which are smaller than the first threshold value and larger than or equal to the second threshold value, and then carrying out moderate early warning.
Optionally, the performing early warning according to the at least one group of the tile temperature predicted value specifically includes:
in response to the wattage predicted value being less than a second threshold value and greater than or equal to a third threshold value, determining at least one subsequent set of the wattage predicted values;
and responding to the fact that the follow-up at least one group of the watt-temperature predicted values are smaller than a second threshold value and larger than or equal to a third threshold value, and then carrying out light early warning.
Optionally, the deep learning neural network model is a long-term memory network model.
Optionally, each factor affecting the temperature of the bearing bush shaft is at least one or more of the yaw of the lower guide bearing X, the active measurement value, the electromagnetic flow of the thrust lower guide water, and the temperature of the thrust bearing oil groove.
Optionally, the training process of the deep learning neural network model includes:
acquiring historical data, wherein the historical data comprises historical data of various factors influencing the temperature of the tile shaft and historical tile temperature data;
and training the deep learning neural network model according to the historical data.
In a second aspect, an embodiment of the present invention provides a tile temperature warning device, where the tile temperature warning device includes:
the system comprises an acquisition unit, a calculation unit and a control unit, wherein the acquisition unit is used for acquiring influence factor data, and the influence factor data are data corresponding to factors influencing the temperature of a tile shaft;
the processing unit is used for inputting the influence factor data into a pre-trained deep learning neural network model and outputting a watt-temperature predicted value;
and the early warning unit is used for early warning according to at least one group of the tile temperature predicted values.
Optionally, the early warning unit is specifically configured to:
and responding to the fact that the tile temperature predicted value is larger than or equal to a first threshold value, and then carrying out height early warning.
Optionally, the early warning unit is specifically configured to:
in response to the tile temperature predicted value being less than a first threshold value and greater than or equal to a second threshold value, determining at least one subsequent set of the tile temperature predicted values;
and responding to at least one subsequent group of the watt-temperature predicted values which are smaller than the first threshold value and larger than or equal to the second threshold value, and then carrying out moderate early warning.
Optionally, the early warning unit is specifically configured to:
in response to the tile temperature predicted value being less than a second threshold value and greater than or equal to a third threshold value, determining at least one subsequent set of the tile temperature predicted values;
and responding to the fact that the follow-up at least one group of the watt-temperature predicted value is smaller than a second threshold value and larger than or equal to a third threshold value, and performing light early warning.
Optionally, the deep learning neural network model is a long-term and short-term memory network model.
Optionally, each factor influencing the tile shaft temperature is at least one or more of an X-direction throw of the lower guide bearing, an active measurement value, an electromagnetic flow of thrust lower guide water, and a temperature of an oil groove of the thrust bearing.
Optionally, the training process of the deep learning neural network model includes:
acquiring historical data, wherein the historical data comprises historical data of factors influencing the temperature of the tile shaft and historical tile temperature data;
and training the deep learning neural network model according to the historical data.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium on which computer program instructions are stored, which when executed by a processor implement the method according to the first aspect or any one of the possibilities of the first aspect.
In a fourth aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory being configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to the first aspect or any one of the possibilities of the first aspect.
According to the embodiment of the invention, influence factor data is obtained, wherein the influence factor data is data corresponding to each factor influencing the temperature of a tile shaft; inputting the influence factor data into a pre-trained deep learning neural network model, and outputting a watt-temperature predicted value; and early warning is carried out according to at least one group of the tile temperature predicted values. By the method, early warning can be effectively carried out on the temperature of the tile, and normal operation of hydroelectric equipment is guaranteed.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of a method for early warning of a wattage temperature according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method of early warning of wattage temperature in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a training process of a deep learning neural network model according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a long-term and short-term memory network structure according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a wattage temperature warning device according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an electronic device of an embodiment of the invention.
Detailed Description
The present disclosure is described below based on examples, but the present disclosure is not limited to only these examples. In the following detailed description of the present disclosure, certain specific details are set forth. It will be apparent to those skilled in the art that the present disclosure may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the present disclosure.
Furthermore, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.
Unless the context clearly requires otherwise, throughout this specification, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
In the description of the present disclosure, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present disclosure, "a plurality" means two or more unless otherwise specified.
