CN112102593A - Pre-alarm technology application for guaranteeing operation safety based on real-time data self-learning model of thermal power plant production - Google Patents
Pre-alarm technology application for guaranteeing operation safety based on real-time data self-learning model of thermal power plant production Download PDFInfo
- Publication number
- CN112102593A CN112102593A CN202010984343.1A CN202010984343A CN112102593A CN 112102593 A CN112102593 A CN 112102593A CN 202010984343 A CN202010984343 A CN 202010984343A CN 112102593 A CN112102593 A CN 112102593A
- Authority
- CN
- China
- Prior art keywords
- self
- alarm
- learning model
- limit value
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/20—Software design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computing Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to a pre-alarming technology for guaranteeing operation safety based on a real-time data self-learning model of thermal power plant production, which comprises the following steps: step 1, establishing an alarm module in a configuration mode, and setting a pre-alarm limit value in advance; step 2, configuring and establishing a self-learning model, and setting an association relationship between the self-learning model and the alarm module; step 3, setting input and output parameter values of the self-learning model, such as weight values and maximum values; and 4, calibrating the alarm module through the self-learning model, and determining a pre-alarm limit value through setting an update limit value of the self-learning module. The invention has the beneficial effects that: the SAMA type configuration mode can form a combined logic on an interface through support pulling and connecting wires, and the interface logic is clear at a glance in a graphical design mode, so that the problem of solidification of software codes is solved. The pre-alarm logic is flexibly configured, the alarm parameters of the equipment can be flexibly and freely modified, the operation is simplified, the cost of system operation and maintenance is reduced, and the alarm logic function is richly expanded.
Description
Technical Field
The invention belongs to the field of pre-alarming of thermal power plants, and particularly relates to a pre-alarming technology for guaranteeing operation safety based on a real-time data self-learning model of thermal power plant production and application thereof.
Background
In the traditional operation monitoring system, program codes are formed by combining the working experience of operators on duty and the process parameters of equipment, and the program codes are solidified in the system. The code can not automatically make corresponding changes according to the aging, updating, replacement and the like of the field equipment, so that operation monitoring personnel can make wrong judgment and treatment on equipment alarm, and further safety accidents are caused.
Different monitoring personnel treat the process parameters and pre-alarm limit values of the equipment, and due to different experiences, the alarm processing time is different; for example, the current of the coal mill A is set to be 50 by an experienced person, and corresponding operation treatment is carried out to avoid safety accidents. However, when a new person gives an alarm with an alarm value of 50, the new person is busy and foot-ridden due to insufficient experience, and the emergency accident cannot be quickly handled. If the pre-alarm occurs when the temperature drops to about 48, the new person has sufficient time to respond.
Meanwhile, a system platform at the DCS side of the power generation enterprise cannot set complex alarm logics, such as broken line alarm and the like; and as DCS belongs to a production side link, technical and safety problems may exist in manual modification.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provides the application of the pre-alarming technology for guaranteeing the operation safety based on the real-time data self-learning model of the thermal power plant production.
The pre-alarming technology for guaranteeing the operation safety based on the real-time data self-learning model for the production of the thermal power plant comprises the following steps:
step 1, establishing an alarm module in a configuration mode, and setting a pre-alarm limit value in advance;
step 2, configuring and establishing a self-learning model, and setting an incidence relation between the self-learning model and the alarm module established in the step 1;
step 3, setting input and output parameter values of the self-learning model, such as weight values and maximum values; through the set association relationship, after the self-learning model is successfully connected with the alarm module, the self-learning module identifies the alarm module, and selects the alarm module to be modified for the alarm limit value through the configuration page of the self-learning model;
step 4, calibrating the alarm module through the self-learning model, and determining a pre-alarm limit value through setting an update limit value of the self-learning module;
step 5, after the logic model built by the configuration from the step 1 to the step 4 is started to operate, the self-learning model calibrates a pre-alarm limit value of an alarm module according to real-time production operation data, and determines whether to alarm or not according to the pre-alarm limit value, if not, the alarm module associated with the self-learning model directly outputs alarm information; if the alarm module is associated with the self-learning model, whether the alarm module gives an alarm or not, the upper limit and the lower limit of the pre-alarm limit value are updated according to the self-learning model in each operation period.
