CN117249471B - Boiler load adjusting method and system - Google Patents
Boiler load adjusting method and system Download PDFInfo
- Publication number
- CN117249471B CN117249471B CN202311546488.3A CN202311546488A CN117249471B CN 117249471 B CN117249471 B CN 117249471B CN 202311546488 A CN202311546488 A CN 202311546488A CN 117249471 B CN117249471 B CN 117249471B
- Authority
- CN
- China
- Prior art keywords
- boiler
- output power
- load
- future
- initial output
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000010438 heat treatment Methods 0.000 claims abstract description 166
- 230000002787 reinforcement Effects 0.000 claims abstract description 70
- 238000012549 training Methods 0.000 claims abstract description 30
- 230000009471 action Effects 0.000 claims description 29
- 230000008859 change Effects 0.000 claims description 29
- 230000001276 controlling effect Effects 0.000 claims description 21
- 239000000446 fuel Substances 0.000 claims description 21
- 238000011217 control strategy Methods 0.000 claims description 13
- 230000001105 regulatory effect Effects 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 abstract description 4
- 238000002485 combustion reaction Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 230000004044 response Effects 0.000 description 4
- 238000012546 transfer Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24D—DOMESTIC- OR SPACE-HEATING SYSTEMS, e.g. CENTRAL HEATING SYSTEMS; DOMESTIC HOT-WATER SUPPLY SYSTEMS; ELEMENTS OR COMPONENTS THEREFOR
- F24D19/00—Details
- F24D19/10—Arrangement or mounting of control or safety devices
- F24D19/1006—Arrangement or mounting of control or safety devices for water heating systems
- F24D19/1009—Arrangement or mounting of control or safety devices for water heating systems for central heating
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/10—Control of fluid heaters characterised by the purpose of the control
- F24H15/144—Measuring or calculating energy consumption
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/20—Control of fluid heaters characterised by control inputs
- F24H15/212—Temperature of the water
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/20—Control of fluid heaters characterised by control inputs
- F24H15/238—Flow rate
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/20—Control of fluid heaters characterised by control inputs
- F24H15/242—Pressure
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24H—FLUID HEATERS, e.g. WATER OR AIR HEATERS, HAVING HEAT-GENERATING MEANS, e.g. HEAT PUMPS, IN GENERAL
- F24H15/00—Control of fluid heaters
- F24H15/40—Control of fluid heaters characterised by the type of controllers
- F24H15/414—Control of fluid heaters characterised by the type of controllers using electronic processing, e.g. computer-based
Abstract
The invention provides a method and a system for adjusting boiler load, and relates to the technical field of boiler control, wherein the method comprises the following steps: acquiring current boiler load data of boiler equipment; obtaining heating requirements of a heating area in a preset future time period according to current boiler load data and meteorological data of the heating area in the preset future time period; obtaining initial output power of the boiler equipment in a preset future time period according to the current boiler load data and heating requirements; obtaining future boiler load data of the boiler equipment in a preset future time period through the initial output power and a boiler load prediction model, and obtaining load adjustment accuracy of the initial output power according to the future boiler load data and heating requirements of the boiler equipment in the preset future time period; and training the initial output power by using a strategy reinforcement learning model to obtain the final output power. Realize the sustainable regulation and optimization to the boiler, improve the load regulation and control precision to the boiler.
Description
Technical Field
The invention relates to the technical field of boiler control, in particular to a boiler load adjusting method and system.
Background
Currently, in order to ensure stability of heating, a boiler is generally required to provide proper energy to meet heating requirements of a building or a park, and therefore, parameters such as load, temperature and the like are generally required to be monitored in real time, and power of the boiler is adjusted according to a feedback signal, so that adjustment of the load of the boiler is achieved.
In the prior art, after parameters such as load and temperature are monitored, the power of the boiler is usually required to be regulated and controlled based on experience and fixed rules, and the load change of the boiler cannot be accurately predicted and controlled.
Disclosure of Invention
The invention solves the technical problem of how to improve the load regulation and control precision of the boiler.
The invention provides a boiler load adjusting method, which comprises the following steps:
s1: acquiring current boiler load data of the boiler equipment, wherein the current boiler load data comprises current boiler temperature, current boiler pressure and current boiler flow;
s2: obtaining the heating requirement of the heating area in a preset future time period according to the heating requirement of the heating area corresponding to the boiler equipment and meteorological data of the heating area in the preset future time period;
S3: obtaining initial output power of the boiler equipment in the preset future time period according to the current boiler temperature, the current boiler pressure, the current boiler flow and the heating requirement, wherein the initial output power specifically comprises the following steps:
s31: obtaining the heat load demand of the heating area at each time point of the preset future time period according to the heating demand;
s32: inputting the heat load demand, the current boiler temperature, the current boiler pressure and the current boiler flow into a boiler control strategy model, and outputting the boiler control strategy model to obtain the initial output power of the boiler equipment at the time point;
s4: inputting the initial output power into a boiler load prediction model to obtain future boiler load data of the boiler equipment in the preset future time period, wherein the future boiler load data comprises future boiler temperature, future boiler pressure and future boiler flow;
s5: obtaining the load adjustment accuracy of the initial output power according to the future boiler load data of the boiler equipment in the preset future time period and the heating requirement, wherein the load adjustment accuracy specifically comprises the following steps:
S51: obtaining an estimated indoor temperature of the heating zone from the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler plant at each of the time points;
s52: obtaining a temperature error value of the heating area according to the expected indoor temperature and the expected indoor temperature;
s53: determining the load regulation accuracy of the initial output power according to the magnitude and the change speed of the temperature error value;
s6: taking the future boiler load data as a state of a strategy reinforcement learning model, taking the initial output power as an action of the strategy reinforcement learning model, taking the load regulation accuracy of the initial output power as a reward of the strategy reinforcement learning model, and training the initial output power;
wherein the state of the policy reinforcement learning model is obtained according to the action of the policy reinforcement learning model;
judging whether the load regulation precision reaches a preset threshold value according to the state;
if the load adjustment accuracy is greater than or equal to the preset threshold, judging that the training of the initial output power is completed;
S7: and taking the initial output power after training as final output power, and controlling the boiler equipment to run according to the final output power.