In the prior art, an online monitoring device is arranged in a hydropower station and used for monitoring the actual temperature of a bearing bush, and when the temperature of the bearing bush reaches a preset threshold value, early warning can be performed, but the method in the prior art only performs early warning on the temperature singly, for example, the temperature of the surface of the bearing bush is measured by using a temperature sensor, so that omnibearing fault analysis and diagnosis are difficult to perform effectively, and when the actual temperature of the bearing bush reaches the preset threshold value, a worker can be late in eliminating risks after receiving early warning, or a bearing burning accident can occur. Therefore, how to effectively carry out early warning on the temperature of the tile and ensure the normal operation of hydroelectric equipment is a problem to be solved at present.
In the embodiment of the present invention, fig. 1 is a flowchart of a method for early warning a wattage temperature in the embodiment of the present invention. As shown in fig. 1, the method specifically comprises the following steps:
s100, obtaining influence factor data, wherein the influence factor data are data corresponding to all factors influencing the temperature of the tile shaft.
Specifically, each factor influencing the temperature of the bearing bush shaft is at least one or more of the lower guide bearing X-direction throw, the active measurement value, the thrust lower guide water electromagnetic flow and the thrust bearing oil groove temperature.
In a possible implementation manner, the factor affecting the temperature of the tile shaft may also be other factors, and the present invention is only an exemplary one and is not limited thereto.
And S101, inputting the influence factor data into a pre-trained deep learning neural network model, and outputting a watt-temperature predicted value.
Specifically, the deep learning neural network model is a Long Short Term Memory (LSTM) model.
And S102, early warning is carried out according to at least one group of the watt-temperature predicted values.
Specifically, the early warning is performed according to at least one group of the tile temperature prediction values, specifically including multiple conditions, which are as follows:
and in case one, responding to the fact that the tile temperature predicted value is larger than or equal to a first threshold value, carrying out height early warning.
For example, assuming that the early warning degrees are classified into a high early warning, a medium early warning and a light early warning, each early warning degree corresponds to a set temperature range, if the first threshold is 60 degrees, when the tile temperature predicted value is 63 degrees and is greater than the first threshold, the high early warning is performed, and the high early warning may prompt the user in a manner of sound or color, for example, when the high early warning occurs, red color is displayed on a display screen of the monitoring device to prompt the user.
In case two, in response to the tile temperature predicted value being less than a first threshold value and greater than or equal to a second threshold value, determining at least one subsequent set of the tile temperature predicted values; and responding to at least one subsequent group of the watt-temperature predicted values which are smaller than the first threshold value and larger than or equal to the second threshold value, and then carrying out moderate early warning.
For example, assuming that the second threshold is 50 degrees, when the predicted wattage temperature value is 53 degrees, the predicted wattage temperature value is greater than the second threshold and smaller than the first threshold; and continuously predicting a next tile temperature predicted value, wherein an actual interval between the next tile temperature predicted value and the current tile temperature predicted value is 5 minutes, the time interval is also a time interval for acquiring influence factor data, and can also be called as a step length, wherein the 5 minutes is exemplary, and is specifically adjusted according to actual conditions, the next tile temperature predicted value is acquired to be 54 degrees, is also greater than the second threshold and is smaller than the first threshold, then a moderate early warning is performed, and the high early warning can prompt a user in a sound or color manner, for example, when the moderate early warning occurs, an orange prompt user is displayed on a display screen of the monitoring equipment.
In a possible implementation manner, the moderate early warning may be performed only after the tile temperature predicted value is continuously determined to be less than the first threshold and greater than or equal to the second threshold three times, or may be performed multiple times, which is not limited in the embodiment of the present invention.
In the embodiment of the invention, the sampling time interval of the actual temperature data of the bearing bush is regarded as a step length in consideration of the fact that the early warning mechanism under various time scales such as ultra-short time, long time and the like can be established on the site of the actual unit.
In case III, in response to the fact that the wattage temperature predicted value is smaller than a second threshold value and larger than or equal to a third threshold value, determining at least one subsequent group of wattage temperature predicted values; and responding to the fact that the follow-up at least one group of the watt-temperature predicted values are smaller than a second threshold value and larger than or equal to a third threshold value, and then carrying out light early warning.
