CN115912658A - Intelligent monitoring method and device for power plant, storage medium and electronic equipment - Google Patents
Intelligent monitoring method and device for power plant, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN115912658A CN115912658A CN202211658876.6A CN202211658876A CN115912658A CN 115912658 A CN115912658 A CN 115912658A CN 202211658876 A CN202211658876 A CN 202211658876A CN 115912658 A CN115912658 A CN 115912658A
- Authority
- CN
- China
- Prior art keywords
- real
- determining
- value
- abnormal
- time 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
Abstract
The disclosure relates to the field of power industry, in particular to an intelligent monitoring method and device for a power plant, a storage medium and electronic equipment. The method comprises the following steps: inputting the acquired real-time data of the monitoring points into a pre-trained real-time prediction model to acquire a predicted value corresponding to the real-time data; determining a first value range according to the estimated value; determining the state of the monitoring point according to the real-time data; and in response to the fact that the monitoring point is determined to have the abnormal phenomenon, determining an abnormal grade according to the real-time data, the first numerical range, the change rate of the real-time data in the preset time and the change rate threshold, and generating corresponding alarm information. Therefore, the determined first numerical range is adaptive to the actual operation state of the power plant equipment, the dependence on manual experience is reduced, and the accuracy of alarming is improved; meanwhile, the original monitoring picture does not need to be switched back and forth to monitor the disk, so that the burden of operators is greatly reduced, and the operation safety of the unit is effectively guaranteed.
Description
Technical Field
The disclosure relates to the field of power industry, in particular to an intelligent monitoring method and device for a power plant, a storage medium and electronic equipment.
Background
With the increasing capacity of the unit, more and more equipment parameters need to be monitored by the operating personnel. The parameters of the power plant are distributed in nearly 200 pictures of each monitoring system, information reading omission easily occurs during monitoring, and the set value of the alarm system is usually a fixed value and is difficult to adapt to the actual state of the power plant, so that the hidden danger of equipment is difficult to find in time. Therefore, the problems that alarm information is inaccurate, abnormal discovery is not timely and the like can be caused, and potential safety hazards are brought to the operation of the power plant unit.
Disclosure of Invention
The invention aims to provide a power plant intelligent monitoring method, a power plant intelligent monitoring device, a storage medium and electronic equipment, so as to improve the operation safety of a power plant unit.
In order to achieve the above object, a first aspect of the present disclosure provides a power plant intelligent monitoring method, including:
inputting the acquired real-time data of the monitoring points into a pre-trained real-time prediction model, and acquiring a predicted value corresponding to the real-time data;
determining a first value range according to the estimated value;
determining the state of the monitoring point according to the real-time data;
and in response to the fact that the monitoring point is determined to have an abnormal phenomenon, determining an abnormal grade according to the real-time data, the first numerical range, the change rate of the real-time data in a preset time length and a change rate threshold value, and generating corresponding alarm information.
Optionally, the method further comprises:
inputting historical data of each monitoring point in a database into a pre-trained knowledge graph to obtain an incidence matrix, wherein the incidence matrix represents incidence relation among the historical data of each monitoring point;
and training according to the incidence matrix to obtain the real-time prediction model.
Optionally, the determining the state of the monitoring point according to the real-time data includes:
and if the real-time data exceeds the first numerical range and/or the change rate of the real-time data in a preset time length is greater than a change rate threshold value, determining that the monitoring point has an abnormal phenomenon.
Optionally, the determining, according to the real-time data, the first numerical range, and a change rate threshold of the real-time data within a preset time, an abnormal level and generating corresponding alarm information includes:
determining a first abnormal state according to the value of the real-time data exceeding the first numerical range;
determining a second abnormal state according to the value that the change rate of the real-time data in a preset time length exceeds a change rate threshold value;
and determining an output abnormal grade according to the first abnormal state and the second abnormal state, and generating corresponding alarm information.