Optionally, the preset future time period includes a plurality of time points; the obtaining the heating requirement of the heating area in the preset future time period according to the heating requirement of the heating area corresponding to the boiler equipment and the meteorological data of the heating area in the preset future time period comprises the following steps:
acquiring a heating demand index of the heating area, wherein the heating demand index comprises an expected indoor temperature and a heating area;
and obtaining the heating requirement of each time point in the preset future time period through a preset heating load calculation method according to the meteorological data, the expected indoor temperature and the heating area.
Optionally, the inputting the initial output power into a boiler load prediction model to obtain future boiler load data of the boiler plant in the preset future time period includes:
inputting the initial output power into the boiler load prediction model to obtain load change data of the boiler equipment after the boiler equipment works at the initial output power at the time point;
Wherein the load change data comprises a boiler temperature change amount, a boiler pressure change amount and a boiler flow change amount;
and obtaining the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler equipment at the time point according to the boiler temperature variation, the boiler pressure variation, the boiler flow variation, the current boiler temperature, the current boiler pressure and the current boiler flow of the boiler equipment.
Optionally, the act of taking the future boiler load data as a state of a strategy reinforcement learning model, the initial output power as the strategy reinforcement learning model, and the load adjustment accuracy of the initial output power as the reward of the strategy reinforcement learning model, training the initial output power, further includes:
and if the load adjustment accuracy is smaller than the preset threshold, adjusting the action of the strategy reinforcement learning model according to the load adjustment accuracy.
Optionally, the controlling the operation of the boiler equipment according to the final output power includes:
obtaining the opening degree of a fuel valve, the rotating speed of a fan and the flow rate of a pump of the boiler equipment according to the ratio of the final output power to the maximum output power of the boiler equipment;
And controlling the boiler equipment to operate at the final output power according to the opening degree of the fuel valve, the rotating speed of the fan and the pump flow rate of the boiler equipment.
Optionally, the boiler load adjustment method is used for a boiler system, the boiler system comprises a plurality of boiler equipment, and each boiler equipment corresponds to one heating area; the boiler load adjusting method further comprises the following steps:
controlling the boiler equipment to run through a distributed system;
the distributed system comprises a plurality of nodes, and each node correspondingly controls one boiler equipment.
The invention also provides a boiler load adjusting system, comprising:
the monitoring unit is used for acquiring current boiler load data of the boiler equipment, wherein the current boiler load data comprises current boiler temperature, current boiler pressure and current boiler flow;
the data processing unit is used for obtaining the heating requirement of the heating area in the preset future time period according to the heating requirement of the heating area corresponding to the boiler equipment and meteorological data of the heating area in the preset future time period;
the reinforcement learning unit is configured to obtain an initial output power of the boiler equipment in the preset future time period according to the current boiler temperature, the current boiler pressure, the current boiler flow and the heating requirement, where the reinforcement learning unit specifically includes:
Obtaining the heat load demand of the heating area at each time point of the preset future time period according to the heating demand;
inputting the heat load demand, the current boiler temperature, the current boiler pressure, and the current boiler flow into a boiler control strategy model;
obtaining the initial output power of the boiler equipment at the time point according to the output of the boiler control strategy model;
the reinforcement learning unit is further used for inputting the initial output power into a boiler load prediction model to obtain future boiler load data of the boiler equipment in the preset future time period, wherein the future boiler load data comprises future boiler temperature, future boiler pressure and future boiler flow;
obtaining the load adjustment accuracy of the initial output power according to the future boiler load data of the boiler equipment in the preset future time period and the heating requirement, wherein the load adjustment accuracy specifically comprises the following steps:
obtaining an estimated indoor temperature of the heating zone from the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler plant at each of the time points;
Obtaining a temperature error value of the heating area according to the expected indoor temperature and the expected indoor temperature;
determining the load regulation precision of the initial output power according to the temperature error value;
the reinforcement learning unit is further used for taking the future boiler load data as a state of a strategy reinforcement learning model, taking the initial output power as an action of the strategy reinforcement learning model, taking the load regulation precision of the initial output power as a reward of the strategy reinforcement learning model, and training the initial output power;
wherein the state of the policy reinforcement learning model is obtained according to the action of the policy reinforcement learning model;
judging whether the load regulation precision reaches a preset threshold value according to the state;
if the load adjustment accuracy is greater than or equal to the preset threshold, judging that the training of the initial output power is completed;
and the control unit is used for taking the initial output power after training as final output power and controlling the boiler equipment to run according to the final output power.
According to the boiler load adjusting method and system, the future boiler load data is predicted through the current boiler load data and the meteorological data of a heating area in a preset future time period, and then the heating requirement is combined, so that the initial output power of the boiler equipment in the preset future time period is obtained, the prediction of the future power output condition is realized, the initial output power is input into a boiler load prediction model, the future boiler load data of the boiler equipment in the preset future time period is obtained, the future boiler load data under the action of the output power is predicted based on the basis of the prediction of the future output power, the predicted future boiler load data is used as the state of a strategy reinforcement learning model, the initial output power is used as the action of the strategy reinforcement learning model, the load adjusting accuracy of the initial output power is used as the reward of the strategy reinforcement learning model, the strategy reinforcement learning model is adopted for training, the self-adaption capacity of boiler load adjustment is improved, the selection of the initial output power can be optimized according to feedback signals and rewards, the continuous adjustment and optimization of the boiler are realized, and the load adjusting accuracy of the boiler is improved.