Preferably, the association relationship in step 2 is established and generated by a connection mode of a configuration logic connection line; and the output value node of the self-learning model is connected with the input value node of the alarm module.
Preferably, when the input parameter value and the output parameter value of the self-learning model in the step 3 are used for controlling self-learning, the limit value of the alarm module fluctuates within a fixed range without sudden over-or under-excess.
Preferably, the maximum value of the input and output parameter values of the self-learning model in step 3 is set to 20, and when the maximum value exceeds the threshold, the maximum value may exceed the current limit by the ratio:
in the above formula, x is the interface input value, x is the real number greater than 0 (used for determining f (x)), f (x) is the specific gravity (percentage) exceeding the current limit value when the out-of-limit occurs, and f (x) is 20% at most; if the input x of the interface exceeds 20, f (x) is 20%, if the input x is less, f (x) is x/100;
preferably, the self-learning model in the step 5 calibrates the pre-alarm limit value of the alarm module according to the real-time production operation data, and corrects the current alarm limit value of the alarm module:
Y′＝Y+(X-Y)*a (2)
in the above formula, Y' is the current alarm limit value, X is the self-learning input value, Y is the out-of-limit alarm limit value, and a is the weight value.
Preferably, the step 2 additionally arranges a programming module or other configuration modules before and after the self-learning model, and the configuration and the graphic arrangement are not influenced by codes solidified in a software system.
An application of a pre-alarming technology for guaranteeing operation safety based on a real-time data self-learning model for thermal power plant production in pre-alarming of a thermal power plant.
The invention has the beneficial effects that:
(1) logical organization: the SAMA type configuration mode can form a combined logic on an interface through support pulling and connecting wires, and the interface logic is clear at a glance in a graphical design mode, so that the problem of solidification of software codes is solved. The pre-alarm logic is flexibly configured, the alarm parameters of the equipment can be flexibly and freely modified, the operation is simplified, the cost of system operation and maintenance is reduced, and the alarm logic function is richly expanded.
(2) On the basis of logical composition, a pre-alarming technology with a self-learning function is established; empirical values may be combined with historical data; the self-learning module solves the problem of inaccurate pre-alarm setting limit value caused by equipment aging, replacement and the like, and also solves the problems of timeliness and stability of operation after pre-alarm caused by personal experience data; on the basis of empirical data, the pre-alarm limit value is automatically calibrated through self-learning of historical alarm data, and is continuously and automatically adjusted and calibrated, so that the alarm limit value is more normalized (a self-learning internal mathematical formula) and is maintained in a reasonable range; the problem that the pre-alarm limit value cannot be automatically updated due to equipment aging, updating, replacing and the like is solved.
(3) The user-defined programming module also belongs to a configuration module, can be combined with other modules at will, and is provided with an input interface and an output interface; DSL (domain specific programming language) is implemented using ANTLR and can be freely programmed. The custom programming module can customize input parameters and output parameters, write service codes and realize any logic. And the self-learning module also solves the problem of individual difference when the experienced personnel and the new people set the pre-alarm limit value, so that each person can make a treatment response within a certain time.
(4) The extended DCS alarm module is internally provided with a DCS side basic configuration logic: adding, subtracting, multiplying, dividing, and alarming with upper and lower limits, NAND, broken line, and other ten kinds of commonly used alarming modules; and the alarm modules which are not available in the traditional DCS, such as broken line alarm and the like, are expanded. Other alarm logics can be further realized through the configuration and programming module, and rich alarm logics are expanded.
Drawings
FIG. 1 is a flow chart of a pre-warning technology for guaranteeing operation safety based on a real-time data self-learning model for thermal power plant production;
FIG. 2 is a flow diagram of a logical compute alarm page generation;
FIG. 3 is a flow chart of alarm unit parameter editing;
FIG. 4 is a flow chart of a periodically executed logic computation alarm page.