Optionally, the determining a first abnormal state according to the value of the real-time data exceeding the first value range includes:
if the value of the real-time data exceeding the first value range is smaller than a first preset value, determining that the abnormal reference level of the first abnormal state is abnormal-free;
if the value of the real-time data exceeding the first value range is greater than or equal to the first preset value and smaller than a second preset value, determining that the abnormal reference level of the first abnormal state is a general abnormality;
and if the value of the real-time data exceeding the first value range is larger than or equal to the second preset value, determining that the abnormal reference level of the first abnormal state is serious abnormality.
Optionally, the determining a second abnormal state according to a value that a change rate of the real-time data within a preset time exceeds a change rate threshold includes:
if the value of the change rate of the real-time data in the preset time length exceeding the change rate threshold is smaller than a third preset value, determining that the abnormal reference level of the second abnormal state is abnormal-free;
if the value of the change rate of the real-time data in the preset time length, which exceeds the change rate threshold value, is greater than or equal to the third preset value and is less than a fourth preset value, determining that the abnormal reference level of the second abnormal state is a general abnormality;
and if the value of the change rate of the real-time data in the preset time length exceeding the change rate threshold is greater than or equal to the fourth preset value, determining that the abnormal reference level of the second abnormal state is serious abnormality.
Optionally, the determining, according to the first abnormal state and the second abnormal state, an output abnormal level and generating corresponding alarm information includes:
and determining an output abnormal grade according to the weight and the abnormal reference grade corresponding to the first abnormal state and the second abnormal state respectively, and generating corresponding alarm information.
Optionally, the method further comprises:
and generating alarm information representing abnormal switch states in response to the fact that the current switch states of the monitoring points are different from the preset switch states.
The second aspect of the disclosure provides an intelligent prison dish device of power plant, includes:
the acquisition module is used for inputting the acquired real-time data of the monitoring points into a pre-trained real-time prediction model to acquire a predicted value corresponding to the real-time data;
a first determining module, configured to determine a first value range according to the estimated value;
the second determining module is used for determining the state of the monitoring point according to the real-time data;
and the third determining module is used for responding to the determination that the monitoring point has an abnormal phenomenon, determining an abnormal grade according to the real-time data, the first numerical range, the change rate of the real-time data in a preset time length and a change rate threshold value, and generating corresponding alarm information.
Optionally, the apparatus further comprises:
a fourth determining module, configured to input historical data of each monitoring point in the database into a pre-trained knowledge graph to obtain an incidence matrix, where the incidence matrix represents an incidence relation between the historical data of each monitoring point;
and the training module is used for obtaining the real-time prediction model according to the incidence matrix training.
Optionally, the second determining module is configured to determine the status of the monitoring point by:
and if the real-time data exceeds the first numerical range and/or the change rate of the real-time data in a preset time length is greater than a change rate threshold value, determining that the monitoring point has an abnormal phenomenon.
Optionally, the third determining module includes:
the first determining submodule is used for determining a first abnormal state according to the value of the real-time data exceeding the first value range;
the second determining submodule is used for determining a second abnormal state according to the value that the change rate of the real-time data in the preset time length exceeds the change rate threshold;
and the third determining submodule is used for determining the output abnormal grade according to the first abnormal state and the second abnormal state and generating corresponding alarm information.
Optionally, the first determining sub-module includes:
a fourth determining submodule, configured to determine that the abnormal reference level of the first abnormal state is abnormal if the real-time data exceeds the first numerical range and is smaller than a first preset value;
a fifth determining sub-module, configured to determine that the abnormal reference level of the first abnormal state is a general abnormality if the real-time data exceeds the first value range by a value greater than or equal to the first preset value and smaller than a second preset value;
and the sixth determining submodule is used for determining that the abnormal reference level of the first abnormal state is serious abnormality if the value of the real-time data exceeding the first value range is greater than or equal to the second preset value.
Optionally, the second determining sub-module includes:
a seventh determining submodule, configured to determine that the abnormal reference level of the second abnormal state is abnormal if a value of a change rate of the real-time data within a preset duration, which exceeds the change rate threshold, is smaller than a third preset value;
an eighth determining sub-module, configured to determine that the abnormal reference level of the second abnormal state is a general abnormality if a value of a change rate of the real-time data within a preset time period, which exceeds the change rate threshold, is greater than or equal to the third preset value and is smaller than a fourth preset value;
and the ninth determining submodule is used for determining that the abnormal reference level of the second abnormal state is serious abnormality if the change rate of the real-time data in the preset time length exceeds the change rate threshold value and is greater than or equal to the fourth preset value.
