CN115390448A - Visual analysis method and system for control strategy of coal-fired power plant - Google Patents
Visual analysis method and system for control strategy of coal-fired power plant Download PDFInfo
- Publication number
- CN115390448A CN115390448A CN202210984645.8A CN202210984645A CN115390448A CN 115390448 A CN115390448 A CN 115390448A CN 202210984645 A CN202210984645 A CN 202210984645A CN 115390448 A CN115390448 A CN 115390448A
- Authority
- CN
- China
- Prior art keywords
- control strategy
- data
- coal
- power plant
- fired power
- 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
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a visual analysis method for a control strategy of a coal-fired power plant, which comprises the following steps: step 1, obtaining historical operation data of a coal-fired power plant, wherein the historical operation data comprises equipment data acquired by a sensor and corresponding sensor position data; step 2, analyzing the equipment data in a preset time interval on the basis of the sensor position data to acquire control strategy information in the time interval; and 3, importing the equipment data, the sensor position data and the control strategy information into a pre-constructed visual model, carrying out graphic drawing on the imported data and information in the visual model, carrying out interactive operation on the data in the graphic, and then outputting and displaying the data. The invention also provides a visual analysis system based on the method. The method allows a user to specify a query control strategy, provides an algorithm for automatically matching and mining the control strategy, and supports the spatial propagation mode and influence time lag analysis of the control strategy.
Description
Technical Field
The invention belongs to the technical field of control strategy analysis, and particularly relates to a visualized analysis and system for a control strategy of a coal-fired power plant.
Background
The control strategy is an important factor affecting the efficiency of coal-fired power generation. Experts often follow specific control strategies to achieve corresponding purposes, such as improving combustion rate and reducing pollution emission, in regulating coal-fired power plants. A large number of sensors monitor the operation of coal-fired power plants, and these sensors can be classified into two types according to the monitoring categories: control sensors that monitor control variables (e.g., valves), status sensors that monitor physical conditions (e.g., temperature). Changes monitored by these sensors are defined as corresponding control events and status events. A control strategy is a sequence of multiple associated control events and state events.
Control strategy analysis techniques fall into two categories: an experience-driven approach and a data-driven approach.
The analysis process supported by the experience-driven method includes data collection, condition monitoring and data presentation. RSSFAD, for example, collects data from sensors that are constantly being transmitted and visualized through a simple dashboard, and such methods are characterized by: firstly, the real-time performance is good, and the online monitoring of electric field data can be supported; secondly, displaying the fine granularity, and presenting the original time sequence data by visualization; third, no inherited automatic algorithm does not support control policy extraction, and the control policy needs to be judged by analyzing raw data empirically, so that mining and analysis of control policies on large-scale data cannot be completed. Moreover, most of the presentation methods of the analysis results are simple static charts, for example, RSSFAD draws a simple flow structure. These single presentation methods limit the user's insight into the control strategy of coal-fired power plants.
The existing data driving method firstly models a coal-fired power plant and then simulates a control strategy, and supports the modeling of an individual unit or all units. When modeling is carried out on an individual unit, the aim of optimizing the control logic inside the single unit is taken as the target, and the complete control strategy of the cross-unit cannot be analyzed. When modeling is carried out on the whole unit, strict modeling conditions (such as steady-state operation) are set, otherwise derivation cannot be established, or machine learning is carried out based on historical data, and huge data accumulation and reasonable interpretable rules are needed. These conditions limit the scalability of the corresponding method.
Patent document CN112102111A discloses an intelligent processing system for power plant data, comprising: the method comprises the following steps: an operation and maintenance management module; a security management module; a data acquisition and extraction module; a data storage module; a general analysis and calculation module; the intelligent calculation and analysis module: based on a machine learning algorithm, an intelligent algorithm model is established and trained by utilizing distributed computing resources, and a prediction model is established through data after multidimensional associated data analysis; an edge calculation module; the micro-service release module: the system is used for issuing and managing system bearing data, computing tasks and external services; and a data management module. But this approach ignores the time lag problem that exists when sensors are fed back.
Disclosure of Invention
In order to solve the problems, the invention provides a visual analysis method for a control strategy of a coal-fired power plant, which is used for processing abnormal events of the coal-fired power plant by adopting time-lag relation optimization based on the influence of the control strategy on the coal-fired power plant.