For example, if the third threshold is 40 degrees, when the wattage temperature predicted value is 42 degrees, the third threshold is greater than the wattage temperature predicted value, and the third threshold is less than the second threshold; and continuously predicting a next tile temperature predicted value, wherein an actual interval between the next tile temperature predicted value and the current tile temperature predicted value is 5 minutes, the time interval is also a time interval for acquiring influence factor data and can also be called a step length, the 5 minutes are exemplary, the next tile temperature predicted value is adjusted according to actual conditions, the obtained next tile temperature predicted value is 42 degrees, is also greater than the third threshold value and is smaller than the second threshold value, then a light early warning is performed, and the light early warning can prompt a user in a sound or color mode, for example, when the light early warning occurs, yellow is displayed on a display screen of the monitoring equipment to prompt the user.
In a possible implementation manner, the mild warning may be performed only after the tile temperature predicted value is continuously determined five times to be smaller than the second threshold and greater than or equal to the third threshold, or may be performed multiple times, which is not limited in the embodiment of the present invention.
Fourthly, when the predicted temperature is increased from the mild early warning to the moderate early warning, the temperature is in an increasing trend, and subsequent judgment is carried out according to a moderate early warning rule; or when the predicted temperature is reduced from the moderate early warning to the mild early warning, the temperature is in a descending trend, and subsequent judgment is carried out according to mild early warning rules.
In the embodiment of the invention, the watt-temperature value is effectively predicted, the system can send out real-time alarm according to the preset early warning strategy, and the field monitoring and on-duty personnel can find problems in time and process the problems as early as possible, so that the running safety of the hydroelectric generating set is ensured, and the predictability and the recognition capability of the running personnel on equipment defects are improved.
In a possible implementation manner, after step S101, the method further includes the following steps, specifically as shown in fig. 2, where fig. 2 is a flow chart of a method for early warning a wattage temperature according to an embodiment of the present invention, and specifically includes the following steps:
and step S103, storing the predicted value of the watt-temperature.
In a possible implementation manner, the watt-temperature predicted value is stored in a time sequence database in real time, a corresponding curve chart can be provided, a user can conveniently observe the difference between an actual sampling value and a predicted value of the temperature of relevant equipment in real time, the user can conveniently predict the change trend of the long-term running state of the unit, when a fault occurs, the real-time data module stores output continuous data information including a period of time before and after the fault occurs to the event data module for subsequent analysis of the fault event, and meanwhile, the fault data module also stores an analysis result of the fault diagnosis analysis system for the event for subsequent query and event review.
In the embodiment of the present invention, a training process of the deep learning neural network model is shown in fig. 3, and specifically includes the following steps:
step S300, obtaining historical data, wherein the historical data comprises historical data of factors influencing the temperature of the tile shaft so as to obtain historical tile temperature data.
Specifically, after the historical data is acquired, a data set is constructed according to a time sequence, then the data set is divided into a training set and a test set, the training set is used for training a deep learning neural network model, the test set is used for testing the performance of the deep learning neural network model, the division ratio of the training set and the test set is set according to preset parameters, the size of the parameters can be 0-1, for example, the division ratio of the selected training set is 0.7, namely 70% of the historical operation data volume is divided into the training set, and the other 30% of the historical operation data volume is divided into the test set; and preprocessing the historical data, wherein the preprocessing can be data cleaning, and after the data cleaning, normalization processing is further performed on the data in order to convert the data into effective data which can be processed by a deep learning neural network.
In the embodiment of the invention, a MinMaxScaler method is selected to carry out normalization processing on data, and the specific mathematical expression is as follows:
wherein, x is max Representing the maximum value, x, in the input data min Representing the minimum value in the input data, X is the normalized result and ranges between 0 and 1.
And S301, training the deep learning neural network model according to the historical data.
Specifically, the deep learning neural network model is a long-term memory network model, the structure of which is shown in fig. 4, and the LSTM removes or adds information to the state of the cell through a well-designed structure called a "gate". The gate is a method for determining whether information passes through, and comprises a Sigmoid neural network layer and a bit-wise multiplication operation. The mathematical formula of the Sigmoid function is as follows:
wherein x represents input, the output value y of the Sigmoid function is a value between 0 and 1, 0 represents "no quantity is allowed to pass through", and 1 means "any quantity is allowed to pass through". The LSTM has three gates, an input gate, a forgetting gate, and an output gate, for protecting and controlling cell states.
The forgetting gate can read the output value h of the last moment of the cell t-1 And the input value x at the current time t Outputting a value f between 0 and 1 t To cell state C t-1 。
f t ＝σ(W f [h t-1 ，x t ]+b f )
H is t-1 Is the output at time t-1, said x t For input at time t, W f Is the weight of the forgotten gate, b f The sigma is a Sigmoid activation function, and the forgetting gate is mainly used for memorizing useful information in the previous unit and discarding the useless information.
