CN117951601B - Boiler low-load stable combustion monitoring method and device applied to deep peak shaving - Google Patents

Boiler low-load stable combustion monitoring method and device applied to deep peak shaving Download PDF

Info

Publication number
CN117951601B
CN117951601B CN202410137005.2A CN202410137005A CN117951601B CN 117951601 B CN117951601 B CN 117951601B CN 202410137005 A CN202410137005 A CN 202410137005A CN 117951601 B CN117951601 B CN 117951601B
Authority
CN
China
Prior art keywords
boiler unit
power generation
boiler
generation load
load
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.)
Active
Application number
CN202410137005.2A
Other languages
Chinese (zh)
Other versions
CN117951601A (en
Inventor
罗必雄
倪煜
李德波
杨卧龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Power Engineering Consulting Group Corp
Original Assignee
China Power Engineering Consulting Group Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Power Engineering Consulting Group Corp filed Critical China Power Engineering Consulting Group Corp
Priority to CN202410137005.2A priority Critical patent/CN117951601B/en
Publication of CN117951601A publication Critical patent/CN117951601A/en
Application granted granted Critical
Publication of CN117951601B publication Critical patent/CN117951601B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Primary Health Care (AREA)
  • Probability & Statistics with Applications (AREA)
  • Regulation And Control Of Combustion (AREA)

Abstract

The invention relates to the technical field of boiler steady combustion monitoring, in particular to a method and a device for monitoring low-load steady combustion of a boiler, which are applied to deep peak shaving, and can dynamically adjust a monitoring strategy according to real-time operating conditions, so that the monitoring efficiency of a thermal power unit in a low-load steady combustion state under the deep peak shaving condition is improved; the method comprises the following steps: acquiring planned response power generation load of the monitored boiler unit participating in deep peak shaving, real-time power generation load of the boiler unit and the lowest design power generation load of the boiler unit; calculating to obtain peak regulation response evaluation indexes of the boiler unit according to the planned response power generation load, the real-time power generation load and the lowest design power generation load; setting operation data acquisition frequency and operation data monitoring time windows of the boiler unit in the deep peak regulation process, wherein each operation data monitoring time window comprises a plurality of operation data acquisition time nodes; and acquiring combustion data information of the boiler unit according to the set operation data acquisition frequency.