A visual analysis method for a coal-fired power plant control strategy, comprising:
and 3, importing the equipment data, the sensor position data and the control strategy information into a pre-constructed visual model, carrying out graphic drawing on the imported data and information in the visual model, carrying out interactive operation on the data in the graphic, and then outputting and displaying the data.
Specifically, the device data includes operation state data and control instruction data of the device.
Specifically, the time interval is the range time of the power generation efficiency, the negative pressure parameter of the furnace or the sudden change of pollutant emission, namely the area containing the maximum value or the minimum value of the first derivative, and the threshold is set to be 80% of the maximum absolute value of the first derivative.
Preferably, the analysis in step 2 adopts an aggregation operation method to analyze the spatial position of the sensor, the correlation between adjacent sensors, and the relationship between the sensor data change and the time series.
Preferably, the relationship of the sensor data change to the time series is displayed in time delay alignment.
The invention also provides a visual analysis system which is simple to operate and high in feedback speed, and the visual analysis method for the control strategy of the coal-fired power plant comprises the following steps:
the view filtering module is used for filtering and analyzing historical operating data according to the abnormal events and outputting the time intervals of the abnormal events;
the detail view module is used for carrying out aggregation operation according to the time interval output by the filter view module and the historical operating data and outputting control strategy information in the time interval;
the graph view module analyzes and feeds back the propagation mode of the control strategy on the space according to the obtained control strategy information;
the strategy view module is used for drawing time cascade corresponding to the control strategy according to the obtained control strategy information;
and the algorithm module calculates and outputs specific control strategy, propagation information and time cascade information according to the interaction information and the operation data of the four modules.
Preferably, the analysis and filtering of the view filtering module is based on a time-lag perception control strategy extraction method, and the control strategy extraction method comprises forward query and backward query.
Preferably, the forward query uses a longest common subsequence algorithm to divide the abnormal events in the time interval into a plurality of ascending and descending events, and performs fuzzy matching according to preset conditions.
Specifically, the forward query specifically includes the following steps:
step 4, slave matrix M S Middle fetch sum matrix M T The row in which the common sensor is located is M A Let M stand A And M T The rows are the same, and then each column of the two matrixes is combined according to the rows to obtain two sequences A and T;
step 5, a longest common subsequence matching algorithm is used for the sequences A and T, F (i, j) represents the length of the longest common subsequence in the first i item of A and the first j item of T, and the dynamic planning transfer equation is as follows:
preferably, the backward query carries out extended retrieval according to the key sensor which feeds back the abnormal event in the time interval.
Specifically, the backward query specifically includes the following steps:
and 3, shifting the time sequence of all the sensors Q to be distributed backward by t time steps, and calculating a Pearson coefficient c in a specified time zone for each t sensor Q to be distributed and the first sensor P in 1-15 minutes:
step 4, if the pearson coefficient c is larger than 0.8, determining that the correlation exists, adding the sensor Q to be distributed into the search queue L, and increasing T for the time T;
and 5, if the search queue L is an empty set or the time T exceeds 2 hours, terminating the search, and otherwise, returning to the step 2 for continuation.
Compared with the prior art, the invention has the beneficial effects that:
the method allows a user to specify an inquiry control strategy, provides an algorithm for automatically matching and excavating the control strategy, supports the spatial propagation mode and influence time lag analysis of the control strategy, does not limit the model and the operating condition of the coal-fired power plant, displays the analysis result of the control strategy by proper visualization from multiple levels and angles, and allows the user to interactively gradually explore and finally verify the reliability of the control strategy.
Drawings
FIG. 1 is a schematic diagram of a visual analysis method for a control strategy of a coal-fired power plant according to the present invention;
FIG. 2 is a schematic diagram of a visual analysis system for a control strategy of a coal-fired power plant according to the present embodiment;
FIG. 3 is a schematic diagram of a filtered view module provided in this embodiment;
FIG. 4 is a schematic diagram of a map view module provided in this embodiment;
fig. 5 is a schematic diagram of a policy view module provided in this embodiment;
FIG. 6 is a schematic diagram of a detail view module provided in the present embodiment;
FIG. 7 is a diagram illustrating forward query provided by the present embodiment;
fig. 8 is a flowchart of backward query provided in this embodiment.