The input gate is used for updating cell information, and mainly selectively records the input information in the memory unit and transmits the input information to the next stage, and the calculation formula of the input gate is as follows:
I t ＝σ(W i [h t-1 ，x t ]+b i )
wherein, W i Is a weight matrix of the input gate, b i Is the offset vector of the input gate.
The calculation formula of the current input unit state is as follows:
wherein, the
Value of input cell state at time t, W c Is a weight matrix of the input cell, said b c Is the offset vector of the input unit;
the calculation formula of the unit state at the current moment is as follows:
c t ＝f t *c t-1 +i*c t
where denotes the multiplication of elements.
The calculation formula of the output gate is as follows:
o t ＝σ(W o [h t-1 ，x t ]+b o )
where W is the weight matrix of the output gates, b o Is the offset vector of the output gate.
Finally, the final output of the LSTM is calculated as follows:
h t ＝o t *tanh(c t )
wherein, the output result is determined by the output gate and the unit state, and finally the structure is transmitted to the next stage.
In a possible implementation, a loss function and a regularization term are also considered when training the long-term and short-term memory network model, where the loss function is generally selected as a mean square error loss:
or selecting a cross entropy loss function:
wherein said Θ represents a set of parameters of said LSTM, said
Is the desired output value of the network.
The regularization term is used for preventing overfitting of the neural network, and specifically comprises the following steps:
L(Θ)＝J(Θ)+λ(‖W f ‖ 2 +‖W i ‖ 2 +‖W c ‖ 2 +‖W o ‖ 2 )
wherein λ is a regularization parameter, W f The above W i The above W c And said W o Respectively a forgetting gate weight, an input unit state weight and an output gate weight.
In the embodiment of the invention, the bearing bush temperature can be predicted in advance through the bearing bush temperature predicted value, a user can preprocess the occurring conditions in advance according to the bearing bush temperature predicted value, and the bearing bush temperature predicted value can effectively assist the manual omnibearing fault analysis and diagnosis, carry out the fault diagnosis on the faults of the hydroelectric generating set and effectively avoid the conventional risks so as to ensure the safe and stable operation of the hydroelectric generating plant because the long-time memory network model for predicting the bearing bush temperature predicted value relates to several important factors influencing the bearing bush temperature.
Fig. 5 is a schematic diagram of a wattage temperature warning device according to an embodiment of the present invention. As shown in fig. 5, the apparatus of the present embodiment includes an acquisition unit 501, a processing unit 502, and an early warning unit 503.
The acquiring unit 501 is configured to acquire influence factor data, where the influence factor data is data corresponding to each factor that influences the temperature of the tile axle; the processing unit 502 is configured to input the data of the impact factors into a pre-trained deep learning neural network model, and output a predicted value of the wattage temperature; the early warning unit 503 is configured to perform early warning according to at least one group of the wattage temperature predicted values.
Further, the early warning unit is specifically configured to:
and responding to the fact that the tile temperature predicted value is larger than or equal to a first threshold value, and then carrying out height early warning.
Further, the early warning unit is specifically configured to:
in response to the tile temperature predicted value being less than a first threshold value and greater than or equal to a second threshold value, determining at least one subsequent set of the tile temperature predicted values;
and responding to at least one subsequent group of the watt-temperature predicted value smaller than a first threshold value and larger than or equal to a second threshold value, and performing moderate early warning.
Further, the early warning unit is specifically configured to:
in response to the tile temperature predicted value being less than a second threshold value and greater than or equal to a third threshold value, determining at least one subsequent set of the tile temperature predicted values;
and responding to the fact that the follow-up at least one group of the watt-temperature predicted values are smaller than a second threshold value and larger than or equal to a third threshold value, and then carrying out light early warning.
Further, the deep learning neural network model is a long-time and short-time memory network model.
Further, the factors influencing the temperature of the bearing bush are at least one or more of X-direction throw of the lower guide bearing, a measured value, electromagnetic flow of water guided under thrust, and oil groove temperature of the thrust bearing.
Further, the training process of the deep learning neural network model comprises the following steps:
acquiring historical data, wherein the historical data comprises historical data of factors influencing the temperature of the tile shaft and historical tile temperature data;
and training the deep learning neural network model according to the historical data.