Optionally, the third determining submodule is configured to determine an output abnormality level and generate corresponding alarm information by:
and determining an output abnormal grade according to the weight and the abnormal reference grade corresponding to the first abnormal state and the second abnormal state respectively, and generating corresponding alarm information.
Optionally, the apparatus further comprises:
and the fifth determining module is used for generating alarm information representing abnormal switch states in response to the fact that the current switch state of the monitoring point is different from the preset switch state.
A third aspect of the present disclosure provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method provided by the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an electronic device, comprising:
a memory having a computer program stored thereon;
a controller, which when executed by the controller, implements the steps of the method provided by the first aspect of the disclosure.
In the technical scheme, the estimated value obtained by the real-time prediction model can enable the first numerical range to be adaptive to the actual running state of the power plant equipment, reduces the dependence on manual experience, and improves the accuracy of alarming. Meanwhile, the monitoring disc can be switched back and forth without the original monitoring picture, the actual full-time and full-parameter point non-blind area monitoring is achieved, the situation that abnormal events are not found due to careless monitoring of operators is avoided, the burden of the operators is greatly reduced, the operation safety of the unit is effectively guaranteed, and the artificial intelligence application of a power plant is realized.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure. In the drawings:
FIG. 1 is a flowchart of a power plant intelligent supervision method according to an exemplary embodiment of the present disclosure.
Fig. 2 is a block diagram of an intelligent monitoring device of a power plant according to an exemplary embodiment of the present disclosure.
Fig. 3 is a block diagram of an electronic device provided by an exemplary embodiment of the present disclosure.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
It should be noted that all actions of acquiring signals, information or data in the present disclosure are performed under the premise of complying with the corresponding data protection regulation policy of the country of the location and obtaining the authorization given by the owner of the corresponding device.
FIG. 1 is a flowchart of a method for monitoring a power plant according to an exemplary embodiment of the present disclosure. As shown in fig. 1, the method may include S101 to S104.
S101, inputting the acquired real-time data of the monitoring points into a pre-trained real-time prediction model, and acquiring a predicted value corresponding to the real-time data.
For example, the estimated value corresponding to the real-time data may be determined based on a pre-trained real-time prediction model, specifically, the acquired real-time data of the monitoring point may be input into the pre-trained real-time prediction model, and the obtained model output result is the corresponding estimated value. It should be noted that the real-time prediction model may be a machine learning model trained in a machine learning manner and capable of determining a predicted value according to real-time data of a monitoring point. The real-time prediction model may be stored locally, for example, for local invocation at each use, or may be stored on a third party platform for invocation from a third party at each use, and is not particularly limited herein. The estimated value can be used to determine a first value range, i.e. a range of data changes during normal operating conditions of the power plant. Therefore, the determined estimated value can be adapted to the actual running state of the power plant equipment, the dependence on manual experience is reduced, and the accuracy of alarming is improved.
S102, determining a first numerical range according to the estimated value.
For example, the sum of the estimated value and the preset deviation threshold may be determined as the upper limit of the first numerical range; the difference between the estimated value and a predetermined deviation threshold is determined as the lower limit of the first value range. The preset deviation threshold value may be set by an operator based on experience. Therefore, the first numerical range determined through the estimated value is adaptive to the actual operation state of the power plant equipment, dependence on manual experience is reduced, and the accuracy of the data change range of the determined power plant equipment in the normal operation state is improved.
And S103, determining the state of the monitoring point according to the real-time data.
And S104, responding to the fact that the monitoring point is abnormal, determining an abnormal grade according to the real-time data, the first numerical range, the change rate of the real-time data in the preset duration and the change rate threshold, and generating corresponding alarm information.