Detailed Description
The present invention will be further described with reference to the following examples. The following examples are set forth merely to aid in the understanding of the invention. It should be noted that, for a person skilled in the art, several modifications can be made to the invention without departing from the principle of the invention, and these modifications and modifications also fall within the protection scope of the claims of the present invention.
As an embodiment, as shown in fig. 1, the implementation process of the pre-warning technology for guaranteeing the operation safety based on the real-time data self-learning model for the production of the thermal power plant is as follows: setting a certain alarm logic, and calculating and storing historical data. If the self-learning model exists in the calculation, the self-learning is carried out. The description will be given by taking as an example the combination of an upper and lower limit alarm (SAMA alarm unit), a programming module and a self-learning module (SAMA auxiliary unit).
As shown in fig. 2, the graphic editor may generate a graphic by means of configuration dragging, and after the SAMA computing unit, the SAMA alarm unit, and the SAMA auxiliary unit are connected by a connection line, the SAMA alarm logic is combined, and then the basic graphic element and the SAMA alarm logic are dragged and laid out on the editor interface, so as to design a logic computing alarm page. The basic graphic elements include: straight lines, polygons, rectangles, ellipses, trend graphs, bar graphs, pie graphs, analog quantities, and switching quantities; the SAMA calculation unit includes: addition, subtraction, multiplication, division, continuous addition, logical AND, logical OR and logical NOT; the SAMA alarm unit comprises: upper and lower limit alarm, non-alarm, state alarm and broken line alarm; the SAMA auxiliary unit comprises: the device comprises a connecting line, a point measurement value, a point measurement module, a global variable, a programming module, a delay module, a self-learning module and a random number.
The SAMA alarm unit and the SAMA auxiliary unit need to design various parameters according to requirements, and the implementation steps are as shown in FIG. 3: the SAMA alarm unit and the SAMA auxiliary unit are connected through a connecting line, and then parameter values of the SAMA alarm unit and parameter values of the SAMA auxiliary unit are respectively edited; the SAMA alarm unit parameter values comprise upper and lower limit values of upper and lower levels, a state 0 and a state 1, color, voice, a broken line list and the like. The SAMA auxiliary unit parameter values comprise measuring points, indexes, storage numbers, delay time, weighted values, proportions and the like.
After the SAMA calculating unit, the SAMA alarming unit and the SAMA auxiliary unit are edited, the SAMA calculating unit, the SAMA alarming unit and the SAMA auxiliary unit can operate according to a custom period, and the process is shown in fig. 4: dragging and arranging basic graphic elements and SAMA alarm logic on an editor interface, designing a logic calculation alarm page, starting to run periodically, executing an SAMA logic unit (an SAMA calculation unit, an SAMA alarm unit and an SAMA auxiliary unit) according to a connecting line transmission sequence, and judging whether an alarm module gives an alarm or not; if the alarm module does not alarm, returning to restart the periodic operation; if the alarm module gives an alarm, prompts such as voice and sound-light alarm are given out, the alarm information is stored in the time sequence database, and the periodic operation is restarted.