Drawings
FIG. 1 is a schematic flow chart of a method for regulating boiler load according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for regulating the load of a boiler according to another embodiment of the present invention;
FIG. 3 is a schematic flow chart of a method for regulating the load of a boiler according to another embodiment of the present invention;
FIG. 4 is a schematic flow chart of a method for regulating the load of a boiler according to another embodiment of the present invention;
fig. 5 is a schematic view showing a structure of a boiler load adjusting system according to still another 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 of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a method for adjusting a load of a boiler, comprising:
s1: current boiler load data of the boiler plant is obtained, the current boiler load data comprising a current boiler temperature, a current boiler pressure and a current boiler flow.
Specifically, the current temperature data of the boiler can be obtained by measuring the output value of the sensor through the temperature sensor. The current pressure of the boiler plant is measured by means of a pressure sensor. The current flow of the boiler plant is measured by a flow meter. These sensors and flowmeters may be connected to the control system via analog or digital signals to transmit real-time temperature, pressure and flow data to the control system for subsequent data processing and analysis.
S2: and obtaining the heating requirement of the heating area in the preset future time period according to the heating requirement of the heating area corresponding to the boiler equipment and the meteorological data of the heating area in the preset future time period.
Specifically, first, the heating requirement of the heating area is determined according to the characteristics of the heating area corresponding to the boiler plant, the building area, the indoor temperature requirement, and the like, and in a preferred embodiment of the present invention, it can be calculated by considering the set value of the indoor temperature and the ability to maintain the indoor temperature. Meteorological data, including outdoor temperature, humidity, wind speed, etc., is collected or acquired over a predetermined future period of time, which may be from a weather station or other source of weather data. The heating requirements of the heating zone are calculated in combination with the weather data, which may vary over time due to the influence of weather factors. For example, the heating demand may increase in cold weather. And combining the heating requirement with the meteorological data through a physical model or an empirical model to acquire the heating requirement in a preset future time period.
S3: obtaining initial output power of the boiler equipment in the preset future time period according to the current boiler temperature, the current boiler pressure, the current boiler flow and the heating requirement, wherein the initial output power specifically comprises the following steps:
s31: obtaining the heat load demand of the heating area at each time point of the preset future time period according to the heating demand;
s32: and inputting the heat load demand, the current boiler temperature, the current boiler pressure and the current boiler flow into a boiler control strategy model, and outputting the boiler control strategy model to obtain the initial output power of the boiler equipment at the time point.
Specifically, with reference to fig. 3, the output power of the current boiler can be calculated by combining the parameters of the current boiler such as temperature, pressure, flow and the like and the thermal efficiency of the boiler equipment. The required thermal power at each time point in the future can be determined from a variation curve of the heating demand in a preset future time period. And then, according to the future heating demand, the initial output power of the preset future time period is presumed, wherein the initial output power is only the obtained initial data, and the subsequent training is needed based on the initial output power. In a preferred embodiment of the invention, the prediction of the initial output power may be achieved by machine learning.
The heat load demand at each point in time is calculated based on the heating demand and the heating zones within a preset future time period, wherein the heat load demand reflects the amount of heat that the heating system needs to provide at different points in time. By inputting the heat load demand, the current boiler temperature, the current boiler pressure and the current boiler flow into the boiler control strategy model, the output result of the model, i.e. the initial output power of the boiler plant in a preset future time period, can be obtained.
S4: and inputting the initial output power into a boiler load prediction model to obtain future boiler load data of the boiler equipment in the preset future time period, wherein the future boiler load data comprises future boiler temperature, future boiler pressure and future boiler flow.
In particular, the boiler load prediction model may be understood as a boiler environment model, by which future boiler load data may be simulated when an initial output power is applied to the boiler plant, the future boiler load data reflecting the state of the boiler plant in a future time period. The input of the initial output power to the boiler load prediction model may be used to predict future boiler load data of the boiler plant over a preset future period of time, including future boiler temperature, future boiler pressure, and future boiler flow. In a preferred embodiment of the present invention, the boiler load prediction model may be a regression-based model (e.g., linear regression, support vector regression, etc.) or a time series-based model (e.g., ARIMA, LSTM, etc.).
S5: obtaining the load adjustment accuracy of the initial output power according to the future boiler load data of the boiler equipment in the preset future time period and the heating requirement, wherein the load adjustment accuracy specifically comprises the following steps:
s51: obtaining an estimated indoor temperature of the heating zone from the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler plant at each of the time points;
s52: obtaining a temperature error value of the heating area according to the expected indoor temperature and the expected indoor temperature;
s53: and determining the load regulation accuracy of the initial output power according to the magnitude and the change speed of the temperature error value.
Specifically, as shown in connection with fig. 4, predicted future boiler load data is obtained using a boiler load prediction model, and the predicted future boiler load data and the actually occurring boiler load data are compared. According to the historical data or the actual monitoring data, the actual boiler load condition can be obtained, and the load adjustment accuracy is calculated. The load regulation accuracy of the initial output power is calculated by analyzing future load data and heating requirements of the boiler equipment. From the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler plant at each point in time, the predicted indoor temperature of the heating zone can be predicted. To calculate and estimate the expected indoor temperature based on the heat provided by the boiler plant, as well as other factors. The predicted indoor temperature is compared with the desired indoor temperature, and a temperature error value of the heating region can be calculated, wherein the temperature error value reflects a difference between the actual indoor temperature and the desired indoor temperature. Wherein the larger the absolute value of the temperature error value, the larger the difference between the actual indoor temperature and the desired temperature. If the absolute value of the temperature error value is small, the initial output power adjusting capability is strong. In addition, the change speed of the temperature error value is considered in addition to the magnitude of the temperature error value, and if the change speed of the temperature error value is smaller, the adjustment accuracy of the initial output power is higher.