For example, the power plant equipment operation abnormality occurs at different speeds, and the severity of the abnormality can be determined by the magnitude of the value of the real-time data exceeding the first value range and the magnitude of the value of the change rate of the real-time data exceeding the change rate threshold within the preset time length. The larger the value exceeded, the higher the severity of the abnormal phenomenon. The preset duration and the change rate threshold can be set by an operator according to experience.
And generating corresponding alarm information according to different abnormal levels. For example, the alarm information may be a color indicator, the color indicator may be gray if there is no abnormality, the color indicator may be yellow if it is determined that there is an abnormal phenomenon and the abnormality level is low (general abnormality), the color indicator may be red if it is determined that there is an abnormal phenomenon and the abnormality level is high (serious abnormality), and the color indicator may be displayed on the corresponding abnormal data, that is, the ground color of the text of the abnormal data is changed. Therefore, the monitoring system can enable operators to quickly locate abnormal data and determine monitoring points where abnormal phenomena occur, and can conveniently and quickly carry out next-step prevention or inspection work. For another example, the alarm information may be a sound identifier, and the sounds corresponding to different abnormality levels are different.
In the technical scheme, the estimated value obtained by the real-time prediction model can enable the first numerical range to be adaptive to the actual operation state of the power plant equipment, so that the dependence on manual experience is reduced, and the accuracy of alarming is improved. Meanwhile, the monitoring disc can be switched back and forth without the original monitoring picture, the actual full-time and full-parameter point non-blind area monitoring is achieved, the situation that abnormal events are not found due to careless monitoring of operators is avoided, the burden of the operators is greatly reduced, the operation safety of the unit is effectively guaranteed, and the artificial intelligence application of a power plant is realized.
Optionally, the intelligent monitoring method for the power plant provided by the present disclosure may further include:
inputting historical data of each monitoring point in a database into a pre-trained knowledge graph to obtain an incidence matrix, wherein the incidence matrix represents incidence relation among the historical data of each monitoring point;
and training according to the incidence matrix to obtain a real-time prediction model.
Therefore, unordered historical data can be sorted into a data state matrix with strong correlation to obtain a real-time prediction model through training, and the data with the highest similarity value in the historical data is positioned through the real-time data of the monitoring points and the real-time prediction model to carry out prediction value judgment. Therefore, the determined estimated value can be adapted to the actual running state of the power plant equipment, the dependence on manual experience is reduced, and the accuracy of alarming is improved.
Optionally, in S103, determining the state of the monitoring point according to the real-time data may include:
and if the real-time data exceeds the first numerical range and/or the change rate of the real-time data in the preset time length is greater than the change rate threshold value, determining that the monitoring point has an abnormal phenomenon.
For example, the power plant equipment may operate at different rates. On one hand, whether the monitoring point is abnormal or not can be determined by comparing the real-time data with the first numerical range; on the other hand, whether the monitoring point is abnormal or not can be determined by comparing the change rate of the real-time data in the preset time length with the change rate threshold value. Thus, the comprehensiveness of abnormality monitoring can be ensured.
Optionally, in S104, in response to determining that the monitoring point has an abnormal phenomenon, determining an abnormal level according to the real-time data, the first numerical range, the change rate of the real-time data within the preset time and the change rate threshold, and generating corresponding alarm information, which may include:
determining a first abnormal state according to the value of the real-time data exceeding the first numerical range;
determining a second abnormal state according to the value that the change rate of the real-time data in the preset time length exceeds the change rate threshold value;
and determining an output abnormal grade according to the first abnormal state and the second abnormal state, and generating corresponding alarm information.
Specifically, determining the first abnormal state according to the value of the real-time data exceeding the first value range may include:
if the value of the real-time data exceeding the first value range is smaller than a first preset value, determining that the abnormal reference level of the first abnormal state is abnormal-free;
if the value of the real-time data exceeding the first value range is greater than or equal to a first preset value and smaller than a second preset value, determining that the abnormal reference level of the first abnormal state is a general abnormality;
and if the value of the real-time data exceeding the first value range is greater than or equal to a second preset value, determining that the abnormal reference grade of the first abnormal state is serious abnormality.
The first preset value and the second preset value can be set by an operator according to experience.