Description

Boiler low-load stable combustion monitoring method and device applied to deep peak shaving
Technical Field
The invention relates to the technical field of boiler stable combustion monitoring, in particular to a boiler low-load stable combustion monitoring method and device applied to deep peak shaving.
Background
In an electric power system, deep peak shaving refers to the requirement of improving the capacity of renewable energy sources and guaranteeing the power supply stability in order to cope with the peak-valley difference of the load of a power grid, and a thermal power unit needs to have the capacity of efficient and stable operation under a low-load working condition. However, boilers often suffer from unstable combustion under low load conditions, such as flame extinction, incomplete combustion, etc., which not only affect thermal efficiency, but also result in increased pollutant emissions and increased risk of equipment damage. Therefore, the low-load running state of the boiler needs to be monitored in real time.
The existing monitoring method is mainly based on fixed monitoring data acquisition frequency, and the acquisition frequency of the monitoring data is difficult to dynamically adjust according to the power generation load of the boiler unit responding to peak shaving and the lowest design power generation load of the boiler unit. The fixed monitoring data acquisition frequency is difficult to capture the fine fluctuation of the combustion state in time, so that effective monitoring of the key stable combustion parameters is missed.
Therefore, a method for monitoring low-load stable combustion of a boiler applied to deep peak shaving is needed to solve the above problems.
Disclosure of Invention
In order to solve the technical problems, the invention provides the boiler low-load steady combustion monitoring method which can dynamically adjust the monitoring strategy according to real-time operation conditions and improve the monitoring efficiency of the low-load steady combustion state of the thermal power generating unit under the deep peak regulation condition.
In a first aspect, the present invention provides a method for monitoring boiler low load stable combustion applied to deep peak shaving, the method comprising:
Acquiring planned response power generation load of the monitored boiler unit participating in deep peak shaving, real-time power generation load of the boiler unit and the lowest design power generation load of the boiler unit;
Calculating to obtain peak regulation response evaluation indexes of the boiler unit according to the planned response power generation load, the real-time power generation load and the lowest design power generation load;
Setting operation data acquisition frequency and operation data monitoring time windows of the boiler unit in the deep peak shaving process based on peak shaving response evaluation indexes, wherein each operation data monitoring time window comprises a plurality of operation data acquisition time nodes;
Collecting combustion data information of the boiler unit according to the set operation data collection frequency; the boiler unit combustion data information comprises smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters;
Converting collected smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters into a boiler unit operation feature matrix according to operation data acquisition frequency and an operation data monitoring time window; in the operation characteristic matrix of the boiler unit, the same type of combustion data is positioned in the same column, and different types of combustion data under the same acquisition time node are positioned in the same row, wherein the operation characteristic matrix of the boiler unit comprises a plurality of operation data acquisition time nodes in the operation data monitoring time window;
Inputting the operation characteristic matrix of the boiler unit into a pre-constructed stable combustion monitoring and evaluating model of the boiler unit to obtain a stable combustion evaluating index of the boiler unit;
Comparing the stable combustion evaluation index of the boiler unit with a preset stable combustion evaluation threshold of the boiler unit, and prompting abnormal operation of the boiler unit to an operation maintenance person if the stable combustion evaluation index of the boiler unit is lower than the stable combustion evaluation threshold of the boiler unit; if the stable combustion evaluation index of the boiler unit is not lower than the stable combustion evaluation threshold of the boiler unit, the set operation data acquisition frequency is kept for data acquisition and monitoring. .
On the other hand, the application also provides a boiler low-load stable combustion monitoring device applied to deep peak shaving, which comprises:
The load information acquisition module is used for acquiring the planned response power generation load of the monitored boiler unit in the deep peak shaving period, the real-time power generation load in actual operation and the lowest design power generation load of the unit in real time;
The peak regulation response evaluation calculation module is used for comprehensively analyzing and calculating a peak regulation response evaluation index of the boiler unit according to the acquired planned response power generation load, real-time power generation load and minimum design power generation load data;
The dynamic monitoring strategy setting module is used for setting the operation data acquisition frequency and the data monitoring time window of the boiler unit in the deep peak shaving stage according to the obtained peak shaving response evaluation index, and ensuring that each monitoring time window comprises a plurality of operation data acquisition time nodes;
the combustion data acquisition module is used for acquiring combustion data information of the boiler unit on each time node according to the set operation data acquisition frequency, wherein the combustion data information of the boiler unit comprises smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters;
The data characteristic conversion module is used for converting the acquired combustion data information of the boiler unit into a boiler unit operation characteristic matrix according to the operation data acquisition frequency and the operation data monitoring time window;
The stable combustion monitoring and evaluating module is used for inputting the operation characteristic matrix of the boiler unit into a prestored stable combustion monitoring and evaluating model of the boiler unit to obtain a stable combustion evaluation index of the boiler unit in an operation data monitoring time window;
The running state early warning module is used for comparing the stable combustion evaluation index of the boiler unit with a preset stable combustion evaluation threshold value of the boiler unit: if the stable combustion evaluation index of the boiler unit is lower than the stable combustion evaluation threshold of the boiler unit, prompting abnormal operation of the boiler unit to an operation and maintenance person; if the stable combustion evaluation index of the boiler unit is not lower than the stable combustion evaluation threshold of the boiler unit, the set operation data acquisition frequency is kept for data acquisition and monitoring.
In a third aspect, the present application provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, the computer program when executed by the processor implementing the steps of any of the methods described above.
In a fourth aspect, the application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
Compared with the prior art, the invention has the beneficial effects that:
The data acquisition frequency and the monitoring time window can be flexibly set according to the actual operation conditions by acquiring and analyzing the planned response power generation load, the real-time power generation load and the lowest design power generation load of the boiler unit and calculating the peak regulation response evaluation index; the method can timely capture the change of the combustion state, and especially when the low-load fluctuation is large, the sensitivity and the accuracy of monitoring the key stable combustion parameters can be improved; the method not only focuses on a single parameter, but also comprehensively collects various combustion data information including smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters to form a boiler unit operation characteristic matrix, so that the stable combustion condition of the boiler can be more comprehensively estimated from multiple angles;
Converting the operation characteristic matrix into a stable combustion evaluation index of the boiler unit by using a pre-constructed stable combustion monitoring evaluation model, and comparing the stable combustion evaluation index with a preset threshold; when the stable combustion evaluation index is lower than the threshold value, abnormal prompts can be sent to operation and maintenance personnel rapidly to guide the operation and maintenance personnel to take measures in time to optimize the combustion process or avoid potential faults; on the contrary, under the condition of good stable combustion state, a given data acquisition strategy is maintained, so that resource waste is avoided; through the fine monitoring and intelligent evaluation of the combustion process, the thermal power generating unit is helped to realize efficient and stable combustion in a wide load range, so that the thermal efficiency loss is effectively reduced, the pollutant emission is reduced, the safe operation of equipment is ensured, and the overall operation flexibility and economy of the power system are improved;
in summary, the method breaks through the limitation of the traditional fixed frequency monitoring mode, realizes the dynamic adjustment of the monitoring strategy according to the real-time operation condition, improves the monitoring efficiency of the low-load stable combustion state of the thermal power unit under the deep peak regulation condition, and provides powerful technical support for the stable operation of the power system.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for monitoring boiler low load steady combustion applied to deep peak shaving according to an embodiment of the present invention;
FIG. 2 is a hardware architecture diagram of an electronic device according to an embodiment of the present invention;
FIG. 3 is a block diagram of a boiler low-load stable combustion monitoring device applied to deep peak shaving according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort based on the embodiments of the present invention are within the scope of protection of the present invention.
Referring to fig. 1, an embodiment of the present invention provides a method for monitoring boiler low-load stable combustion applied to deep peak shaving, the method comprising:
S1, acquiring planned response power generation load of a monitored boiler unit participating in deep peak shaving, real-time power generation load of the boiler unit and the lowest design power generation load of the boiler unit;
S2, calculating to obtain peak regulation response evaluation indexes of the boiler unit according to the planned response power generation load, the real-time power generation load and the lowest design power generation load;
Step S3, setting operation data acquisition frequency and operation data monitoring time windows of the boiler unit in the deep peak shaving process based on peak shaving response evaluation indexes, wherein each operation data monitoring time window comprises a plurality of operation data acquisition time nodes;
S4, acquiring combustion data information of the boiler unit according to the set operation data acquisition frequency; the boiler unit combustion data information comprises smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters;
S5, converting collected smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters into a boiler unit operation feature matrix according to operation data acquisition frequency and an operation data monitoring time window; in the operation characteristic matrix of the boiler unit, the same type of combustion data is positioned in the same column, and different types of combustion data under the same acquisition time node are positioned in the same row, wherein the operation characteristic matrix of the boiler unit comprises a plurality of operation data acquisition time nodes in the operation data monitoring time window;
S6, inputting the operation characteristic matrix of the boiler unit into a pre-constructed stable combustion monitoring and evaluating model of the boiler unit to obtain a stable combustion evaluating index of the boiler unit;
S7, comparing the stable combustion evaluation index of the boiler unit with a preset stable combustion evaluation threshold of the boiler unit, and prompting abnormal operation of the boiler unit to an operation and maintenance personnel if the stable combustion evaluation index of the boiler unit is lower than the stable combustion evaluation threshold of the boiler unit; if the stable combustion evaluation index of the boiler unit is not lower than the stable combustion evaluation threshold of the boiler unit, the set operation data acquisition frequency is kept for data acquisition and monitoring.
In the embodiment, the data acquisition frequency and the monitoring time window can be flexibly set according to the actual operation conditions by acquiring and analyzing the planned response power generation load, the real-time power generation load and the lowest design power generation load of the boiler unit and calculating the peak regulation response evaluation index; the method can timely capture the change of the combustion state, and especially when the low-load fluctuation is large, the sensitivity and the accuracy of monitoring the key stable combustion parameters can be improved; the method not only focuses on a single parameter, but also comprehensively collects various combustion data information including smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters to form a boiler unit operation characteristic matrix, so that the stable combustion condition of the boiler can be more comprehensively estimated from multiple angles; converting the operation characteristic matrix into a stable combustion evaluation index of the boiler unit by using a pre-constructed stable combustion monitoring evaluation model, and comparing the stable combustion evaluation index with a preset threshold; when the stable combustion evaluation index is lower than the threshold value, abnormal prompts can be sent to operation and maintenance personnel rapidly to guide the operation and maintenance personnel to take measures in time to optimize the combustion process or avoid potential faults; on the contrary, under the condition of good stable combustion state, a given data acquisition strategy is maintained, so that resource waste is avoided; through the fine monitoring and intelligent evaluation of the combustion process, the thermal power generating unit is helped to realize efficient and stable combustion in a wide load range, so that the thermal efficiency loss is effectively reduced, the pollutant emission is reduced, the safe operation of equipment is ensured, and the overall operation flexibility and economy of the power system are improved; in summary, the method breaks through the limitation of the traditional fixed frequency monitoring mode, realizes the dynamic adjustment of the monitoring strategy according to the real-time operation condition, improves the monitoring efficiency of the low-load stable combustion state of the thermal power unit under the deep peak regulation condition, and provides powerful technical support for the stable operation of the power system.
The manner in which the individual steps shown in fig. 1 are performed is described below.
For step S1:
Step S1, acquiring planned response power generation load of a monitored boiler unit participating in deep peak shaving, real-time power generation load of the boiler unit and the lowest design power generation load of the boiler unit; the purpose of the step is to determine the power generation load condition of the boiler in the deep peak shaving process, so that stable combustion monitoring is better carried out; specifically, step S1 includes the following key aspects:
planning the response power generation load: the planned response power generation load is the power generation load required to be responded by the boiler unit in the deep peak shaving plan; the planning of the plan may involve factors such as power grid load prediction, renewable energy consumption plan and the like; in general, an operator of a power system or a power plant can make a deep peak shaving plan in advance, and a unit which needs to participate in deep peak shaving and a response power generation load thereof are determined;
Real-time power generation load: the current real-time power generation load of the boiler unit is obtained by monitoring the state of the power system and the running condition of the boiler in real time; this can be achieved by real-time acquisition of data by power system monitoring equipment, sensors, etc.; the real-time power generation load is dynamically changed, so that the real-time power generation load needs to be updated in real time to reflect the current running state;
minimum design power generation load: the lowest design power generation load of the boiler unit refers to the lowest power generation load level of the unit which can stably run during design; this is a basic design parameter, typically determined by the boiler manufacturer or designer at the design stage; when the unit is operated under low load, the power generation load is required to be ensured not to be lower than the minimum design power generation load so as to ensure stable operation and combustion efficiency.
In actual operation, the information can be obtained through real-time communication with power system dispatching, operation and maintenance personnel and boiler equipment; the system relates to a monitoring and scheduling system of the power system, real-time acquisition and transmission of sensor data and a control system of the boiler unit; through the information acquisition, the system can know the participation condition of the boiler in the deep peak shaving plan, and basic data is provided for subsequent stable combustion monitoring.
For step S2:
In step S2, calculating to obtain peak shaving response evaluation indexes of the boiler unit according to the planned response power generation load, the real-time power generation load and the lowest design power generation load; the step aims at evaluating the performance of the boiler unit in the deep peak shaving process and provides basis for the follow-up monitoring strategy and the early warning mechanism; calculating a peak shaving response evaluation index of the boiler unit based on the data obtained in the step S1; the index can comprehensively reflect the performance of the boiler unit in the deep peak shaving process, including the response speed and stability of the power generation load, the realization condition of the lowest design power generation load and the like; the specific calculation formula is as follows:
Wherein K r represents a peak shaver response evaluation index, P r represents a planned response power generation load of the boiler unit participating in deep peak shaver, P t represents a real-time power generation load of the boiler unit, and P min represents a minimum design power generation load of the boiler unit.
In the step, the load adjustment capability and the stable combustion performance of the boiler unit in the deep peak shaving process can be dynamically evaluated according to the actual operation condition by calculating the peak shaving response evaluation index; compared with a mode of fixed monitoring frequency, the real-time evaluation mechanism based on the load data change is more flexible and accurate; the peak regulation response evaluation index comprehensively plans three key parameters of response power generation load, real-time power generation load and minimum design power generation load;
wherein, the first part of the formula: The method is used for measuring whether the current load is in a safe and effectively controllable range, and if the current load is 1, the planned response power generation load is higher than the lowest design power generation load; if the value is-1, the planned response power generation load is lower than the lowest design power generation load, and the risk of unstable combustion possibly exists;
Second, second part: the log |P r-Pt | is used for quantifying the difference between the planned response power generation load and the real-time power generation load, so that the evaluation index value when the difference between the two loads is large can be effectively amplified, the capturing capability of the fine fluctuation of the combustion state is enhanced, and the potential stable combustion problem can be found and solved in time; the calculation result of the peak regulation response evaluation index directly influences the subsequent data acquisition strategy, so that the key information reflecting the stable combustion condition of the boiler can be collected in a more efficient manner at key moments, and a basis is provided for optimizing operation control; the design of the step S2 fully reflects the requirement of real-time monitoring of the steady combustion state of the thermal power generating unit in the deep peak regulation state, realizes the fine management of the running state of the boiler through the integrated analysis of various important parameters, and establishes a more scientific and reasonable data acquisition strategy based on the fine management.