S6: taking the future boiler load data as a state of a strategy reinforcement learning model, taking the initial output power as an action of the strategy reinforcement learning model, taking the load regulation accuracy of the initial output power as a reward of the strategy reinforcement learning model, and training the initial output power;
wherein the state of the policy reinforcement learning model is obtained according to the action of the policy reinforcement learning model;
judging whether the load regulation precision reaches a preset threshold value according to the state;
and if the load adjustment accuracy is greater than or equal to the preset threshold, judging that the training of the initial output power is completed.
Specifically, taking future boiler load data as states, such as future boiler temperature, future boiler pressure, and future boiler flow, taking initial output power as a model, the motion space can be set to a continuous value within a certain range or discrete preset power options; the load regulation accuracy of the initial output power is used as a reward function for measuring the performance of the model. The reward function should be defined according to the requirements of the task, for example, the reciprocal of the load adjustment accuracy may be used as a reward, so that the model gets a higher reward in terms of load adjustment. Training the model by using a reinforcement learning algorithm, in each training step, the model observes the current state by interacting with the environment, selects actions, evaluates performance according to a reward function, and enables the model to learn a proper output power strategy by iteratively optimizing model parameters. And obtaining the state of the model according to the action of the reinforcement learning model, wherein future boiler load data is used as an input state, and the reinforcement learning model can make a decision according to the current state and the historical state to select the action of output power. Judging whether the load regulation accuracy reaches a preset threshold according to the state, calculating the load regulation accuracy according to the difference between the output power output by the model and the actual heating effect, and comparing the load regulation accuracy with the preset threshold. If the load adjustment accuracy reaches or exceeds a preset threshold, the initial output power training is judged to be completed, and when the load adjustment accuracy reaches the preset threshold, the output power training can be considered to be completed. By taking future load data as a state, the reinforcement learning model can perceive current and future heating demand conditions, thereby better making decisions to adjust output power. The response speed and the adaptability of the system are improved, the output power can be ensured to accurately meet the heating requirement, and the energy efficiency and the performance of the system are improved.
S7: and taking the initial output power after training as final output power, and controlling the boiler equipment to run according to the final output power.
Specifically, the operation of the boiler equipment is controlled according to the final output power obtained through training as the optimal initial output power so as to meet the heating requirement and improve the energy efficiency and the stability of the boiler equipment.
According to the boiler load adjusting method, the future boiler load data is predicted through the current boiler load data and the meteorological data of a heating area in a preset future time period, and then the heating requirement is combined, so that the initial output power of the boiler equipment in the preset future time period is obtained, the prediction of the future power output condition is realized, the initial output power is input into a boiler load prediction model, the future boiler load data of the boiler equipment in the preset future time period is obtained, the future boiler load data under the action of the output power is predicted based on the prediction of the future output power, the predicted future boiler load data is used as the state of a strategy reinforcement learning model, the initial output power is used as the action of the strategy reinforcement learning model, the load adjusting accuracy of the initial output power is used as the reward of the strategy reinforcement learning model, the strategy reinforcement learning model is adopted for training, the self-adaption capacity of boiler load adjustment is improved, the selection of the initial output power can be optimized according to feedback signals and rewards, and the continuous adjustment and optimization of the boiler are realized, and the load adjusting accuracy of the boiler is improved.
In the embodiment of the present invention, as shown in fig. 2, the preset future time period includes a plurality of time points; the S2: according to the heating requirement of the heating area corresponding to the boiler equipment and the meteorological data of the heating area in a preset future time period, obtaining the heating requirement of the heating area in the preset future time period comprises the following steps:
s21: acquiring a heating demand index of the heating area, wherein the heating demand index comprises an expected indoor temperature and a heating area;
s22: and obtaining the heating requirement of each time point in the preset future time period through a preset heating load calculation method according to the meteorological data, the expected indoor temperature and the heating area.
In this embodiment, according to the heating requirement index of the heating area, including the desired indoor temperature and the heating area, the required heating level is defined, the desired indoor temperature reflects the comfort requirement of the user, and the heating area determines the magnitude of the heating load; and calculating the heating requirements at each time point in a preset future time period by using the meteorological data such as the external temperature, the humidity and the like through combining the heating requirement index of the heating area and the preset heating load calculating method.
In a preferred embodiment of the present invention, weather data such as air temperature, humidity, solar radiation, etc. is collected from weather forecast, weather station or weather monitoring station channels. The desired indoor temperature required is determined based on the usage requirements of the building and comfort criteria. The building area to be heated is determined, including walls, ceilings, floors, etc. And calculating static load by adopting a U-value heat transfer method and calculating heat transfer parameters of various materials in the building and heat insulation performance and temperature difference of the building. And according to the dynamic heat balance of the building and considering external heat sources, internal heat sources and other factors, performing time stepping calculation through a model to obtain the heating requirement of each time point in a preset future time period.
According to the boiler load adjusting method, the change trend of the heating demand in the future time period is predicted according to the meteorological data and the user demand index. This helps the heating system to better arrange for production and regulation of heat, ready in advance. By knowing the change in heating demand, the heating system can be flexibly adjusted according to the heating demand at different time points within a preset future time period.