Detailed Description
As shown in fig. 1, a visual analysis method for a coal-fired power plant control strategy includes:
and 3, importing the equipment data, the sensor position data and the control strategy information into a pre-constructed visual model, carrying out graphic drawing on the imported data and information in the visual model, carrying out interactive operation on the data in the graphic, and then outputting and displaying the data.
The invention also provides a visualized analysis system for the control strategy of the coal-fired power plant, which comprises the following components:
the detail view module is used for carrying out aggregation operation according to the time interval output by the filter view module and the historical operating data and outputting control strategy information in the time interval;
the graph view module analyzes and feeds back the propagation mode of the control strategy on the space according to the obtained control strategy information;
the strategy view module is used for drawing time cascade corresponding to the control strategy according to the obtained control strategy information;
and the visualization module is used for graphically drawing the data and the information output by the system and outputting visualized image information for analyzing the coal-fired power plant control strategy problem.
To better illustrate the technical effects of the present invention, the analysis is performed with the actual operation data of a coal-fired power plant having 203 sensors, 158 control sensors and 45 status sensors. The first derivative threshold is set to 80% of the maximum absolute value.
As shown in fig. 2, an incomplete control strategy is specified. The furnace was observed from historical data to have unbalanced combustion, with the temperature on the right side higher than the left side, and the water reducing valve on the right side should be adjusted in order to reduce the detrimental effects of unbalanced combustion.
However, the subsequent impact of such adjustments and the time delay to propagate to the efficiency of the power generation are not yet clear, and therefore this control strategy is specified at the input panel of the filtered view, as shown. After the ranking panel displays the matching results, the results are selected for further analysis because the matching score of the first result is the highest and the power generation efficiency has a significant change in the time interval.
The exploration control strategy affects the propagation over space: to see the relationship between the sensors more clearly, a relationship mode is selected. Click on the highlighted sensor in the desuperheated water to analyze the propagation link of the effect. The effect can be observed to propagate from the desuperheated water to the superheater to the fly ash carbon content and finally to the power generation efficiency. Wherein, the desuperheater and the superheater, the carbon content of the fly ash and the power generation efficiency are all in negative correlation relationship.
Exploration control strategy influences the cascade relation in time: first, the histograms are aligned according to the time delay, observing the cascading effect of the control strategy and the time delay. After the unbalanced combustion occurred for 1 minute, the temperature-reduced water on the right side was adjusted; after 5 minutes, the temperature of the superheater is reduced; and finally, the power generation efficiency is improved. Based on the above observations and domain knowledge, it can be concluded that adjusting the right side desuperheating water can avoid the diffusion of the harmful effects of unbalanced combustion;
the control strategy is then compiled to understand the cause of the unbalanced combustion. And (4) unfolding the temperature node of the hearth forward to obtain a complete control strategy. It has been found that multiple dampers are cooperatively up-regulated prior to unbalanced combustion, which may be the cause of unbalanced combustion.
Check and verify the conclusion: the detail view is checked for detail information of the relevant sensor. The temperature difference between the left side and the right side of the hearth level 1 and the hearth level 2 is checked, the temperature of the left side is subtracted from the temperature of the right side, and the conditions that the temperature of the right side is obviously higher and the unbalanced combustion phenomenon is obvious can be seen. The aggregate characteristics of the coordinated adjustments can then be seen looking at the data integration of the coordinated adjustment dampers. It can be concluded that the damper adjustment results in unbalanced combustion.
Finally, the control strategy is led into a filtering view, and the support value can be seen to reach over 75 percent, so that the negative effect caused by unbalanced combustion can be effectively reduced by timely adjusting the temperature-reducing water valve.
As shown in FIG. 3, for the output of the individual filter view modules: the system is used for displaying the historical state of the coal-fired power plant and helping to determine a time interval with an abnormality, or assisting in inquiring and extracting a control strategy, and filtering to obtain the time interval with a specific control strategy; the filtered view designs a line graph for the forward analysis task, an input panel and a sequencing panel for the backward analysis task.
The input panel adopts a multi-column view, and the control strategy of the input part is assisted. Wherein the specially designed event icons include important detail attributes (event trend, sensor type, sensor phase, action or state), icons in the same column mean that events occur simultaneously, and different columns mean that events occur sequentially.
The sorting panel is divided into a list mode and a grouping mode, and the list mode is defaulted. After the expert inputs the appointed incomplete control strategy, the system can extract all matched complete control strategies and display the complete control strategies in a list mode for the expert to check and select.