For step S3:
step S3 designs a method for intelligently and dynamically adjusting the operation data acquisition frequency and monitoring time window on the basis of the peak shaving response evaluation index calculated in step S2, and the specific implementation mode is as follows:
When the peak shaving response evaluation index is a positive number, the unit is subjected to deep peak shaving and still operates in a safe and stable design load range; at this time, the data acquisition frequency can be moderately adjusted according to the specific value of the peak shaving response evaluation index, for example, the higher the index value is, the larger the peak shaving span is, and the acquisition frequency does not need to be greatly increased, but the acquisition times can be properly increased or the acquisition interval can be thinned, so that the change trend of the combustion state in a larger peak shaving range can be ensured to be captured; the specific acquisition frequency adjustment strategy can be determined according to actual requirements and system resources; for example, when the index is between 0 and 10, the acquisition frequency may be set to acquire once every 10 minutes; when the index is higher than 10, the acquisition frequency may be set to acquire once every 5 minutes; such a setting can not only meet the real-time monitoring requirements, but also avoid excessive data acquisition and processing burden.
When the peak shaving response evaluation index is negative, the current planned response power generation load is lower than the lowest design power generation load of the boiler unit, which may cause problems of unstable combustion, reduced thermal efficiency, increased pollutant emission and the like; in this case, the system will automatically and greatly raise the frequency of operation data acquisition to more densely acquire various key parameter information in the combustion process, including but not limited to flue gas pollutant components, steam pressure, boiler vibration frequency, furnace negative pressure, furnace temperature distribution, etc., so as to find and deal with possible stable combustion problems in time; the specific acquisition frequency boost strategy can be determined according to the magnitude of the negative value of the index; for example, when the index is below-10, the acquisition frequency may be set to acquire once every 2 minutes; when the index is between-10 and 0, the acquisition frequency can be set to acquire every 5 minutes; by improving the data acquisition frequency, the system can monitor the tiny change of the combustion state more accurately, discover potential problems in time and take corresponding measures to stabilize combustion and ensure the safety of the unit.
Setting an operation data monitoring time window according to the positive and negative values and the magnitude of the peak regulation response evaluation index; if the peak shaver response evaluation index is positive and has a larger value, which means that the peak shaver span of the boiler unit is larger, the time window can be set longer, for example, 1 hour or 2 hours; if the peak shaver response evaluation index is negative or has a small value, which means that the peak shaver span is larger, and the planned response power generation load is already lower than the lowest design power generation load of the boiler unit, the time window needs to be set shorter, for example, 10 minutes or 20 minutes; by shortening the length of the time window, the data can be analyzed more frequently and accurately, the fine fluctuation of the combustion state can be captured in time, and the real-time performance and accuracy of monitoring are improved.
Through the steps, the data acquisition frequency and the monitoring time window can be adjusted in real time according to the actual peak regulation response evaluation index of the boiler unit, so that the flexible monitoring of the combustion state change under different load working conditions is realized, the moderate monitoring requirement in the safe and stable design range is met, and the monitoring intensity can be rapidly improved under the conditions of low load and unstable combustion; the reasonable data acquisition frequency is set according to different peak-shaving response evaluation indexes, so that not only can the calculation resource waste caused by not excessively acquiring data in a normal operation state be ensured, but also the key information can be ensured to be rapidly captured when an abnormal condition occurs, and the effective utilization of the system resource is realized; when the peak regulation response evaluation index is a negative number, potential problems can be found and solved in time when the risk of unstable combustion and the like is increased by greatly improving the data acquisition frequency, the risks of equipment damage and increased pollutant emission are effectively avoided, and the response speed and the treatment efficiency of operation and maintenance personnel to abnormal conditions are improved; different operation data monitoring time window lengths are set according to peak regulation span sizes, so that finer analysis of the combustion state is facilitated, and particularly when the combustion state fluctuates severely, the variation trend of the combustion parameters can be reflected more accurately through a short time window, and therefore accuracy and reliability of monitoring results are improved.
For step S4:
Step S4, in the field of stable combustion monitoring of boilers, is based on the operation data acquisition frequency set in the step S3, and acquiring combustion data information in real time in a preset monitoring time window; the specific implementation content of the step is as follows:
S41, automatically triggering data acquisition operation in each preset monitoring time window according to the operation data acquisition frequency (such as every 5 minutes, every 10 minutes or shorter time interval) set in the step S3;
S42, detecting and recording key stable combustion parameters of the boiler unit in real time through professional sensor equipment and a data acquisition system, so as to ensure the accuracy and instantaneity of data; more specifically, the boiler unit combustion data information includes
Smoke pollutant components: the gas analyzer and other equipment are used for monitoring pollutant components in the flue gas in real time, such as sulfur dioxide, nitrogen oxides, particulate matters and the like, so that the environment friendliness of combustion can be evaluated and the emission standard can be met;
Steam pressure: measuring the steam pressure of the boiler through a steam pressure sensor to know the steam generation condition of the boiler, wherein the change of the steam pressure is related to the combustion state;
Boiler vibration frequency: monitoring the vibration frequency of the boiler by using a vibration sensor, which can reflect the running condition inside the boiler, and abnormal vibration frequency can indicate unstable combustion or other problems;
Hearth negative pressure: the negative pressure sensor is used for measuring the negative pressure condition of the boiler hearth, so that the judgment of the air flow state of combustion in the hearth is facilitated, and flame instability can be caused by abnormal negative pressure;
furnace temperature distribution characterization parameters: measuring the temperature distribution condition in the hearth by using a temperature sensor array, wherein the uneven temperature distribution can prompt combustion problems;
S43, integrating the measured values of the parameters under the same acquisition time node into a group of data, and transmitting the data to a data center or a control room in real time for further analysis and processing; this process may involve communication network technology, ensuring efficient, secure transmission of data;
And S44, continuously collecting data according to the set collection frequency in the whole depth peak regulation process, and continuously accumulating to form a detailed historical database so as to comprehensively and deeply study and optimize the low-load stable combustion state of the boiler.
The step S4 can capture the variation trend of the combustion state in time by collecting and monitoring the key stable combustion parameters of the boiler unit in real time, thereby effectively solving the problem that the traditional fixed frequency monitoring method is difficult to adapt to the low-load working condition of the boiler; meanwhile, rich operation data also provides powerful support for realizing an accurate and intelligent stable combustion monitoring and evaluating model, and further helps to improve the operation efficiency, safety and environmental protection performance of the thermal power generating unit under the deep peak regulation condition.
For step S5:
Before step S5, the operation data acquisition frequency and time window of the boiler unit are set, and next step S5 is to integrate the acquired combustion data information into a structured matrix so as to be conveniently input into a stable combustion monitoring and evaluating model of the boiler unit for analysis and evaluation; specifically, the operation of step S5 is as follows:
S51, in the step S4, combustion data information comprises smoke pollutant components, steam pressure, boiler vibration frequency, furnace negative pressure and furnace temperature distribution characterization parameters; these data are collected at a predetermined operational data collection frequency to form an original data set;
S52, preprocessing the collected original data, including but not limited to data cleaning, missing value processing, abnormal value detection and processing; the data of the input model is guaranteed to be good in quality, and subsequent feature construction is facilitated;
s53, dividing the data according to the operation data monitoring time windows, and ensuring that each time window comprises a plurality of operation data acquisition time nodes; this helps to capture changes in the operating conditions of the boiler unit at different points in time;
S54, organizing various combustion data into a matrix form according to the types of the combustion data; in the operation feature matrix of the boiler unit, the same type of combustion data is positioned in the same column, and different types of combustion data under the same acquisition time node are positioned in the same row, so that the operation feature matrix of the boiler unit is formed; such a matrix form helps the model to better understand the relationship between the data.