In an embodiment of the present invention, the inputting the initial output power into a boiler load prediction model to obtain future boiler load data of the boiler equipment in the preset future time period includes:
Inputting the initial output power into the boiler load prediction model to obtain load change data of the boiler equipment after the boiler equipment works at the initial output power at the time point;
wherein the load change data comprises a boiler temperature change amount, a boiler pressure change amount and a boiler flow change amount;
and obtaining the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler equipment at the time point according to the boiler temperature variation, the boiler pressure variation, the boiler flow variation, the current boiler temperature, the current boiler pressure and the current boiler flow of the boiler equipment.
In this embodiment, the initial output power of the boiler plant is transmitted as input to the boiler load prediction model; load change data of the boiler equipment after a time point can be predicted according to the initial output power and other relevant factors through a boiler load prediction model, wherein the load change data comprises a boiler temperature change amount, a boiler pressure change amount and a boiler flow change amount. According to the boiler temperature variation, the boiler pressure variation and the boiler flow variation, the current boiler temperature, the boiler pressure and the boiler flow of the boiler equipment are combined, and the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler equipment after the time point can be calculated.
The boiler load adjusting method predicts the future load change condition of the boiler equipment according to the initial output power, updates the state index and the operation parameter of the boiler equipment, is beneficial to controlling the operation of the boiler equipment, meets the heating requirement, and improves the energy efficiency and the operation stability.
In the embodiment of the present invention, the training the initial output power by using the future boiler load data as the state of the policy reinforcement learning model, using the initial output power as the action of the policy reinforcement learning model, and using the load adjustment accuracy of the initial output power as the reward of the policy reinforcement learning model further includes:
and if the load adjustment accuracy is smaller than the preset threshold, adjusting the action of the strategy reinforcement learning model according to the load adjustment accuracy.
In the present embodiment, the future boiler load data is used as a state, the initial output power is used as an action, and the load adjustment accuracy of the initial output power is used as a reward based on the training process of reinforcement learning. Meanwhile, if the load regulation accuracy is lower than a preset threshold, the action of the reinforcement learning model is regulated according to the load regulation accuracy, and if the load regulation accuracy is lower than the preset threshold, the current regulation strategy is not accurate enough, the action is required to be regulated, and the heating system is regulated by selecting proper initial output power so as to meet the expected load demand.
The boiler load adjusting method of the invention uses future load data as a state, and predicts and optimizes the load of the heating system before the load changes by using the reinforcement learning model, thereby improving the performance and efficiency of the heating system.
In an embodiment of the present invention, the controlling the operation of the boiler device according to the final output power includes:
obtaining the opening degree of a fuel valve, the rotating speed of a fan and the flow rate of a pump of the boiler equipment according to the ratio of the final output power to the maximum output power of the boiler equipment;
and controlling the boiler equipment to operate at the final output power according to the opening degree of the fuel valve, the rotating speed of the fan and the pump flow rate of the boiler equipment.
In this embodiment, the fuel valve opening, fan speed, and pump flow of the boiler plant are typically based on the design and specifications of the heating system, as well as performance curves and control algorithms associated with the boiler plant. Determining parameters such as fuel valve opening, fan rotating speed and pump flow of the boiler equipment according to the final output power, and firstly, obtaining the fuel valve opening according to the proportion of the final output power to the maximum output power of the boiler, wherein the linear relation between the fuel valve opening and the proportion is as follows: fuel valve opening = maximum fuel valve opening x (final output power/maximum output power), the fuel valve opening is adjusted according to actual conditions to provide proper fuel supply in consideration of response characteristics and stability of the boiler plant, so as to ensure stability, high efficiency and safety of combustion.
Obtaining the rotating speed of the fan according to the proportion of the final output power to the maximum output power of the boiler, wherein the linear relation between the rotating speed of the fan and the proportion is as follows: fan speed = maximum fan speed x (final output power/maximum output power), taking into account dynamic changes in oxygen demand and air supply balance during combustion of the boiler. According to the actual situation, the stability and efficiency of combustion can be realized by continuously adjusting the rotating speed of the fan according to the response characteristic of the boiler.
And obtaining the pump flow according to the proportion of the final output power to the maximum output power of the boiler, wherein the linear relation between the pump flow and the proportion is as follows: pump flow rate=maximum pump flow rate× (final output power/maximum output power), considering the heat transfer requirement of the boiler and the supply balance of water, according to the actual situation, the pump flow rate is continuously adjusted according to the response characteristics of the boiler, to achieve the stability and efficiency of heat transfer. And calculating the opening degree of the corresponding fuel valve according to the required output power and the characteristics of fuel supply so as to control the supply amount of the boiler fuel. The required fan speed is calculated based on the required amount of combustion air and the characteristics of the boiler combustion system to ensure adequate air supply during combustion. The required pump flow is calculated based on the required heat medium flow and the characteristics of the boiler system to ensure proper circulation of the heat medium in the heating system. Finally, controlling the boiler plant to achieve operation of the final output power according to the fuel valve opening, the fan speed and the pump flow rate of the boiler plant, including: controlling the opening and closing degree of the fuel valve through a corresponding actuator according to the calculated opening of the fuel valve so as to adjust the supply quantity of fuel; controlling the rotation speed of the fan by adjusting a motor or a frequency converter of the fan according to the calculated rotation speed of the fan so as to ensure sufficient combustion air supply in the combustion process; and controlling the switching degree or the pump speed of the pump through a corresponding actuator according to the calculated pump flow so as to regulate the flow of the heating medium in the heating system.
The boiler load adjusting method disclosed by the invention operates according to the requirement of final output power so as to meet the requirement of a heating system, improve the operation efficiency, stability and accuracy of the heating system and ensure that the system can provide required heat according to the requirement.