Wherein each row represents a control strategy, the pie chart shows matching scores, and all control strategies are sorted from high to low according to the scores; each column corresponds to a sensor event group of the input panel, showing the matching of the sensor event group, and the bluish bar chart encodes the matching proportion of the group; the rectangle colored square specifically shows which events match successfully. The grouping mode can show an overview of the matching condition of the input control strategy and is mainly applied to the final verification stage of the system use flow;
the far left end shows the number of in-group control strategies, the rectangular colored square still corresponds to the sensor event of the input panel, and the transparency encodes the proportion of the in-group control strategies that match the event.
In addition, the support between sensor event groups is marked on the connection chain between columns, and can reflect the credibility between event groups.
The line graph shows the time series of key sensors. Key sensors have power generation efficiency, pollution (NOx emissions) and safety (furnace pressure), switching sensors by the top right option. The expert may view the data details by zooming and dragging, and select the abnormal time interval by swiping.
As shown in fig. 4, the output content of the individual view module is: a propagation mode used for reflecting the influence of the control strategy on the space, and having a context-oriented mode and a relation-oriented mode; the context guidance mode is used for displaying workflow information and actual spatial layout, and the relationship guidance mode is used for simplifying presentation association conditions;
the relationship guide mode adopts the existing multi-level force guide graph layout algorithm, and the closer the distance is, the greater the relevance of the sensor is. To reduce the time complexity, the method computes the layout for the hierarchy. The layout algorithm first calculates the positions of the force directing graphs for all the units, then calculates the position of the sensor in each unit, and finally calculates the convex hull according to the unit outer tangent line belonging to the same component.
The contextual model uses a simplified coal power plant floor plan structure diagram because when the user is interested in the actual location of the units and the workflow information, the abstract node connection diagram is difficult to understand and the user is very familiar with the workflow structure.
As shown in fig. 5, for the output content of the individual policy view module: the time cascade is used for describing the time cascade influenced by the control strategy, and the topological structure and the time lag alignment time sequence of the control strategy are visualized.
The topological structure visualization adopts a design based on a node connection diagram, each node represents one sensor and corresponds to time information on the right side one by one, and the two nodes are connected to represent that influence propagation exists between the two sensors.
The higher the node, the greater the time delay, the effect propagates from the upper sensor to the lower connected sensor, where the thickness of the link also encodes the magnitude of the correlation.
The time-lag alignment time sequence visualization adopts a design based on a histogram, each row of the histogram corresponds to time sequence data of one sensor, and in order to highlight the data change trend, the column height and the color transparency encode data values.
Common time sequence visualization comprises a line graph, an area graph and the like, a bar graph is rarely used, and the design has the advantages that each bar graph corresponds to data of one time step, and time delay can be seen clearly.
In addition, the sensors are sorted from top to bottom according to the time delay from large to small, the sensors with the same delay are divided into a group, and the specific delay value is marked at the lower left of each group.
The view also provides an alignment function, the sensor data are aligned according to time delay, the data change intervals can be seen to be concentrated into a column in the vertical direction, and the influence of influence propagation on the data trend can be seen more clearly.
To intelligently analyze control strategies, the strategy view module adds interactions (e.g., extensions, insertions, deletions) for editing and mining control strategies in depth.
Since coal-fired power plants are complex systems with many control strategies operating simultaneously, occasional missed analysis results may also occur, e.g., sensor impact relationships that may be lost during longer time delays.
Therefore, the system provides an editing mode to help the expert to correct the control strategy, three types of interaction of insertion, expansion and deletion are supported, and the expert can click an interaction button to edit. Wherein the insertion is used to insert a new sensor between two connected sensors; the expansion is used for expanding the control strategy and searching more associated sensors forwards; sensors for removing extraneous or erroneous sensors are deleted.
As shown in FIG. 6, for the output of the individual detail view modules: for searching sensors and performing aggregation operations (e.g., averaging, summing, differencing) to more deeply understand the control strategy from the raw data.
The structure diagram on the left side shows the spatial position of the part to which the sensor belongs, and the area diagram on the right side shows a specific time sequence.
The left and right endpoints of the area map are aligned with the histogram of the strategy view, and if the strategy view chooses to align the time series with a time delay, the time series of the sensors appearing in the strategy view will also be aligned with a time delay in the detail view.