Through the steps, the originally scattered combustion data are organized in a matrix form, so that the structured storage and processing of the data are realized, and the computer algorithm is convenient to read, calculate and analyze quickly; the data in the same row reflects the interrelationship and state between each combustion parameter on the same acquisition time node; by observing different rows (namely different time points), the change trend of the parameters along with time can be intuitively known, and the key moment and mode of the change of the combustion state can be captured; this matrix format is well suited for input into a machine learning or statistical model for analysis; many data analysis and prediction models require that the input data have a unified structure, such as a data set in a tabular form, so that stable combustion performance evaluation and anomaly detection can be efficiently performed; the operation data acquisition frequency is dynamically set according to the peak regulation response evaluation index, so that the formed feature matrix can reflect the combustion condition in a key time period, and the reasonable utilization of system resources is facilitated on the premise of ensuring the monitoring effect, and the data redundancy and calculation burden caused by unnecessary high-frequency data acquisition are avoided; if new monitoring parameters are needed to be added or a monitoring window is needed to be adjusted in the future, only columns or rows are needed to be added in the matrix, the whole data processing flow is not needed to be changed, and the method has good expandability and compatibility.
Wherein, the boiler unit operation characteristic matrix format is:
Wherein, (C NO,CSO,CPM)n represents the nitrogen oxide concentration, the particulate matter concentration, and the sulfur oxide concentration collected at the nth operation data collection time node; Representing the steam pressure collected at the nth operational data collection time node; f n represents the boiler vibration frequency acquired at the nth operation data acquisition time node; representing the hearth negative pressure acquired at the nth operation data acquisition time node; And representing the characteristic parameters of the temperature distribution of the hearth acquired at the nth operation data acquisition time node.
More specifically, the calculation formula of the characteristic parameters of the temperature distribution of the hearth is as follows:
wherein T i represents the temperature of the ith key point in the hearth temperature distribution diagram; Representing the average temperature of all key points in the furnace temperature distribution diagram; omega represents an adjustment coefficient, which is determined according to actual application requirements and experience and is used for adjusting the sensitivity of the index;
Wherein, the smaller the K T value is, the more uniform the temperature distribution in the hearth is; otherwise, the temperature distribution is scattered or uneven; the calculation method considers the data of more temperature measuring points, and measures the discrete degree of the temperature distribution of the hearth by a statistical method, thereby providing a relatively comprehensive hearth temperature distribution evaluation index; in practical applications, appropriate modifications and optimization may also be required in combination with specific combustion process characteristics, equipment configurations, operating conditions, and the like.
For step S6:
in the step S6, the construction of a stable combustion monitoring and evaluating model of the boiler unit is one of key links of the whole monitoring method; the model aims at evaluating the stable combustion performance of the boiler unit according to the input operation characteristic matrix and provides a basis for the subsequent stable combustion evaluation index; the following specific steps of constructing a stable combustion monitoring and evaluating model of the boiler unit are as follows:
s61, a large amount of historical data needs to be collected from an actually-operated boiler system, wherein the data comprises, but is not limited to, combustion parameters (such as smoke pollutant components, steam pressure, boiler vibration frequency, furnace negative pressure, furnace temperature distribution and the like) under different loads, and corresponding boiler operation state information; before use, the data is subjected to pretreatment such as cleaning, missing value treatment, abnormal value detection, standardization and the like;
s62, selecting and extracting key features capable of effectively reflecting a low-load stable combustion state of the boiler based on a physical principle and expert experience; for example, ratios, differences, derivatives, etc. between related features may be calculated to represent dynamic trends in the combustion process;
S63, selecting a proper machine learning or data mining model, such as a support vector machine, a decision tree, a random forest, a neural network or a deep learning model, and the like according to the characteristics of the stable combustion problem of the boiler; training the selected model by utilizing the preprocessed characteristic data set, and adjusting model parameters through an optimization algorithm, so that the model can accurately fit training data and has good generalization capability;
S64, evaluating the performance of the model by using a cross verification mode, an independent test set mode and the like, and ensuring the reliability of the prediction effect of the model on unknown data; commonly used evaluation indexes may include accuracy, precision, recall, F1 score, AUC value and the like, and for stable combustion monitoring scenes, the ability of the model to recognize unstable combustion is focused on;
S65, along with accumulation of more real-time monitoring data, updating and iterating are carried out on the model regularly so as to adapt to data distribution changes caused by factors such as equipment aging, operation condition changes and the like, and timeliness and accuracy of the model are maintained.
The steady combustion monitoring and evaluating model of the boiler unit constructed by the steps can evaluate the steady combustion performance of the boiler according to the operation feature matrix input in real time, and the evaluation method based on the model can fully utilize historical data and experience knowledge, so that the accuracy and reliability of evaluation are improved; in practical application, the model can be continuously optimized and updated according to practical conditions so as to adapt to the changes of different working conditions and requirements.
For step S7:
In step S7, comparing the stable combustion evaluation index of the boiler unit with a preset stable combustion evaluation threshold of the boiler unit, which is one of the key links in the whole monitoring process; the stable combustion evaluation index obtained through real-time calculation is compared with a preset threshold value, so that the stable combustion performance problem of the boiler unit can be found in time, and corresponding measures are taken for early warning or intervention; specifically, step S7 includes the steps of:
s71, setting a preset stable combustion evaluation threshold of the boiler unit according to historical data and actual operation experience of stable combustion performance of the boiler unit; this threshold should be based on in-depth knowledge and adequate analysis of the normal operating conditions to ensure that the stable combustion performance of the boiler unit can be accurately reflected;
S72, comparing the stable combustion evaluation index of the boiler unit obtained in the step S6 with a preset stable combustion evaluation threshold of the boiler unit; through comparison, whether the stable combustion performance of the boiler unit is normal or not can be judged;
s73, if the stable combustion evaluation index of the boiler unit is lower than a preset stable combustion evaluation threshold of the boiler unit, the stable combustion performance of the boiler unit is possibly problematic; in this case, the system should give an early warning to the operation and maintenance personnel to prompt the abnormal operation of the boiler unit; the early warning information can comprise specific abnormality types, degrees and possible reasons so that operation and maintenance personnel can quickly take corresponding measures;
S74, after receiving the early warning, operation and maintenance personnel can adjust or optimize the boiler unit according to the early warning information, such as adjusting combustion parameters, increasing monitoring frequency and the like, so as to improve stable combustion performance and ensure safe and stable operation; meanwhile, a preset stable combustion evaluation threshold value can be revised according to the early warning information so as to better adapt to the actual running condition;
S75, if the stable combustion evaluation index of the boiler unit is not lower than a preset stable combustion evaluation threshold of the boiler unit, indicating that the stable combustion performance of the boiler unit is in a normal state; in this case, the system will continue to perform data acquisition and monitoring at the set operating data acquisition frequency and maintain attention to and analysis of future data to continuously monitor and evaluate the stable combustion performance of the boiler unit.
Step S7 realizes the functions of real-time monitoring and early warning of the low-load running state of the boiler by comparing with a preset stable combustion evaluation threshold; the comparison method based on the threshold value is simple and visual, can quickly and accurately find potential problems, and provides timely feedback and guidance for operation and maintenance personnel; in practical application, the details of threshold setting, early warning modes and the like can be further optimized according to the practical requirements and the system capacity, so that the accuracy and the effectiveness of monitoring are improved.
More specifically, the setting of the stable combustion evaluation threshold of the boiler unit needs to comprehensively consider the following aspects:
Historical data analysis: based on historical operation data, calculating and analyzing stable combustion performance parameters of the boiler under different load conditions, and finding out typical ranges or trends of the parameters under normal and stable combustion states; combining expert experience and theoretical knowledge to determine a threshold value capable of effectively distinguishing normal and abnormal states;
device characteristics and design specifications: according to design parameters, structural characteristics and technical data provided by manufacturers of the boiler, the stable combustion capacity of the boiler under the low load working condition is defined, and a stable combustion evaluation threshold value is set according to the stable combustion capacity;