Specifically, determining the second abnormal state according to a value that a change rate of the real-time data within a preset time exceeds a change rate threshold may include:
if the value of the change rate of the real-time data in the preset time length exceeding the change rate threshold is smaller than a third preset value, determining that the abnormal reference level of the second abnormal state is abnormal-free;
if the value of the change rate of the real-time data in the preset time length exceeding the change rate threshold is greater than or equal to a third preset value and smaller than a fourth preset value, determining that the abnormal reference level of the second abnormal state is a general abnormality;
and if the value of the change rate of the real-time data in the preset time length exceeding the change rate threshold value is greater than or equal to a fourth preset value, determining that the abnormal reference grade of the second abnormal state is serious abnormality.
The third preset value and the fourth preset value can be set by an operator according to experience.
The anomaly reference grade may include no anomaly, general anomaly and severe anomaly, the anomaly coefficients corresponding to no anomaly, general anomaly and severe anomaly may be preset, the anomaly coefficient corresponding to no anomaly may be 0, and the anomaly coefficients corresponding to general anomaly and severe anomaly may be positive numbers. Wherein the anomaly coefficient corresponding to the general anomaly is less than the anomaly coefficient corresponding to the severe anomaly. Therefore, the corresponding abnormal grade can be determined according to the value exceeding the threshold value so as to distinguish the abnormal degree, and operating personnel can know the abnormal severity degree accurately.
Specifically, determining an output abnormality level according to the first abnormality state and the second abnormality state, and generating corresponding alarm information may include:
and determining an output abnormal grade according to the weight and the abnormal reference grade corresponding to the first abnormal state and the second abnormal state respectively, and generating corresponding alarm information.
For example, the respective weights of the first abnormal state and the second abnormal state may be set in advance, for example, may be set to 0.5. The corresponding abnormality coefficient may be determined according to the abnormality level. And performing weighted summation through the weights and the abnormal coefficients corresponding to the first abnormal state and the second abnormal state respectively to determine the output abnormal level. For example, if the result of the weighted summation is smaller than a preset reference threshold, it may be determined that the output anomaly level is a general anomaly; and if the weighted sum result is not less than the preset reference threshold, determining that the output abnormal grade is serious abnormal. The alarm information corresponding to general abnormality can be a yellow mark, and the alarm information corresponding to serious abnormality can be a red mark.
Further, in order to make the operator know the abnormal condition more clearly, the upper limit and the lower limit may be distinguished when the real-time data is determined to be beyond the first value range. For example, when the alarm information is a color indicator, text information for prompting an upper limit or a lower limit is generated at the same time as the color indicator. As another example, a distinction may be made between color designations that exceed an upper limit or exceed a lower limit.
Optionally, the intelligent power plant monitoring method provided by the present disclosure may further include:
and generating alarm information representing abnormal switch states in response to the fact that the current switch states of the monitoring points are different from the preset switch states.
Illustratively, the switch states may include two states, on and off, and may be represented by 0 for off and 1 for on. If the current switch state of the monitoring point is determined to be 0 and the preset switch state is 1, the switching value of the monitoring point can be determined to be abnormal, and corresponding alarm information can be generated, for example, the alarm information of 'abnormal switch of the monitoring point' is displayed through a display screen of the control terminal. For another example, still can set up the speaker on the control terminal, can carry out voice broadcast to above-mentioned alarm information through the speaker to indicate the operating personnel. For another example, the background color of the text indicating the state of the switching value corresponding to the monitoring point may be changed to prompt the operator.
The method can be used by operators to comprehensively diagnose and analyze the equipment, discover the change trend and potential risk of the equipment parameters, provide support for the change of the traditional parameter alarm to a new mode of early warning pre-Control for operators on duty, support the comprehensive monitoring and early warning of multiple parameter trend changes of analog quantity and switching quantity, and improve the monitoring efficiency of the operators.