Fig. 6 is a schematic diagram of an electronic device of an embodiment of the invention. As shown in fig. 6, the electronic device shown in fig. 6 is a device for early warning of wattage temperature, and includes a general-purpose computer hardware structure, which at least includes a processor 601 and a memory 602. The processor 601 and the memory 602 are connected by a bus 603. The memory 602 is adapted to store instructions or programs executable by the processor 601. Processor 601 may be a stand-alone microprocessor or a collection of one or more microprocessors. Thus, the processor 601 implements the processing of data and the control of other devices by executing instructions stored by the memory 602 to perform the method flows of embodiments of the present invention as described above. The bus 603 connects the above components together, as well as to the display controller 604 and the display device and input/output (I/O) device 605. Input/output (I/O) device 605 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, the input/output devices 605 are connected to the system through input/output (I/O) controllers 606.
Wherein the instructions stored by the memory 602 are executed by the at least one processor 601 to implement: .
Specifically, the electronic device includes: one or more processors 601 and memory 602, fig. 6 taking one processor 601 as an example. The processor 601 and the memory 602 may be connected by a bus or other means, and fig. 6 illustrates an example of a connection by a bus. The memory 602, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The processor 601 executes various functional applications and data processing of the device by running nonvolatile software programs, instructions and modules stored in the memory 602, that is, the method for early warning of the wattage temperature is implemented.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store a list of options, etc. Further, the memory 602 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 602 may optionally include memory located remotely from the processor 601, which may be connected to an external device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more modules are stored in the memory 602 and when executed by the one or more processors 601 perform the method of wattage warning in any of the method embodiments described above.
The product can execute the method provided by the embodiment of the application, has corresponding functional modules and beneficial effects of the execution method, and can refer to the method provided by the embodiment of the application without detailed technical details in the embodiment.
Embodiments of the present invention relate to a non-transitory storage medium storing a computer-readable program for causing a computer to perform some or all of the above-described method embodiments.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing related hardware, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific to implementations of the invention, and that various changes in form and detail may be made therein without departing from the spirit and scope of the invention in practice.
Claims (10)
1. A method for early warning of watt temperature is characterized by comprising the following steps:
acquiring influence factor data, wherein the influence factor data are data corresponding to each factor influencing the temperature of the tile shaft;
inputting the influence factor data into a pre-trained deep learning neural network model, and outputting a tile temperature predicted value;
and early warning is carried out according to at least one group of the tile temperature predicted value.
2. The method according to claim 1, wherein the performing early warning according to at least one of the sets of the predicted wattage temperature values specifically comprises:
and responding to the fact that the tile temperature predicted value is larger than or equal to a first threshold value, and then carrying out height early warning.
3. The method according to claim 1, wherein the early warning according to at least one of the sets of wattage temperature predicted values specifically comprises:
in response to the wattage predicted value being less than a first threshold value and greater than or equal to a second threshold value, determining at least one subsequent set of the wattage predicted values;
and responding to at least one subsequent group of the watt-temperature predicted values which are smaller than the first threshold value and larger than or equal to the second threshold value, and then carrying out moderate early warning.
4. The method according to claim 1, wherein the performing early warning according to at least one of the sets of the predicted wattage temperature values specifically comprises:
in response to the tile temperature predicted value being less than a second threshold value and greater than or equal to a third threshold value, determining at least one subsequent set of the tile temperature predicted values;
and responding to the fact that the follow-up at least one group of the watt-temperature predicted values are smaller than a second threshold value and larger than or equal to a third threshold value, and then carrying out light early warning.
5. The method of claim 1, in which the deep learning neural network model is an long-and-short memory network model.
6. The method of claim 1, wherein the factors affecting the temperature of the shoe shaft are at least one or more of lower guide bearing X-throw, active measurement, thrust lower guide inlet electromagnetic flow, thrust bearing sump temperature.
7. The method of claim 1, wherein the training process of the deep-learning neural network model comprises:
acquiring historical data, wherein the historical data comprises historical data of various factors influencing the temperature of the tile shaft and historical tile temperature data;
and training the deep learning neural network model according to the historical data.
8. The utility model provides a device of temperature of a watt early warning which characterized in that, the device includes:
the system comprises an acquisition unit, a calculation unit and a control unit, wherein the acquisition unit is used for acquiring influence factor data, and the influence factor data are data corresponding to factors influencing the temperature of a tile shaft;
the processing unit is used for inputting the influence factor data into a pre-trained deep learning neural network model and outputting a watt-temperature predicted value;
and the early warning unit is used for early warning according to at least one group of the tile temperature predicted value.