Environmental protection requirements and safety standards: ensuring that the set stable combustion evaluation threshold accords with the national and local environmental emission standards and safety production regulations, and preventing the exceeding of pollutants or potential safety risks caused by stable combustion problems;
Actual operating environment and conditions: considering the actual running environment (such as fuel quality, climate condition and the like) and the running requirement change of the thermal power generating unit, the stable combustion evaluation threshold value may need to have a certain dynamic adjustment space so as to adapt to different working conditions;
Commissioning and debugging optimization: in the initial stage of system online, data can be collected through the trial running and debugging process, and the stable combustion evaluation threshold value is continuously adjusted and optimized, so that the stable combustion evaluation threshold value is closer to the actual running condition, and the effectiveness and accuracy of monitoring and early warning are improved;
In summary, the preset stable combustion evaluation threshold of the boiler unit is a scientific and reasonable value comprehensively determined by fully researching and analyzing and combining actual operation data, equipment characteristics and external constraint conditions, so that the stable combustion state of the boiler unit can be accurately judged in the real-time monitoring process, and effective measures can be timely taken to ensure that the unit operates efficiently, safely and environmentally.
As shown in fig. 2 and 3, the embodiment of the invention provides a boiler low-load stable combustion monitoring device applied to deep peak shaving. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. In terms of hardware, as shown in fig. 2, a hardware architecture diagram of an electronic device where a boiler low-load steady combustion monitoring device applied to deep peak shaving is provided in an embodiment of the present invention, besides a processor, a memory, a network interface, and a nonvolatile memory shown in fig. 2, the electronic device where the device is located in the embodiment may generally include other hardware, such as a forwarding chip responsible for processing a message, and so on. Taking a software implementation as an example, as shown in fig. 3, the device in a logic sense is formed by reading a corresponding computer program in a nonvolatile memory into a memory by a CPU of an electronic device where the device is located and running the computer program.
As shown in fig. 3, the low-load stable combustion monitoring device for a boiler applied to deep peak shaving provided in this embodiment includes:
The load information acquisition module is used for acquiring the planned response power generation load of the monitored boiler unit in the deep peak shaving period, the real-time power generation load in actual operation and the lowest design power generation load of the unit in real time;
The peak regulation response evaluation calculation module is used for comprehensively analyzing and calculating a peak regulation response evaluation index of the boiler unit according to the acquired planned response power generation load, real-time power generation load and minimum design power generation load data;
The dynamic monitoring strategy setting module is used for setting the operation data acquisition frequency and the data monitoring time window of the boiler unit in the deep peak shaving stage according to the obtained peak shaving response evaluation index, and ensuring that each monitoring time window comprises a plurality of operation data acquisition time nodes;
the combustion data acquisition module is used for acquiring combustion data information of the boiler unit on each time node according to the set operation data acquisition frequency, wherein the combustion data information of the boiler unit comprises smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters;
The data characteristic conversion module is used for converting the acquired combustion data information of the boiler unit into a boiler unit operation characteristic matrix according to the operation data acquisition frequency and the operation data monitoring time window;
The stable combustion monitoring and evaluating module is used for inputting the operation characteristic matrix of the boiler unit into a prestored stable combustion monitoring and evaluating model of the boiler unit to obtain a stable combustion evaluation index of the boiler unit in an operation data monitoring time window;
The running state early warning module is used for comparing the stable combustion evaluation index of the boiler unit with a preset stable combustion evaluation threshold value of the boiler unit: if the stable combustion evaluation index of the boiler unit is lower than the stable combustion evaluation threshold of the boiler unit, prompting abnormal operation of the boiler unit to an operation and maintenance person; if the stable combustion evaluation index of the boiler unit is not lower than the stable combustion evaluation threshold of the boiler unit, the set operation data acquisition frequency is kept for data acquisition and monitoring.
In the embodiment, the load information acquisition module acquires and analyzes different working condition data of the unit in the deep peak shaving period in real time, so that the accurate grasp of the running state of the boiler is realized; the peak regulation response evaluation calculation module calculates a peak regulation response evaluation index according to the data, dynamically sets a monitoring strategy based on the peak regulation response evaluation index, and solves the problem that the traditional fixed acquisition frequency cannot flexibly cope with the combustion state change under different load conditions; the dynamic monitoring strategy setting module ensures that the fine fluctuation of the combustion state of the boiler can be captured by the most suitable data acquisition frequency and time window under different peak regulation response states, and the timeliness and the accuracy of monitoring the key stable combustion parameters are improved; the combustion data acquisition module collects various parameters representing the combustion stability of the boiler, including smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure, hearth temperature distribution and the like, and comprehensively reflects the running condition of the boiler under low load; the data characteristic conversion module converts the acquired original data into an operation characteristic matrix which is convenient for model processing, the stable combustion monitoring evaluation module performs intelligent analysis by utilizing a pre-constructed stable combustion monitoring evaluation model, and accurately calculates a stable combustion evaluation index of the boiler unit; the running state early warning module can compare the stable combustion evaluation index with a preset threshold in real time, and immediately give an alarm to operation and maintenance personnel once abnormal conditions are found, so that early recognition and prevention of faults are realized, and the equipment safety and environmental protection emission standard are ensured; the device realizes closed-loop management of the low-load stable combustion state of the boiler, can ensure high-efficiency monitoring under the normal stable combustion state, and can also conduct targeted adjustment and optimization aiming at unstable low-load working conditions, thereby effectively improving the operation efficiency and stability of the thermal power unit when participating in deep peak regulation of a power grid, and simultaneously being beneficial to improving the renewable energy consumption capability and reducing pollutant emission.
It will be appreciated that the structure illustrated in the embodiments of the present invention does not constitute a specific limitation on a low load steady combustion monitoring apparatus for a boiler applied to deep peak shaving. In other embodiments of the present invention, a low load steady combustion monitoring apparatus for a boiler for deep shaving may include more or less components than shown, or may be combined with certain components, or may be split into certain components, or may be arranged in different components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
The content of information interaction and execution process between the modules in the device is based on the same conception as the embodiment of the method of the present invention, and specific content can be referred to the description in the embodiment of the method of the present invention, which is not repeated here.
The embodiment of the invention also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the low-load stable combustion monitoring method of the boiler applied to the deep peak shaving in any embodiment of the invention is realized.
The embodiment of the invention also provides a computer readable storage medium, and the computer readable storage medium is stored with a computer program, when the computer program is executed by a processor, the processor is caused to execute the boiler low-load stable combustion monitoring method applied to deep peak shaving in any embodiment of the invention.
Specifically, a system or apparatus provided with a storage medium on which a software program code realizing the functions of any of the above embodiments is stored, and a computer (or CPU or MPU) of the system or apparatus may be caused to read out and execute the program code stored in the storage medium.
In this case, the program code itself read from the storage medium may realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code form part of the present invention.
Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs, DVD+RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer by a communication network.
Further, it should be apparent that the functions of any of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform part or all of the actual operations based on the instructions of the program code.
Further, it is understood that the program code read out by the storage medium is written into a memory provided in an expansion board inserted into a computer or into a memory provided in an expansion module connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion module is caused to perform part and all of actual operations based on instructions of the program code, thereby realizing the functions of any of the above embodiments.
It is noted that relational terms such as first and second, and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: various media in which program code may be stored, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (9)