As shown in fig. 7, for a forward query, where the input is a known but incomplete control strategy, represented as a time-ordered sequence of sensor events, the model needs to find all the control strategies and their subsequent effects that can be fuzzy matched to it; the algorithm firstly divides the time sequence into a plurality of ascending and descending events, aligns the events one by one, and then carries out fuzzy matching according to specified conditions to finally obtain a query result. Here fuzzy matching uses the existing longest common subsequence algorithm.
The specific process of forward query is as follows:
1-1, discretizing all historical operation data into trend intervals, namely an ascending interval, a descending interval and a stable interval;
step 1-2, all the intervals are cut and aligned, so that the historical operation data can be expressed as a matrix M S Wherein each row represents a sensor, each column represents a time interval, the values in the matrix indicate a specific trend of the sensor in this time interval, 0 represents plateau, 1 represents fall, 2 represents rise;
step 1-3, recording the control strategy of forward query as a similar matrix M T I.e. each row represents the sensors involved in the target control strategy, each column represents the expected occurring trend changes;
step 1-4, slave matrix M S Middle fetch sum matrix M T The row in which the common sensor is located is M A Let M stand A And M T The rows are the same, and then each column of the two matrixes is respectively merged according to the rows to obtain two sequences A and T;
1-5, using a longest common subsequence matching algorithm for the sequences A and T, wherein F (i, j) represents the length of the longest common subsequence in the first i item of A and the first j item of T, and the dynamic programming transfer equation is as follows:
as shown in fig. 8, for backward query, a time interval including an abnormality, in which the input is a key sensor, needs to be expanded forward from the key sensor to find a sensor event associated with the abnormality, and obtains a complete control strategy causing the abnormality.
The backward query is divided into five steps:
step 2-1, adding a specified key sensor to a search queue L, and setting T as 0;
step 2-2, acquiring a first sensor P in the queue;
step 2-3, for each sensor Q, shifting the time series of Q backwards by t time steps, calculating for each t in the range of 1 to 15 minutes the pearson coefficient c for P and Q in the specified time interval:
wherein M represents a time-series length, X i Indicating the length of the time series for the first sensor P in the ith queue,
representing the average of the lengths of the time series, Y, of the first sensor P in all queues i+t Indicating the length of the time series for the i + t-th sensor,
represents the time series length average of all sensors;
step 2-4, if the Pearson coefficient c exceeds 0.8, considering that P and Q have relevance, adding Q to a search queue L, and increasing T;
and 2-5, if the search queue L is empty or T exceeds 2 hours, terminating the search, otherwise, returning to the step 2 for continuation.
The complexity of this algorithm is O (N) 2 M), N is the number of sensors, and M is the time series length.
Claims (8)
1. A visual analysis method for a control strategy of a coal-fired power plant, comprising:
step 1, obtaining historical operation data of a coal-fired power plant, wherein the historical operation data comprises equipment data acquired by a sensor and corresponding sensor position data;
step 2, analyzing equipment data in a preset time interval on the basis of the sensor position data to acquire control strategy information in the time interval;
and 3, importing the equipment data, the sensor position data and the control strategy information into a pre-constructed visual model, carrying out graphic drawing on the imported data and information in the visual model, carrying out interactive operation on the data in the graphic, and then outputting and displaying the data.
2. The visual analysis method for a coal fired power plant control strategy according to claim 1, characterized in that the equipment data comprises operational status data and control instruction data of the equipment.
3. The visual analysis method for the control strategy of a coal-fired power plant according to claim 1, characterized in that the time interval is a range time for selecting the power generation efficiency, the negative pressure parameter of the furnace, or the sudden change of the pollutant emission.
4. The visual analysis method for the control strategy of the coal-fired power plant according to claim 1, wherein the analysis in the step 2 adopts an aggregation operation method to analyze the spatial position of the sensors, the correlation degree between adjacent sensors, and the relationship between the data change of the sensors and the time series.