9. A computer-readable storage medium on which computer program instructions are stored, which, when executed by a processor, implement the method of any one of claims 1-7.
10. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211267996.3A CN115700324A (en) | 2022-10-17 | 2022-10-17 | Tile temperature early warning method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211267996.3A CN115700324A (en) | 2022-10-17 | 2022-10-17 | Tile temperature early warning method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115700324A true CN115700324A (en) | 2023-02-07 |
Family
ID=85121054
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211267996.3A Pending CN115700324A (en) | 2022-10-17 | 2022-10-17 | Tile temperature early warning method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115700324A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117249036A (en) * | 2023-11-20 | 2023-12-19 | 南方电网调峰调频发电有限公司检修试验分公司 | Pumped storage system, hydroelectric generating set state evaluation method and device |
| CN118128686A (en) * | 2024-05-07 | 2024-06-04 | 国网甘肃省电力公司 | Top cover pressure adjusting method and system for vertical hydroelectric generating set, electronic equipment and storage medium |
-
2022
- 2022-10-17 CN CN202211267996.3A patent/CN115700324A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117249036A (en) * | 2023-11-20 | 2023-12-19 | 南方电网调峰调频发电有限公司检修试验分公司 | Pumped storage system, hydroelectric generating set state evaluation method and device |
| CN117249036B (en) * | 2023-11-20 | 2024-02-20 | 南方电网调峰调频发电有限公司检修试验分公司 | Pumped storage system, hydroelectric generating set state evaluation method and device |
| CN118128686A (en) * | 2024-05-07 | 2024-06-04 | 国网甘肃省电力公司 | Top cover pressure adjusting method and system for vertical hydroelectric generating set, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Prediction of time series of NPP operating parameters using dynamic model based on BP neural network | |
| CN110135064B (en) | Method, system and controller for predicting temperature faults of rear bearing of generator | |
| CN112884008B (en) | Prediction evaluation method and device for running state of power information acquisition system | |
| Cross et al. | Model-based and fuzzy logic approaches to condition monitoring of operational wind turbines | |
| CN104063577B (en) | Method for forecasting characteristic gas development tendency in transformer oil based on generalized recurrent neural network | |
| CN111784061B (en) | Training method, device and equipment for power grid engineering cost prediction model | |
| Tian et al. | Spatial correlation and temporal attention-based LSTM for remaining useful life prediction of turbofan engine | |
| CN116306798A (en) | Ultra-short time wind speed prediction method and system | |
| CN113344288A (en) | Method and device for predicting water level of cascade hydropower station group and computer readable storage medium | |
| CN115700324A (en) | Tile temperature early warning method and device and electronic equipment | |
| Zhang et al. | A new adaptive Mamdani-type fuzzy modeling strategy for industrial gas turbines | |
| CN115879369A (en) | Coal mill fault early warning method based on optimized LightGBM algorithm | |
| CN113295399B (en) | Converter valve element state evaluation method, device, electronic equipment and storage medium | |
| CN103472866A (en) | Furnace temperature optimization system and method of pesticide waste liquid incinerator of intelligent fuzzy system | |
| Chen et al. | Multi-scale memory-enhanced method for predicting the remaining useful life of aircraft engines | |
| CN114239396A (en) | Fan gear box state prediction method and system | |
| CN113240217A (en) | Photovoltaic power generation prediction method and device based on integrated prediction model | |
| Back et al. | Prediction and uncertainty analysis of power peaking factor by cascaded fuzzy neural networks | |
| CN112580254A (en) | Multi-dimensional analysis and early warning method for converter transformer based on multi-level decision fusion | |
| Huang et al. | Elman neural network considering dynamic time delay estimation for short-term forecasting of offshore wind power | |
| CN116522594A (en) | Time self-adaptive transient stability prediction method and device based on convolutional neural network | |
| CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network | |
| CN114254904B (en) | Method and device for evaluating operation health degree of engine room of wind turbine generator | |
| CN113866375A (en) | Intelligent online monitoring method and system for effluent nitrogenous substances | |
| CN103472729B (en) | The pesticide waste liquid incinerator hazardous emission controls up to par system and method for gunz |
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 |