1. A method for monitoring boiler low-load stable combustion applied to deep peak shaving, which is characterized by comprising the following steps:
Acquiring planned response power generation load of the monitored boiler unit participating in deep peak shaving, real-time power generation load of the boiler unit and the lowest design power generation load of the boiler unit;
Calculating to obtain peak regulation response evaluation indexes of the boiler unit according to the planned response power generation load, the real-time power generation load and the lowest design power generation load;
Setting operation data acquisition frequency and operation data monitoring time windows of the boiler unit in the deep peak shaving process based on peak shaving response evaluation indexes, wherein each operation data monitoring time window comprises a plurality of operation data acquisition time nodes;
Collecting combustion data information of the boiler unit according to the set operation data collection frequency;
According to the operation data acquisition frequency and the operation data monitoring time window, converting the acquired combustion data information of the boiler unit into an operation characteristic matrix of the boiler unit;
Inputting the operation characteristic matrix of the boiler unit into a pre-constructed stable combustion monitoring and evaluating model of the boiler unit to obtain a stable combustion evaluating index of the boiler unit;
comparing the stable combustion evaluation index of the boiler unit with a preset stable combustion evaluation threshold of the boiler unit, and prompting abnormal operation of the boiler unit to an operation maintenance person if the stable combustion evaluation index of the boiler unit is lower than the stable combustion evaluation threshold of the boiler unit; if the stable combustion evaluation index of the boiler unit is not lower than the stable combustion evaluation threshold of the boiler unit, the set operation data acquisition frequency is kept for data acquisition and monitoring;
the calculation formula of the peak shaving response evaluation index is as follows:
；
Wherein, Represents the peak shaver response evaluation index,Representing the planned response power generation load of the boiler unit participating in deep peak shaving,Represents the real-time power generation load of the boiler unit,Representing the lowest design power generation load of the boiler unit;
The method is used for measuring whether the current load is in a safe and effectively controllable range, and if the current load is 1, the planned response power generation load is higher than the lowest design power generation load; if the value is-1, the planned response power generation load is lower than the lowest design power generation load, and the risk of unstable combustion exists;
The evaluation index value is used for quantifying the gap between the planned response power generation load and the real-time power generation load and amplifying the gap between the planned response power generation load and the real-time power generation load;
When the peak regulation response evaluation index is a positive number, the boiler unit is in deep peak regulation and still operates in a safe and stable design load range, and at the moment, the operation data acquisition frequency does not need to be improved according to the specific numerical value of the peak regulation response evaluation index; when the peak regulation response evaluation index is a negative number, the current planned response power generation load is lower than the lowest design power generation load of the boiler unit, and at the moment, the operation data acquisition frequency is increased according to the specific numerical value of the peak regulation response evaluation index;
Setting an operation data monitoring time window according to the positive and negative values and the magnitude of the peak regulation response evaluation index; if the peak regulation response evaluation index is positive and the numerical value is larger, the peak regulation span of the boiler unit is larger, and the operation data monitoring time window is set to be 1-2 hours; if the peak shaver response evaluation index is negative or smaller, the peak shaver span of the boiler unit is larger, and the planned response power generation load is lower than the lowest design power generation load of the boiler unit, the operation data monitoring time window is set to 10 minutes to 20 minutes.
2. The method for monitoring boiler low-load stable combustion applied to deep peak shaving according to claim 1, wherein the boiler unit combustion data information comprises smoke pollutant components, steam pressure, boiler vibration frequency, furnace negative pressure and furnace temperature distribution characterization parameters.
3. The method for monitoring boiler low-load stable combustion applied to deep peak shaving according to claim 2, wherein in the boiler unit operation feature matrix, the same type of combustion data is located in the same column, different types of combustion data under the same acquisition time node are located in the same row, and the boiler unit operation feature matrix comprises a plurality of operation data acquisition time nodes in the operation data monitoring time window; the operation characteristic matrix format of the boiler unit is as follows:
；
Wherein, Indicating the concentration of nitrogen oxides, the concentration of particulate matters and the concentration of sulfur oxides collected at the nth operation data collection time node; representing the steam pressure collected at the nth operational data collection time node; Representing the vibration frequency of the boiler acquired at the nth operation data acquisition time node; representing the hearth negative pressure acquired at the nth operation data acquisition time node; And representing the characteristic parameters of the temperature distribution of the hearth acquired at the nth operation data acquisition time node.
4. The method for monitoring the low-load stable combustion of the boiler applied to the deep peak shaving according to claim 2, wherein the calculation formula of the characteristic parameters of the temperature distribution of the hearth is as follows:
；
Wherein, Representing the temperature of the ith key point in the furnace temperature distribution diagram; representing the average temperature of all key points in the furnace temperature distribution diagram; and the index is used for representing an adjustment coefficient, and is determined according to practical application requirements and experience and used for adjusting the sensitivity of the index.
5. The method for monitoring boiler low-load stable combustion applied to deep peak shaving according to any one of claims 2 to 4, wherein the method for constructing the boiler unit stable combustion monitoring evaluation model comprises the following steps:
Collecting historical data from an actually operated boiler system, wherein the historical data comprise smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution under different loads and corresponding boiler operation state information;
Selecting and extracting key features capable of reflecting the low-load stable combustion state of the boiler;
selecting a machine learning model according to the characteristics of the stable combustion problem of the boiler;
training and optimizing the selected model by utilizing the characteristic data set; and the model performance was evaluated using cross-validation.
6. The method for monitoring the stable combustion of the low load of the boiler applied to the deep peak shaver according to claim 5, wherein the decision factors for setting the stable combustion evaluation threshold of the boiler unit comprise: historical data analysis, equipment characteristics and design specifications, environmental requirements and safety standards, and actual operating environments and conditions.
7. A boiler low-load steady combustion monitoring device applied to deep peak shaving, characterized in that the device comprises:
The load information acquisition module is used for acquiring the planned response power generation load of the monitored boiler unit in the deep peak shaving period, the real-time power generation load in actual operation and the lowest design power generation load of the unit in real time;
The peak regulation response evaluation calculation module is used for comprehensively analyzing and calculating a peak regulation response evaluation index of the boiler unit according to the acquired planned response power generation load, real-time power generation load and minimum design power generation load data;
The dynamic monitoring strategy setting module is used for setting the operation data acquisition frequency and the data monitoring time window of the boiler unit in the deep peak shaving stage according to the obtained peak shaving response evaluation index, and ensuring that each monitoring time window comprises a plurality of operation data acquisition time nodes;
the combustion data acquisition module is used for acquiring combustion data information of the boiler unit on each time node according to the set operation data acquisition frequency, wherein the combustion data information of the boiler unit comprises smoke pollutant components, steam pressure, boiler vibration frequency, hearth negative pressure and hearth temperature distribution characterization parameters;
The data characteristic conversion module is used for converting the acquired combustion data information of the boiler unit into a boiler unit operation characteristic matrix according to the operation data acquisition frequency and the operation data monitoring time window;
The stable combustion monitoring and evaluating module is used for inputting the operation characteristic matrix of the boiler unit into a prestored stable combustion monitoring and evaluating model of the boiler unit to obtain a stable combustion evaluation index of the boiler unit in an operation data monitoring time window;
The running state early warning module is used for comparing the stable combustion evaluation index of the boiler unit with a preset stable combustion evaluation threshold value of the boiler unit: if the stable combustion evaluation index of the boiler unit is lower than the stable combustion evaluation threshold of the boiler unit, prompting abnormal operation of the boiler unit to an operation and maintenance person; if the stable combustion evaluation index of the boiler unit is not lower than the stable combustion evaluation threshold of the boiler unit, the set operation data acquisition frequency is kept for data acquisition and monitoring;
the calculation formula of the peak shaving response evaluation index is as follows:
；
Wherein, Represents the peak shaver response evaluation index,Representing the planned response power generation load of the boiler unit participating in deep peak shaving,Represents the real-time power generation load of the boiler unit,Representing the lowest design power generation load of the boiler unit;
The method is used for measuring whether the current load is in a safe and effectively controllable range, and if the current load is 1, the planned response power generation load is higher than the lowest design power generation load; if the value is-1, the planned response power generation load is lower than the lowest design power generation load, and the risk of unstable combustion exists;
The evaluation index value is used for quantifying the gap between the planned response power generation load and the real-time power generation load and amplifying the gap between the planned response power generation load and the real-time power generation load;
When the peak regulation response evaluation index is a positive number, the boiler unit is in deep peak regulation and still operates in a safe and stable design load range, and at the moment, the operation data acquisition frequency does not need to be improved according to the specific numerical value of the peak regulation response evaluation index; when the peak regulation response evaluation index is a negative number, the current planned response power generation load is lower than the lowest design power generation load of the boiler unit, and at the moment, the operation data acquisition frequency is increased according to the specific numerical value of the peak regulation response evaluation index;
Setting an operation data monitoring time window according to the positive and negative values and the magnitude of the peak regulation response evaluation index; if the peak regulation response evaluation index is positive and the numerical value is larger, the peak regulation span of the boiler unit is larger, and the operation data monitoring time window is set to be 1-2 hours; if the peak shaver response evaluation index is negative or smaller, the peak shaver span of the boiler unit is larger, and the planned response power generation load is lower than the lowest design power generation load of the boiler unit, the operation data monitoring time window is set to 10 minutes to 20 minutes.
8. A boiler low load steady burning monitoring electronic device for deep peak shaving comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and operable on the processor, the transceiver, the memory and the processor being connected by the bus, characterized in that the computer program when executed by the processor realizes the steps in the method according to any of claims 1-6.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-6.
CN202410137005.2A 2024-01-31 2024-01-31 Boiler low-load stable combustion monitoring method and device applied to deep peak shaving Active CN117951601B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410137005.2A CN117951601B (en) 2024-01-31 2024-01-31 Boiler low-load stable combustion monitoring method and device applied to deep peak shaving