Based on the same inventive concept, the invention also provides an intelligent monitoring device for the power plant. Fig. 2 is a block diagram of an intelligent monitoring device 200 for a power plant according to an exemplary embodiment of the present disclosure. Referring to fig. 2, the intelligent monitoring device 200 of the power plant may include:
an obtaining module 201, configured to input the obtained real-time data of the monitoring point into a pre-trained real-time prediction model, and obtain a predicted value corresponding to the real-time data;
a first determining module 202, configured to determine a first value range according to the estimated value;
a second determining module 203, configured to determine a state of the monitoring point according to the real-time data;
and a third determining module 204, configured to determine, in response to determining that the monitoring point has an abnormal phenomenon, an abnormal level according to the real-time data, the first numerical range, and a change rate threshold of the real-time data within a preset time, and generate corresponding alarm information.
In the technical scheme, the estimated value obtained by the real-time prediction model can enable the first numerical range to be adaptive to the actual running state of the power plant equipment, reduces the dependence on manual experience, and improves the accuracy of alarming. Meanwhile, the monitoring disc can be switched back and forth without the original monitoring picture, the actual full-time and full-parameter point non-blind area monitoring is achieved, the situation that abnormal events are not found due to careless monitoring of operators is avoided, the burden of the operators is greatly reduced, the operation safety of the unit is effectively guaranteed, and the artificial intelligence application of a power plant is realized.
Optionally, the apparatus 200 further comprises:
the fourth determining module is used for inputting the historical data of each monitoring point in the database into a pre-trained knowledge graph to obtain an incidence matrix, wherein the incidence matrix represents the incidence relation among the historical data of each monitoring point;
and the training module is used for obtaining the real-time prediction model according to the incidence matrix training.
Optionally, the second determining module 203 is configured to determine the status of the monitoring point by:
and if the real-time data exceeds the first numerical range and/or the change rate of the real-time data in a preset time length is greater than a change rate threshold value, determining that the monitoring point has an abnormal phenomenon.
Optionally, the third determining module 204 includes:
the first determining submodule is used for determining a first abnormal state according to the value of the real-time data exceeding the first value range;
the second determining submodule is used for determining a second abnormal state according to the value that the change rate of the real-time data in the preset time length exceeds the change rate threshold;
and the third determining submodule is used for determining the output abnormal grade according to the first abnormal state and the second abnormal state and generating corresponding alarm information.
Optionally, the first determining submodule includes:
a fourth determining sub-module, configured to determine that the abnormal reference level of the first abnormal state is abnormal if the real-time data exceeds the first value range and is smaller than a first preset value;
a fifth determining sub-module, configured to determine that the abnormal reference level of the first abnormal state is a general abnormality if the real-time data exceeds the first value range by a value greater than or equal to the first preset value and smaller than a second preset value;
and the sixth determining submodule is used for determining that the abnormal reference level of the first abnormal state is serious abnormality if the value of the real-time data exceeding the first value range is greater than or equal to the second preset value.
Optionally, the second determining submodule includes:
a seventh determining submodule, configured to determine that the abnormal reference level of the second abnormal state is abnormal if a value of a change rate of the real-time data within a preset duration, which exceeds the change rate threshold, is smaller than a third preset value;
an eighth determining sub-module, configured to determine that the abnormal reference level of the second abnormal state is a general abnormality if a value of a change rate of the real-time data within a preset time period, which exceeds the change rate threshold, is greater than or equal to the third preset value and is smaller than a fourth preset value;
and the ninth determining submodule is used for determining that the abnormal reference level of the second abnormal state is serious abnormality if the change rate of the real-time data in the preset time length exceeds the change rate threshold value and is greater than or equal to the fourth preset value.
Optionally, the third determining submodule is configured to determine an output abnormality level and generate corresponding alarm information by:
and determining an output abnormal grade according to the weight and the abnormal reference grade corresponding to the first abnormal state and the second abnormal state respectively, and generating corresponding alarm information.
Optionally, the apparatus 200 further comprises:
and the fifth determining module is used for generating alarm information representing abnormal switch states in response to the fact that the current switch states of the monitoring points are different from the preset switch states.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 3 is a block diagram illustrating an electronic device 700 according to an example embodiment. As shown in fig. 3, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a communication component 705.