In an embodiment of the present invention, the boiler load adjustment method is used in a boiler system, where the boiler system includes a plurality of boiler devices, and each boiler device corresponds to one heating area; the boiler load adjusting method further comprises the following steps:
controlling the boiler equipment to run through a distributed system;
the distributed system comprises a plurality of nodes, and each node correspondingly controls one boiler equipment.
In this embodiment, the boiler load adjustment method is applied to a boiler system having a plurality of boiler plants and heating zones, each node may be a separate computer or controller having separate processing and communication capabilities. Each boiler equipment corresponds to one node, so that each node is responsible for controlling the corresponding boiler equipment, and distribution is carried out according to the system topology or the requirements, so that each heating area can be properly heated; a common goal or strategy is defined so that the nodes can work cooperatively under given conditions to achieve load regulation of the overall boiler system. This may involve cooperation and coordination between the nodes to control the output power and operating conditions of the boiler plant. The distributed control among the nodes ensures that the system has higher flexibility and reliability, and if one node fails or fails, other nodes can still continue to work, so that the stable operation of the heating system is ensured.
According to the boiler load adjusting method, a plurality of boiler equipment can be operated simultaneously and controlled in a coordinated manner through the distributed control method, so that the overall optimization effect is realized, and the performance and the energy utilization efficiency of a heating system are improved.
As shown in connection with fig. 5, the present invention also provides a boiler load adjustment system 100, comprising:
a monitoring unit 110 for acquiring current boiler load data of the boiler plant, the current boiler load data comprising a current boiler temperature, a current boiler pressure and a current boiler flow;
the data processing unit 120 is configured to obtain, according to a heating requirement of a heating area corresponding to the boiler equipment and weather data of the heating area in a preset future time period, the heating requirement of the heating area in the preset future time period;
the reinforcement learning unit 130 is configured to obtain an initial output power of the boiler device in the preset future time period according to the current boiler temperature, the current boiler pressure, the current boiler flow, and the heating requirement, where the reinforcement learning unit specifically includes:
obtaining the heat load demand of the heating area at each time point of the preset future time period according to the heating demand;
Inputting the heat load demand, the current boiler temperature, the current boiler pressure, and the current boiler flow into a boiler control strategy model;
obtaining the initial output power of the boiler equipment at the time point according to the output of the boiler control strategy model;
the reinforcement learning unit 130 is further configured to input the initial output power into a boiler load prediction model, and obtain future boiler load data of the boiler plant within the preset future time period, where the future boiler load data includes a future boiler temperature, a future boiler pressure, and a future boiler flow;
obtaining the load adjustment accuracy of the initial output power according to the future boiler load data of the boiler equipment in the preset future time period and the heating requirement, wherein the load adjustment accuracy specifically comprises the following steps:
obtaining an estimated indoor temperature of the heating zone from the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler plant at each of the time points;
obtaining a temperature error value of the heating area according to the expected indoor temperature and the expected indoor temperature;
Determining the load regulation precision of the initial output power according to the temperature error value;
the reinforcement learning unit 130 is further configured to train the initial output power by taking the future boiler load data as a state of a policy reinforcement learning model, taking the initial output power as an action of the policy reinforcement learning model, and taking the load adjustment accuracy of the initial output power as a reward of the policy reinforcement learning model;
wherein the state of the policy reinforcement learning model is obtained according to the action of the policy reinforcement learning model;
judging whether the load regulation precision reaches a preset threshold value according to the state;
if the load adjustment accuracy is greater than or equal to the preset threshold, judging that the training of the initial output power is completed;
and the control unit 140 is used for taking the initial output power after training as final output power and controlling the boiler equipment to operate according to the final output power.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It should be noted that in this document, 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. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A method for regulating a load of a boiler, comprising:
s1: acquiring current boiler load data of the boiler equipment, wherein the current boiler load data comprises current boiler temperature, current boiler pressure and current boiler flow;
s2: obtaining the heating requirement of the heating area in a preset future time period according to the heating requirement of the heating area corresponding to the boiler equipment and meteorological data of the heating area in the preset future time period;
s3: obtaining initial output power of the boiler equipment in the preset future time period according to the current boiler temperature, the current boiler pressure, the current boiler flow and the heating requirement, wherein the initial output power specifically comprises the following steps:
s31: obtaining the heat load demand of the heating area at each time point of the preset future time period according to the heating demand;
s32: inputting the heat load demand, the current boiler temperature, the current boiler pressure and the current boiler flow into a boiler control strategy model, and outputting the boiler control strategy model to obtain the initial output power of the boiler equipment at the time point;
S4: inputting the initial output power into a boiler load prediction model to obtain future boiler load data of the boiler equipment in the preset future time period, wherein the future boiler load data comprises future boiler temperature, future boiler pressure and future boiler flow;
s5: obtaining the load adjustment accuracy of the initial output power according to the future boiler load data and the heating demand of the boiler equipment in the preset future time period, wherein the load adjustment accuracy specifically comprises the following steps:
s51: obtaining an estimated indoor temperature of the heating zone from the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler plant at each of the time points;
s52: obtaining a temperature error value of the heating area according to the expected indoor temperature and the expected indoor temperature;
s53: determining the load regulation accuracy of the initial output power according to the magnitude and the change speed of the temperature error value;
s6: taking the future boiler load data as a state of a strategy reinforcement learning model, taking the initial output power as an action of the strategy reinforcement learning model, taking the load regulation accuracy of the initial output power as a reward of the strategy reinforcement learning model, and training the initial output power;
Wherein the state of the policy reinforcement learning model is obtained according to the action of the policy reinforcement learning model;
judging whether the load regulation precision reaches a preset threshold value according to the state;
if the load adjustment accuracy is greater than or equal to the preset threshold, judging that the training of the initial output power is completed;
s7: and taking the initial output power after training as final output power, and controlling the boiler equipment to run according to the final output power.