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410137005.2A CN117951601B (en) 2024-01-31 2024-01-31 Boiler low-load stable combustion monitoring method and device applied to deep peak shaving

Publications (2)

Publication Number Publication Date
CN117951601A CN117951601A (en) 2024-04-30
CN117951601B true CN117951601B (en) 2024-07-12

Family

ID=90798057

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410137005.2A Active CN117951601B (en) 2024-01-31 2024-01-31 Boiler low-load stable combustion monitoring method and device applied to deep peak shaving

Country Status (1)

Country Link
CN (1) CN117951601B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114021975A (en) * 2021-11-04 2022-02-08 国网山东省电力公司电力科学研究院 Boiler stable combustion performance evaluation method and system based on deep peak regulation state of thermal power generating unit
CN116951454A (en) * 2023-06-13 2023-10-27 华能山东发电有限公司白杨河发电厂 Peak regulating method and system for stable combustion burner

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12027857B2 (en) * 2020-07-30 2024-07-02 State Grid Gansu Electric Power Research Institute Method for controlling peak saving by wind power grid
CN112162484B (en) * 2020-09-24 2023-03-14 华北电力大学（保定） Thermal power generating unit flexible coordination control method suitable for deep peak regulation operation
CN116663409A (en) * 2023-05-26 2023-08-29 内蒙古机电职业技术学院 Method and system for judging combustion stability of coal-fired boiler

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114021975A (en) * 2021-11-04 2022-02-08 国网山东省电力公司电力科学研究院 Boiler stable combustion performance evaluation method and system based on deep peak regulation state of thermal power generating unit
CN116951454A (en) * 2023-06-13 2023-10-27 华能山东发电有限公司白杨河发电厂 Peak regulating method and system for stable combustion burner

Also Published As

Publication number Publication date
CN117951601A (en) 2024-04-30

Similar Documents

Publication Publication Date Title
Pliego Marugán et al. Advanced analytics for detection and diagnosis of false alarms and faults: A real case study
Zhang et al. Monitoring wind turbine vibration based on SCADA data
CN111260107A (en) Boiler combustion optimization system and method
Hu et al. Using domain knowledge features for wind turbine diagnostics
WO2023207190A1 (en) Fault early warning system and method for fossil fuel power plant, electronic device, and storage medium
Zhang et al. A fault early warning method for auxiliary equipment based on multivariate state estimation technique and sliding window similarity
CN117082105B (en) Environment-friendly intelligent hospital facility monitoring system and method
CN117869930B (en) Multi-variable control method and device for stable combustion of coal-fired boiler in wide load range
CN117648586B (en) Abnormal biomass power generation supervision control system based on data analysis
CN117829516B (en) Coal-fired power plant depth peak regulation evaluation method and device
CN117823882B (en) Low-load hydrodynamic early warning method and device for coal-fired power plant boiler
CN117951601B (en) Boiler low-load stable combustion monitoring method and device applied to deep peak shaving
KR20160091942A (en) Method, system, and computer program product for analyzing production and/or process-engineering processes and/or process steps in a plant
CN116720983A (en) Power supply equipment abnormality detection method and system based on big data analysis
JP6554162B2 (en) Power plant performance evaluation method and power plant performance evaluation program
CN111256166A (en) Boiler operation control system and method
CN117991639B (en) Multi-target combustion optimization control method and device for coal-fired power plant based on machine learning
CN117993667B (en) Multi-element information fusion-based generator set combustion optimization system and method
CN112800672A (en) Boiler fouling coefficient evaluation method, system, medium and electronic equipment
CN110006484A (en) A kind of monitoring method and device of boiler fluctuation status
CN118504794B (en) Intelligent fault diagnosis system of electric spark forming machine
CN111651938B (en) Variable coal quality unit output prediction method based on thermodynamic calculation and big data
CN118331072B (en) Air flow rate self-adaptive control modeling method for air water generator
CN117968431B (en) Method and device for controlling flue gas waste heat recovery of coal-fired power plant
CN113256183B (en) Power plant real-time data association configuration method and system

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
GR01 Patent grant
GR01 Patent grant