The processor 701 is configured to control the overall operation of the electronic device 700, so as to complete all or part of the steps in the above-mentioned intelligent monitoring method for a power plant. The memory 702 is used to store various types of data to support operation at the electronic device 700, such as instructions for any application or method operating on the electronic device 700 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and the like. The Memory 702 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically Erasable Programmable Read-Only Memory (EEPROM), erasable Programmable Read-Only Memory (EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia components 703 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 702 or transmitted through the communication component 705. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or a combination thereof, which is not limited herein. The corresponding communication component 705 may thus include: wi-Fi module, bluetooth module, NFC module, etc.
In an exemplary embodiment, the electronic Device 700 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the above-described intelligent plant monitoring method.
In another exemplary embodiment, a computer readable storage medium including program instructions which, when executed by a processor, implement the steps of the intelligent plant monitoring method described above is also provided. For example, the computer readable storage medium may be the memory 702 described above including program instructions that are executable by the processor 701 of the electronic device 700 to perform the plant intelligent inventory monitoring method described above.
In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable device, the computer program having code portions for performing the above-mentioned plant intelligent inventory monitoring method when executed by the programmable device.
The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details in the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. To avoid unnecessary repetition, the disclosure does not separately describe various possible combinations.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.
Claims (11)
1. A power plant intelligent monitoring method is characterized by comprising the following steps:
inputting the obtained real-time data of the monitoring points into a real-time prediction model which is trained in advance, and obtaining a predicted value corresponding to the real-time data;
determining a first value range according to the estimated value;
determining the state of the monitoring point according to the real-time data;
and in response to the fact that the monitoring point is determined to have an abnormal phenomenon, determining an abnormal grade according to the real-time data, the first numerical range, the change rate of the real-time data in a preset time length and a change rate threshold value, and generating corresponding alarm information.
2. The method of claim 1, further comprising:
inputting historical data of each monitoring point in a database into a pre-trained knowledge graph to obtain an incidence matrix, wherein the incidence matrix represents incidence relation among the historical data of each monitoring point;
and training according to the incidence matrix to obtain the real-time prediction model.
3. The method of claim 1, wherein said determining a status of said monitoring point from said real-time data comprises:
and if the real-time data exceeds the first numerical range and/or the change rate of the real-time data in a preset time length is greater than a change rate threshold value, determining that the monitoring point has an abnormal phenomenon.
4. The method according to claim 1, wherein the determining an anomaly level according to the real-time data, the first numerical range, a change rate of the real-time data within a preset time duration and a change rate threshold, and generating corresponding alarm information comprises:
determining a first abnormal state according to the value of the real-time data exceeding the first value range;
determining a second abnormal state according to the value that the change rate of the real-time data in a preset time length exceeds a change rate threshold value;
and determining an output abnormal grade according to the first abnormal state and the second abnormal state, and generating corresponding alarm information.
5. The method of claim 4, wherein said determining a first abnormal condition based on values of said real-time data exceeding said first range of values comprises:
if the value of the real-time data exceeding the first value range is smaller than a first preset value, determining that the abnormal reference level of the first abnormal state is abnormal-free;
if the value of the real-time data exceeding the first value range is greater than or equal to the first preset value and less than a second preset value, determining that the abnormal reference level of the first abnormal state is a general abnormality;
and if the value of the real-time data exceeding the first value range is larger than or equal to the second preset value, determining that the abnormal reference grade of the first abnormal state is serious abnormality.
6. The method of claim 4, wherein the determining a second abnormal state according to the value that the change rate of the real-time data within the preset time length exceeds the change rate threshold value comprises:
if the value of the change rate of the real-time data in the preset time length exceeding the change rate threshold is smaller than a third preset value, determining that the abnormal reference level of the second abnormal state is abnormal-free;
if the value of the change rate of the real-time data in the preset time length, which exceeds the change rate threshold value, is greater than or equal to the third preset value and is less than a fourth preset value, determining that the abnormal reference level of the second abnormal state is a general abnormality;
and if the value of the change rate of the real-time data in the preset time length exceeding the change rate threshold is greater than or equal to the fourth preset value, determining that the abnormal reference level of the second abnormal state is serious abnormality.