5. A visual analysis system for a control strategy of a coal-fired power plant based on the visual analysis method for the control strategy of the coal-fired power plant of any one of claims 1 to 4, comprising:
the view filtering module is used for filtering and analyzing historical operating data according to the abnormal events and outputting the time intervals of the abnormal events;
the detail view module is used for carrying out aggregation operation according to the time interval output by the filter view module and the historical operating data and outputting control strategy information in the time interval;
the graph view module is used for outputting a propagation mode of the control strategy on the space according to the obtained control strategy information;
the strategy view module is used for outputting time cascade corresponding to the control strategy according to the obtained control strategy information;
and the algorithm module is used for graphically drawing the output results of the filtering view module, the detail view module, the graph view module and the strategy view module and outputting visual image information for analyzing the control strategy problem of the coal-fired power plant.
6. The visual analysis system for coal-fired power plant control strategies according to claim 5, characterized in that the analysis of the filter view module filters time-lag perception based control strategy extraction methods including forward and backward queries.
7. The visual analysis system for the control strategy of the coal-fired power plant according to claim 6, wherein the forward query employs a longest common subsequence algorithm to divide the abnormal events in the time interval into a plurality of ascending and descending events, and performs fuzzy matching according to preset conditions.
8. The visual analytics system for coal-fired power plant control strategies as claimed in claim 6, wherein the backward queries conduct an extended search based on key sensors that feed back abnormal events over a time interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210984645.8A CN115390448A (en) | 2022-08-17 | 2022-08-17 | Visual analysis method and system for control strategy of coal-fired power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210984645.8A CN115390448A (en) | 2022-08-17 | 2022-08-17 | Visual analysis method and system for control strategy of coal-fired power plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115390448A true CN115390448A (en) | 2022-11-25 |
Family
ID=84120358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210984645.8A Pending CN115390448A (en) | 2022-08-17 | 2022-08-17 | Visual analysis method and system for control strategy of coal-fired power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115390448A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116360352A (en) * | 2022-12-02 | 2023-06-30 | 山东和信智能科技有限公司 | Intelligent control method and system for power plant |
-
2022
- 2022-08-17 CN CN202210984645.8A patent/CN115390448A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116360352A (en) * | 2022-12-02 | 2023-06-30 | 山东和信智能科技有限公司 | Intelligent control method and system for power plant |
| CN116360352B (en) * | 2022-12-02 | 2024-04-02 | 山东和信智能科技有限公司 | Intelligent control method and system for power plant |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112987666B (en) | Power plant unit operation optimization regulation and control method and system | |
| US20090125155A1 (en) | Method and System for Optimizing Industrial Furnaces (Boilers) through the Application of Recursive Partitioning (Decision Tree) and Similar Algorithms Applied to Historical Operational and Performance Data | |
| CN106101121B (en) | A kind of all-network flow abnormity abstracting method | |
| CN110135716B (en) | Power grid infrastructure project dynamic early warning identification method and system | |
| Khademolqorani et al. | An adjusted decision support system through data mining and multiple criteria decision making | |
| Billari et al. | Timing, sequencing, and quantum of life course events: A machine learning approach | |
| CN110222416B (en) | Industrial steam amount prediction method based on big data | |
| CN113515049A (en) | Operation regulation and control system and method for gas-steam combined cycle generator set | |
| CN111340063A (en) | Coal mill data anomaly detection method | |
| CN107885857B (en) | A kind of search results pages user's behavior pattern mining method, apparatus and system | |
| CN115390448A (en) | Visual analysis method and system for control strategy of coal-fired power plant | |
| CN117194919A (en) | Production data analysis system | |
| CN117787743A (en) | Blast furnace condition intelligent evaluation method and system based on big data | |
| Liu et al. | ECoalVis: visual analysis of control strategies in coal-fired power plants | |
| JP5097019B2 (en) | Production planning system and method | |
| CN111967003B (en) | Automatic wind control rule generation system and method based on black box model and decision tree | |
| CN117575339A (en) | Intelligent carbon reduction evaluation optimization method and system for park | |
| CN112633561A (en) | Production risk intelligent prediction early warning method based on industrial big data | |
| CN110135740A (en) | Real time knowledge towards coal-burning boiler flow object finds method and system | |
| Zhou et al. | Study on Optimization of Data-Driven Anomaly Detection | |
| CN113177040A (en) | Full-process big data cleaning and analyzing method for aluminum/copper plate strip production | |
| CN114154849A (en) | Operation guidance system and method based on data mining analysis | |
| CN113505850A (en) | Boiler fault prediction method based on deep learning | |
| Duan et al. | Data mining technology for structural health monitoring | |
| CN117875726B (en) | Value chain optimization management and control method based on deep learning |
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 |