The combined application of a certain upper and lower limit alarm, programming module and self-learning module is as follows: if the upper and lower limit alarm units are the temperature of the outlet of the A mill, alarm limit values are set according to experience, for example, the upper third of the temperature of the outlet of the A mill is equal to 105, and the upper second is equal to 100, once the current of the A mill exceeds 100, the upper second alarm is carried out, and the upper third alarm is carried out when the current exceeds 105. Attribute information such as color (red and green) at the time of alarm, whether to broadcast by voice, alarm description remark information, whether to pop up a window or not, and the like can also be set for the alarm unit (different SAMA alarm units may have different attributes, which are just listed as commonalities, and other attributes are not described in detail). But self-learning is not required at all times, for example, according to business requirements, when the unit load rate is 40% -80%, the A mill outlet temperature is output as it is; when the load factor of the unit is less than 40%, the temperature value of the grinding outlet A is multiplied by 0.95; when the unit load factor is greater than 80%, the A mill outlet temperature is multiplied by the 1.05 output. At this time, if the grinding outlet temperature of the SAMA alarm unit A needs a self-learning function, the configuration connection mode is as follows: the output value port of the A mill outlet temperature module is connected with the input port of the programming module through a connecting wire; the programming module can automatically recognize the input value of the input module, the added input variable is A _ in, then the output end needs to be dynamically added in the programming module, the added output end is A _ out, and according to the business logic, pseudo codes in the programming module (assuming that the unit load rate is a global variable power):
then, the output end dynamically generated by the programming module is connected with the input end of the self-learning module through a connecting wire, and the output value end of the self-learning module is connected back to the self-learning input end of the A grinding outlet temperature SAMA alarm unit through a connecting wire. Thus, an SAMA alarm unit alarming from the upper and lower limits is combined with the SAMA auxiliary unit programming module and the self-learning module to complete the configuration. The attribute description for the self-learning module is as in equations (1) and (2):
in the formula, x is an interface input value, x is a real number greater than 0, f (x) is the specific gravity exceeding the current limit value when the out-of-limit occurs, and f (x) is maximum 20%; if the input x of the interface exceeds 20, f (x) is 20%, if the input x is less, f (x) is x/100;
the self-learning model calibrates the pre-alarm limit value of the alarm module according to the real-time production operation data, and corrects the current alarm limit value of the alarm module:
Y′＝Y+(X-Y)*a (2)
in the above formula, Y' is the current alarm limit value, X is the self-learning input value, Y is the out-of-limit alarm limit value, and a is the weight value;
for example, the weight a in the self-learning module is 10%, and the maximum value is 15%. If the temperature of the outlet of the grinding A is 110 and is more than 105 of the upper three, alarming is started; meanwhile, 110 is transmitted to the programming module, if the unit load rate is 70% at the moment, the output is still 110 according to the codes of the programming module, and 110 is transmitted to the self-learning module. According to the formula (1), (110-; thus, the module is executed and then waits for the start of the next cycle;
the single unchangeable empirical value cannot reflect the change of the alarm limit value caused by the complex environment (equipment aging, severe production and operation environment, equipment maintenance and replacement and the like) of the power plant. The embodiment can not only dynamically maintain, but also reflect the real information of the upper and lower alarm limits of the equipment in real time through self-learning (the upper and lower modification limits and the like are also in a reasonable floating range). In short, through dragging and connecting (organizing) of the graphic elements and the SAMA units, a logic calculation alarm page which is finally needed can be generated.
Claims (7)
1. The pre-alarming technology for guaranteeing the operation safety based on the real-time production data self-learning model of the thermal power plant is characterized by comprising the following steps of:
step 1, establishing an alarm module in a configuration mode, and setting a pre-alarm limit value in advance;
step 2, configuring and establishing a self-learning model, and setting an incidence relation between the self-learning model and the alarm module established in the step 1;
step 3, setting input and output parameter values of the self-learning model; through the set association relationship, after the self-learning model is successfully connected with the alarm module, the self-learning module identifies the alarm module, and selects the alarm module to be modified for the alarm limit value through the configuration page of the self-learning model;
step 4, calibrating the alarm module through the self-learning model, and determining a pre-alarm limit value through setting an update limit value of the self-learning module;
step 5, after the logic model built by the configuration from the step 1 to the step 4 is started to operate, the self-learning model calibrates a pre-alarm limit value of an alarm module according to real-time production operation data, and determines whether to alarm or not according to the pre-alarm limit value, if not, the alarm module associated with the self-learning model directly outputs alarm information; if the alarm module is associated with the self-learning model, the upper limit and the lower limit of the pre-alarm limit value are updated according to the self-learning model in each operation period.
2. The pre-alarming technology for guaranteeing the operation safety based on the real-time data self-learning model of the thermal power plant production as claimed in claim 1, wherein: the incidence relation in the step 2 is established and generated in a mode of connecting configuration logic connecting lines; and the output value node of the self-learning model is connected with the input value node of the alarm module.
3. The pre-alarming technology for guaranteeing the operation safety based on the real-time data self-learning model of the thermal power plant production as claimed in claim 1, wherein: and 3, when the input parameter value and the output parameter value of the self-learning model in the step 3 are used for controlling self-learning, the limit value of the alarm module fluctuates in a fixed range.