7. The method of claim 4, wherein determining an output anomaly level based on the first and second anomaly states and generating corresponding alert information comprises:
and determining an output abnormal grade according to the weight and the abnormal reference grade corresponding to the first abnormal state and the second abnormal state respectively, and generating corresponding alarm information.
8. The method of claim 1, further comprising:
and generating alarm information representing abnormal switch states in response to the fact that the current switch states of the monitoring points are different from the preset switch states.
9. The utility model provides an intelligent prison dish device of power plant which characterized in that includes:
the acquisition module is used for inputting the acquired real-time data of the monitoring points into a pre-trained real-time prediction model to acquire a predicted value corresponding to the real-time data;
a first determining module for determining a first value range based on the estimated value;
the second determining module is used for determining the state of the monitoring point according to the real-time data;
and the third determining module is used for responding to the determination that the monitoring point has an abnormal phenomenon, determining an abnormal grade according to the real-time data, the first numerical range, the change rate of the real-time data in a preset time length and a change rate threshold value, and generating corresponding alarm information.
10. A non-transitory computer readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
11. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to implement the steps of the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211658876.6A CN115912658A (en) | 2022-12-22 | 2022-12-22 | Intelligent monitoring method and device for power plant, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211658876.6A CN115912658A (en) | 2022-12-22 | 2022-12-22 | Intelligent monitoring method and device for power plant, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115912658A true CN115912658A (en) | 2023-04-04 |
Family
ID=86479576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211658876.6A Pending CN115912658A (en) | 2022-12-22 | 2022-12-22 | Intelligent monitoring method and device for power plant, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115912658A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116088398A (en) * | 2023-04-10 | 2023-05-09 | 中国电力工程顾问集团西南电力设计院有限公司 | Be used for wisdom prison dish alarm system of thermal power plant |
-
2022
- 2022-12-22 CN CN202211658876.6A patent/CN115912658A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116088398A (en) * | 2023-04-10 | 2023-05-09 | 中国电力工程顾问集团西南电力设计院有限公司 | Be used for wisdom prison dish alarm system of thermal power plant |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108206747B (en) | Alarm generation method and system | |
| CN109088775B (en) | Abnormity monitoring method and device and server | |
| CN115912658A (en) | Intelligent monitoring method and device for power plant, storage medium and electronic equipment | |
| CN103810823B (en) | Alarm processing method and device | |
| US10824963B2 (en) | Alarm handling system and method in plant process automation | |
| KR20140073043A (en) | Application service system of smart terminal for watching power equipment | |
| CN112532435B (en) | Operation and maintenance method, operation and maintenance management platform, equipment and medium | |
| CN115941453B (en) | Machine room alarm processing method and device based on digital twin, machine room and medium | |
| CN111130867B (en) | Intelligent household equipment alarm method and device based on Internet of things | |
| CN106913313B (en) | Sleep monitoring method and system | |
| CN112233370A (en) | Gas leakage alarm method, device and equipment | |
| CN107368058A (en) | It is a kind of for the fault monitoring method of equipment, equipment and computer-readable medium | |
| CN207731133U (en) | Industrial automation monitoring early-warning system | |
| CN112462237A (en) | Information processing method and device for circuit safety early warning | |
| WO2017051574A1 (en) | Abnormality indication monitoring system | |
| CN111289036A (en) | Equipment fault early warning method, device, equipment and system | |
| EP3705783A1 (en) | System for controlling and monitoring devices, plants and/or domestic circuits and operation method thereof | |
| CN116416764A (en) | Alarm threshold generation method and device, electronic equipment and storage medium | |
| CN114244681A (en) | Equipment connection fault early warning method and device, storage medium and electronic equipment | |
| CN113254287A (en) | Health state self-checking method, device, equipment and computer readable medium | |
| CN104898535A (en) | Monitoring method, device and system | |
| CN111382035A (en) | Global matching device and method for alarm triggering rules of operation and maintenance system | |
| CN112634593B (en) | Equipment early warning method and device, computer equipment and storage medium | |
| JP2020016462A (en) | Monitoring device, monitoring method and monitoring program | |
| TW201929584A (en) | Fault identification server and method for base station |
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 |