CN116822682A - Online prediction method for heat load of heating power station - Google Patents
Online prediction method for heat load of heating power station Download PDFInfo
- Publication number
- CN116822682A CN116822682A CN202310099611.5A CN202310099611A CN116822682A CN 116822682 A CN116822682 A CN 116822682A CN 202310099611 A CN202310099611 A CN 202310099611A CN 116822682 A CN116822682 A CN 116822682A
- Authority
- CN
- China
- Prior art keywords
- heat
- temperature
- station
- heat 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.)
- Pending
Links
- 238000010438 heat treatment Methods 0.000 title claims abstract description 135
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 53
- 230000005855 radiation Effects 0.000 claims description 19
- 238000013461 design Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000001105 regulatory effect Effects 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 7
- 239000003570 air Substances 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 239000012080 ambient air Substances 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000009471 action Effects 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000011664 signaling Effects 0.000 claims description 3
- 239000008400 supply water Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000005265 energy consumption Methods 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention relates to an on-line prediction method for heat load of a heating power station, which comprises the following steps: step S1, a room temperature monitoring module is arranged in a typical heat user room connected with each heating station, the room temperature is monitored, and room temperature data are stored; s2, carrying out hydraulic balance adjustment on a courtyard pipe network of each heating station to enable the indoor temperature of a heating user to reach the local specified indoor temperature in a heating period; s3, selecting a typical heating power station, and acquiring and collecting heat load data of each time period in the typical heating power station; s4, calculating a typical heat load prediction model of the heating power station according to the data acquired in the S3; s5, correcting a typical thermal station thermal load prediction model according to the historical thermal load proportion data relation and the historical thermal load data of each thermal station to obtain a thermal load prediction model; the prediction method can accurately predict the heat load of each heating power station and reduce the uneven heat loss of heat supply between the heating power stations and between buildings.
Description
Technical Field
The invention relates to the technical field of intelligent heat supply, in particular to an online prediction method for heat load of a heating power station.
Background
Heating in winter in northern areas mainly uses central heating, and the proportion of heat supply energy consumption required by heating in social energy consumption is larger and reaches 30%, so that how to improve central heating efficiency and reduce energy consumption of heating enterprises becomes a problem to be solved urgently.
Most of the heating stations of the heat supply enterprises in society are designed according to 1996 edition of centralized heat supply design manual or 2002 edition of urban heating network design specification. With the development of cities and the progress of technology, the heat supply industry has changed greatly, and the design specification of the heating network has revised a great deal of content in 2010 and is named as the design specification of the urban heat supply network. In 2022, the "urban heat supply network design specification" is revised again in the industry, and is named as "urban heat supply network design standard". Therefore, the existing urban central heating power station and the secondary pipe network cannot adapt to the development of the existing industry, and corresponding transformation is urgently needed. Meanwhile, with the development of technologies such as sensing detection, network communication, hydraulic balance and the like, the establishment of a novel heating power station and a secondary pipe network is also a trend.
In particular, the city central heating at present has the following problems:
(1) The room temperature monitoring and feedback of the heat user are not available, the heat supply quality cannot be known, and the closed-loop control of the heat supply effect cannot be realized.
(2) The heat supply load adjusting curve of the heating power station is set according to experience of heat exchanger set manufacturers or heat supply enterprises, does not meet the actual heat supply condition, cannot supply heat according to needs, and easily causes excessive heat supply and pipe network oscillation.
(3) The control regulation object has limitations, only the control regulation problem of the heating power station itself is considered, and the regulation nonlinearity of the heating system and the strong coupling between the heating power stations are not considered.
(4) The automatic control of the heating station adopts a simple PID regulation strategy, and the feedback signal is generally the water supply temperature, the water return temperature or the average water supply and return temperature of a courtyard pipe network, so that the problems of thermal inertia and time lag of a heating system are not considered.
The problem is to solve above-mentioned problem, first to solve the problem of heating power station heat load total quantity control. Therefore, it is very important to accurately predict the thermal load of the thermal station by a scientific and reasonable method.