4. The pre-alarming technology for guaranteeing the operation safety based on the real-time data self-learning model of the thermal power plant production as claimed in claim 1, wherein: the maximum value of the input and output parameter values of the self-learning model in the step 3 is set to be 20:
in the above formula, x is an interface input value, and x is a real number greater than 0; (x) is the specific gravity exceeding the current limit when the out-of-limit occurs, f (x) is 20% at most; if x of the interface input exceeds 20, f (x) is 20%, and if x of the interface input is less than f (x) is x/100.
5. The pre-alarming technology for guaranteeing the operation safety based on the real-time data self-learning model of the thermal power plant production as claimed in claim 1, wherein: in the step 5, the self-learning model calibrates the pre-alarm limit value of the alarm module according to the real-time production operation data, and corrects the current alarm limit value of the alarm module:
Y′＝Y+(X-Y)*a (2)
in the above formula, Y' is the current alarm limit value, X is the self-learning input value, Y is the out-of-limit alarm limit value, and a is the weight value.
6. The pre-alarming technology for guaranteeing the operation safety based on the real-time data self-learning model of the thermal power plant production as claimed in claim 1, wherein: and step 2, additionally arranging a programming module or other configuration modules before and after the self-learning model.
7. Use of the pre-warning technology for guaranteeing the operation safety based on the real-time data self-learning model of thermal power plant production as defined in claim 1 in the pre-warning of the thermal power plant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010984343.1A CN112102593A (en) | 2020-09-18 | 2020-09-18 | Pre-alarm technology application for guaranteeing operation safety based on real-time data self-learning model of thermal power plant production |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010984343.1A CN112102593A (en) | 2020-09-18 | 2020-09-18 | Pre-alarm technology application for guaranteeing operation safety based on real-time data self-learning model of thermal power plant production |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112102593A true CN112102593A (en) | 2020-12-18 |
Family
ID=73758897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010984343.1A Pending CN112102593A (en) | 2020-09-18 | 2020-09-18 | Pre-alarm technology application for guaranteeing operation safety based on real-time data self-learning model of thermal power plant production |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112102593A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020188582A1 (en) * | 2001-06-08 | 2002-12-12 | Robert Jannarone | Automated analyzers for estimation systems |
| CN101592964A (en) * | 2009-06-26 | 2009-12-02 | 北京首钢自动化信息技术有限公司 | A kind of system for controlling forecast of molten steel temperature of double-station LF furnace |
| CN101989087A (en) * | 2010-09-26 | 2011-03-23 | 中国石油化工股份有限公司 | On-line real-time failure monitoring and diagnosing system device for industrial processing of residual oil |
| CN106682316A (en) * | 2016-12-29 | 2017-05-17 | 北京工业大学 | Real-time effluent total-phosphorus monitoring system based on peak radial basis function neural network |
| CN109492956A (en) * | 2019-01-08 | 2019-03-19 | 北京国电智深控制技术有限公司 | A kind of the operating parameter method for early warning and device of thermal power generation unit |
| CN109524139A (en) * | 2018-10-23 | 2019-03-26 | 中核核电运行管理有限公司 | A kind of real-time device performance monitoring method based on equipment working condition variation |
| CN110148285A (en) * | 2019-05-15 | 2019-08-20 | 东营汉威石油技术开发有限公司 | A kind of oilwell parameter intelligent early-warning system and its method for early warning based on big data technology |
| CN110533294A (en) * | 2019-07-30 | 2019-12-03 | 中国核电工程有限公司 | A kind of nuclear power plant's operation troubles alarm method based on artificial intelligence technology |
| CN111538311A (en) * | 2020-04-22 | 2020-08-14 | 北京航空航天大学 | Flexible multi-state self-adaptive early warning method and device for mechanical equipment based on data mining |
| CN111580479A (en) * | 2020-05-13 | 2020-08-25 | 刘金涛 | Intelligent manufacturing industry parameter optimization method based on machine learning and industrial Internet of things |
-
2020
- 2020-09-18 CN CN202010984343.1A patent/CN112102593A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020188582A1 (en) * | 2001-06-08 | 2002-12-12 | Robert Jannarone | Automated analyzers for estimation systems |