2. The boiler load adjustment method according to claim 1, characterized in that the preset future period of time comprises a plurality of points of time; the obtaining the heating requirement of the heating area in the preset future time period according to the heating requirement of the heating area corresponding to the boiler equipment and the meteorological data of the heating area in the preset future time period comprises the following steps:
acquiring a heating demand index of the heating area, wherein the heating demand index comprises an expected indoor temperature and a heating area;
and obtaining the heating requirement of each time point in the preset future time period through a preset heating load calculation method according to the meteorological data, the expected indoor temperature and the heating area.
3. The boiler load adjustment method according to claim 2, wherein said inputting the initial output power into a boiler load prediction model results in future boiler load data of the boiler plant over the preset future time period, comprising:
inputting the initial output power into the boiler load prediction model to obtain load change data of the boiler equipment after the boiler equipment works at the initial output power at the time point;
wherein the load change data comprises a boiler temperature change amount, a boiler pressure change amount and a boiler flow change amount;
and obtaining the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler equipment at the time point according to the boiler temperature variation, the boiler pressure variation, the boiler flow variation, the current boiler temperature, the current boiler pressure and the current boiler flow of the boiler equipment.
4. The method of claim 1, wherein the act of taking the future boiler load data as a state of a strategy reinforcement learning model, the initial output power as the strategy reinforcement learning model, the load adjustment accuracy of the initial output power as a reward of the strategy reinforcement learning model, training the initial output power, further comprises:
And if the load adjustment accuracy is smaller than the preset threshold, adjusting the action of the strategy reinforcement learning model according to the load adjustment accuracy.
5. The boiler load adjustment method according to claim 1, characterized in that said controlling the operation of the boiler plant according to the final output power comprises:
obtaining the opening degree of a fuel valve, the rotating speed of a fan and the flow rate of a pump of the boiler equipment according to the ratio of the final output power to the maximum output power of the boiler equipment;
and controlling the boiler equipment to operate at the final output power according to the opening degree of the fuel valve, the rotating speed of the fan and the pump flow rate of the boiler equipment.
6. The boiler load adjustment method according to claim 1, characterized in that the boiler load adjustment method is used for a boiler system comprising a plurality of the boiler plants, each of the boiler plants corresponding to one of the heating zones; the boiler load adjusting method further comprises the following steps:
controlling the boiler equipment to run through a distributed system;
the distributed system comprises a plurality of nodes, and each node correspondingly controls one boiler equipment.
7. A boiler load adjustment system, comprising:
the monitoring unit is used for acquiring current boiler load data of the boiler equipment, wherein the current boiler load data comprises current boiler temperature, current boiler pressure and current boiler flow;
the data processing unit is used for obtaining the heating requirement of the heating area in the preset future time period according to the heating requirement of the heating area corresponding to the boiler equipment and meteorological data of the heating area in the preset future time period;
the reinforcement learning unit is configured to obtain an initial output power of the boiler equipment in the preset future time period according to the current boiler temperature, the current boiler pressure, the current boiler flow and the heating requirement, where the reinforcement learning unit specifically includes:
obtaining the heat load demand of the heating area at each time point of the preset future time period according to the heating demand;
inputting the heat load demand, the current boiler temperature, the current boiler pressure, and the current boiler flow into a boiler control strategy model;
obtaining the initial output power of the boiler equipment at the time point according to the output of the boiler control strategy model;
The reinforcement learning unit is further used for inputting the initial output power into a boiler load prediction model to obtain future boiler load data of the boiler equipment in the preset future time period, wherein the future boiler load data comprises future boiler temperature, future boiler pressure and future boiler flow;
obtaining the load adjustment accuracy of the initial output power according to the future boiler load data and the heating demand of the boiler equipment in the preset future time period, wherein the load adjustment accuracy specifically comprises the following steps:
obtaining an estimated indoor temperature of the heating zone from the future boiler temperature, the future boiler pressure and the future boiler flow of the boiler plant at each of the time points;
obtaining a temperature error value of the heating area according to the expected indoor temperature and the expected indoor temperature;
determining the load regulation precision of the initial output power according to the temperature error value;
the reinforcement learning unit is further used for taking the future boiler load data as a state of a strategy reinforcement learning model, taking the initial output power as an action of the strategy reinforcement learning model, taking the load regulation precision of the initial output power as a reward of the strategy reinforcement learning model, and training the initial output power;
Wherein the state of the policy reinforcement learning model is obtained according to the action of the policy reinforcement learning model;
judging whether the load regulation precision reaches a preset threshold value according to the state;
if the load adjustment accuracy is greater than or equal to the preset threshold, judging that the training of the initial output power is completed;