| CN101592964A (en) * | 2009-06-26 | 2009-12-02 | 北京首钢自动化信息技术有限公司 | A kind of system for controlling forecast of molten steel temperature of double-station LF furnace |
| CN101989087A (en) * | 2010-09-26 | 2011-03-23 | 中国石油化工股份有限公司 | On-line real-time failure monitoring and diagnosing system device for industrial processing of residual oil |
| CN106682316A (en) * | 2016-12-29 | 2017-05-17 | 北京工业大学 | Real-time effluent total-phosphorus monitoring system based on peak radial basis function neural network |
| CN109524139A (en) * | 2018-10-23 | 2019-03-26 | 中核核电运行管理有限公司 | A kind of real-time device performance monitoring method based on equipment working condition variation |
| CN109492956A (en) * | 2019-01-08 | 2019-03-19 | 北京国电智深控制技术有限公司 | A kind of the operating parameter method for early warning and device of thermal power generation unit |
| CN110148285A (en) * | 2019-05-15 | 2019-08-20 | 东营汉威石油技术开发有限公司 | A kind of oilwell parameter intelligent early-warning system and its method for early warning based on big data technology |
| CN110533294A (en) * | 2019-07-30 | 2019-12-03 | 中国核电工程有限公司 | A kind of nuclear power plant's operation troubles alarm method based on artificial intelligence technology |
| CN111538311A (en) * | 2020-04-22 | 2020-08-14 | 北京航空航天大学 | Flexible multi-state self-adaptive early warning method and device for mechanical equipment based on data mining |
| CN111580479A (en) * | 2020-05-13 | 2020-08-25 | 刘金涛 | Intelligent manufacturing industry parameter optimization method based on machine learning and industrial Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109269556A (en) | A kind of equipment Risk method for early warning, device, terminal device and storage medium | |
| CN109980631B (en) | Method for calculating clearing and node electricity price of current electric power spot market | |
| CN101382775A (en) | Methods and apparatus to control information presented to process plant operators | |
| US9208677B2 (en) | Systems and methods for process alarm reduction | |
| CN106655158A (en) | Smart grid based distribution network self-healing control system and method | |
| CN109376872A (en) | A kind of offshore wind farm unit maintenance system | |
| CN110752608A (en) | Method and device for switching PID (proportion integration differentiation) parameters of speed regulating system of hydroelectric generating set and storage medium | |
| JP4864839B2 (en) | Power fluctuation prediction system | |
| CN112102593A (en) | Pre-alarm technology application for guaranteeing operation safety based on real-time data self-learning model of thermal power plant production | |
| CN107505922A (en) | Factory's early warning implementation method, apparatus and system | |
| CN113326585B (en) | Energy efficiency abnormality early warning method and device for gas boiler and computer equipment | |
| Wu et al. | Preventive control strategy for an island power system that considers system security and economics | |
| CN110766480B (en) | Real-time market clearing optimization method and device considering condition control section | |
| CN113013990A (en) | Generator set fault early warning method, system and related equipment | |
| WO2024051173A1 (en) | Target function implementation-oriented system success path planning method and system, device, and medium | |
| Jeong et al. | Multistage model predictive control with simplified scenario ensembles for robust control of hydropower station | |
| Liu et al. | Rule-based control system design for smart grids | |
| CN114462710A (en) | Short-term prediction method, device and medium for fan generated power | |
| CN114138452B (en) | High-energy-efficiency computing node selection method and device in edge computing | |
| US20210263486A1 (en) | Adaptive energy storage operating system for multiple economic services | |
| CN114895623A (en) | Granular sludge process intelligent control system, method, computer equipment and storage medium | |
| JP2018132916A (en) | Water treatment plant operation support system | |
| Mitrofanov et al. | Development of a Software Module of Intra-Plant Optimization for Short-Term Forecasting of Hydropower Plant Operating Conditions | |
| CN112947611A (en) | Scheduling method and system based on pressure monitoring | |
| CN105140912A (en) | Power network stability section control limit identification method of considering stability control system operating state |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20201218 |