and the control unit is used for taking the initial output power after training as final output power and controlling the boiler equipment to run according to the final output power.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311546488.3A CN117249471B (en) | 2023-11-20 | 2023-11-20 | Boiler load adjusting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311546488.3A CN117249471B (en) | 2023-11-20 | 2023-11-20 | Boiler load adjusting method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117249471A CN117249471A (en) | 2023-12-19 |
| CN117249471B true CN117249471B (en) | 2024-01-16 |
Family
ID=89126918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311546488.3A Active CN117249471B (en) | 2023-11-20 | 2023-11-20 | Boiler load adjusting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117249471B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105570867A (en) * | 2015-12-29 | 2016-05-11 | 北京市燃气集团有限责任公司 | Regulating method and system for direct heat supply flue gas boiler load parameters |
| CA2977272A1 (en) * | 2016-08-29 | 2018-02-28 | Iot Cloud Technologies Inc. | Weather anticipating programmable thermostat and wireless network ptac control |
| CN112862189A (en) * | 2021-02-03 | 2021-05-28 | 北京百度网讯科技有限公司 | Method, device, apparatus, storage medium, and program product for predicting heat source load |
| CN113655762A (en) * | 2021-07-27 | 2021-11-16 | 咸阳新兴分布式能源有限公司 | Operation optimization control method and system for gas energy supply system |
| CN115013861A (en) * | 2022-05-31 | 2022-09-06 | 新奥数能科技有限公司 | Indoor temperature control method and device based on heating system |
| CN115759422A (en) * | 2022-11-21 | 2023-03-07 | 北京全应科技有限公司 | Heating heat load prediction method, system, device, and medium |
| CN116068890A (en) * | 2022-12-29 | 2023-05-05 | 浙江中控技术股份有限公司 | Cooperation optimization scheduling method and device for furnace-machine network of cogeneration district heating |
| CN116105212A (en) * | 2023-03-04 | 2023-05-12 | 张晓菊 | Capacity-increasing-free electric boiler system and control method thereof |
| KR20230093874A (en) * | 2021-12-20 | 2023-06-27 | 주식회사 경동나비엔 | Boiler management apparatus and method for generating prediction model of boiler based on big-data |
| CN116592417A (en) * | 2023-04-23 | 2023-08-15 | 代傲表计（济南）有限公司 | Centralized heating system optimal control method and system based on load prediction |
-
2023
- 2023-11-20 CN CN202311546488.3A patent/CN117249471B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105570867A (en) * | 2015-12-29 | 2016-05-11 | 北京市燃气集团有限责任公司 | Regulating method and system for direct heat supply flue gas boiler load parameters |
| CA2977272A1 (en) * | 2016-08-29 | 2018-02-28 | Iot Cloud Technologies Inc. | Weather anticipating programmable thermostat and wireless network ptac control |
| CN112862189A (en) * | 2021-02-03 | 2021-05-28 | 北京百度网讯科技有限公司 | Method, device, apparatus, storage medium, and program product for predicting heat source load |
| CN113655762A (en) * | 2021-07-27 | 2021-11-16 | 咸阳新兴分布式能源有限公司 | Operation optimization control method and system for gas energy supply system |
| KR20230093874A (en) * | 2021-12-20 | 2023-06-27 | 주식회사 경동나비엔 | Boiler management apparatus and method for generating prediction model of boiler based on big-data |
| CN115013861A (en) * | 2022-05-31 | 2022-09-06 | 新奥数能科技有限公司 | Indoor temperature control method and device based on heating system |
| CN115759422A (en) * | 2022-11-21 | 2023-03-07 | 北京全应科技有限公司 | Heating heat load prediction method, system, device, and medium |
| CN116068890A (en) * | 2022-12-29 | 2023-05-05 | 浙江中控技术股份有限公司 | Cooperation optimization scheduling method and device for furnace-machine network of cogeneration district heating |
| CN116105212A (en) * | 2023-03-04 | 2023-05-12 | 张晓菊 | Capacity-increasing-free electric boiler system and control method thereof |
| CN116592417A (en) * | 2023-04-23 | 2023-08-15 | 代傲表计（济南）有限公司 | Centralized heating system optimal control method and system based on load prediction |
Non-Patent Citations (1)
| Title |
|---|
| 燃煤锅炉负荷控制运行策略;刘文旭;李德英;周佳;;区域供热(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117249471A (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DK2866117T3 (en) | System and method for distributed adaptive and predictive heating control | |
| Pfeiffer et al. | Control of temperature and energy consumption in buildings-a review. | |
| EP3082010A1 (en) | A system for dynamically balancing a heat load and a method thereof | |
| Viot et al. | Model predictive control of a thermally activated building system to improve energy management of an experimental building: Part II-Potential of predictive strategy | |
| CN111473407A (en) | Model-based centralized heating system on-demand accurate regulation and control method | |
| Yu et al. | Online tuning of a supervisory fuzzy controller for low-energy building system using reinforcement learning | |
| EP0699316A1 (en) | Heating control apparatus | |
| US20160146497A1 (en) | Maintaining an attribute of a building | |
| CN111578370B (en) | Heating regulation and control method, system, medium and electronic equipment | |
| JP2011214794A (en) | Air conditioning system control device | |
| CN115013861B (en) | Indoor temperature control method and device based on heating system | |
| Candanedo et al. | Near-optimal transition between temperature setpoints for peak load reduction in small buildings | |
| US20180372341A1 (en) | Predictive control for domestic heating system | |
| Cholewa et al. | An easy and widely applicable forecast control for heating systems in existing and new buildings: First field experiences | |
| CN117249471B (en) | Boiler load adjusting method and system | |
| Wang et al. | Field test of Model Predictive Control in residential buildings for utility cost savings | |
| CN116817357B (en) | Heating control method and device based on heating station, building and household | |
| Simon et al. | Energy efficient smart home heating system using renewable energy source with fuzzy control design | |
| EP1801508A1 (en) | System and method for the optimised management of a heating system | |
| EP3771957A1 (en) | Method and system for controlling of heating, ventilation and air conditioning | |
| CN116592417A (en) | Centralized heating system optimal control method and system based on load prediction | |
| Liu et al. | An on-off regulation method by predicting the valve on-time ratio in district heating system | |
| US20230349577A1 (en) | Device and method for controlling an orifice of a valve in an hvac system | |
| WO2021239624A1 (en) | Method and system for controlling a fluid transport system | |
| Heidari et al. | Reinforcement learning for occupant-centric operation of residential energy system: Evaluating the adaptation potential to the unusual occupants´ behavior during COVID-19 pandemic |
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 |