The existing heat load prediction method is too many in factors and ideal, and cannot be implemented on line; or the sampling data is too little, the sampling data is not representative, the accuracy is poor, and the energy-saving purpose is not achieved. For example, patent application number 201910088808.2, "heat load prediction method of cogeneration system", collects historical data of heat supply of past 24 hours of a thermal power plant, performs normalization processing on the data of each variable, obtains an equation according to a fuzzy algorithm, and substitutes input variables of a predicted day, namely outdoor temperature, water supply temperature, backwater temperature and water supply flow, into the equation to further predict the corresponding heat load. The problem with this patent is that the prediction object is too large, facing the whole heating system, including all the heating stations; each heating power station has the specificity, and only the total quantity is known, so that the heat load of each heating power station cannot be known; the load predictions for each station should be developed and then summed. The prediction function of this patent considers few heat load influencing factors, does not consider the influence of solar radiation intensity on heat supply load, and radiant heat is an important factor influencing heat load, and must be taken into consideration. Second, the training data is only data within 24 hours, and is not representative, and the entire heating load cannot be predicted. In addition, there may be excessive heat supply or insufficient heat supply under the working condition, and load prediction is performed according to the working condition, so that accuracy is poor.
The patent with application number 202210183998.8 discloses a heat load curve prediction method for classifying multiple-width learning attention mechanisms, which is mainly applicable to heat load curve prediction of users of distributed ground source heat pump heat accumulators of power systems, and divides the heat load curve of each day into two types, wherein the first type of curve is stable, and the second type of curve has larger fluctuation. The similar curves are divided into the types, so that the establishment of a subsequent prediction model is facilitated, and the accuracy of the prediction model is improved. The method is simple to classify, then regularly supplies heat, and does not fundamentally solve the problems of excessive heat supply or insufficient heat supply; at the same time, the training time is shorter, the data is less, the data is not representative, and excessive heat supply or insufficient heat supply can exist under the working condition.
Patent application number 202211077279.4, "a room temperature model prediction control method based on a neural network and constrained by room heat load", inputs weather forecast data sets into a heat load interval prediction module, an indoor temperature prediction module and a radiator module respectively, searches for a globally optimal hot water flow sequence, and finally controls the rotation speed of a water pump. The patent does not determine what types of weather data are, does not consider the hysteresis of room temperature adjustment, directly controls the water pump to adjust the heat load, and easily causes pipe network oscillation.
Patent application number 202010521186.0, "a method for predicting cold and hot loads of buildings constructed based on feature sets," wherein the indoor parameter variables comprise: indoor air dry bulb temperature, indoor air relative humidity, indoor illuminance and indoor wind speed; the meteorological parameter variables include: the outdoor environment dry bulb temperature, the outdoor dew point temperature, the outdoor environment relative humidity, the air pressure, the wind direction, the total radiation day accumulation of the horizontal, the scattered radiation, the direct radiation and the total radiation in the four directions of east, south, west and north. The patent considers too many factors, is more ideal, and cannot be applied to a resident heating system; some load characteristic sets are taken, so that the load has a large accident, and whether the loads are reasonable or not and whether excessive heat supply is performed or not cannot be known.
The patent with application number 202211017410.8 is a heat load prediction method and system considering heat characteristics in alpine regions, wherein the weather comprises the current time temperature, the highest temperature of the day, the lowest temperature of the day, snowfall amount and humidity, the average temperature of the day, the time comprises holiday type, month value, day value and hour value, the building type is divided into office building influence factors, school influence factors, factory influence factors and residence influence factors, the method is suitable for offline heat load calculation, some parameters are difficult to obtain accurate and reliable values, and some parameters are seriously dependent on experience values, so the method has no practical operability.
Patent application number 202111485406.X, "a method and a system for predicting and regulating dynamic heat load of heat exchange station", considers outdoor temperature, solar radiation intensity level, outdoor humidity, wind speed and wind direction, instantaneous heat value of primary network, loaded building type and heating area when the heat station operates, establishes relationship between meteorological parameters and time sequence and time-by-time heat value of primary network of heat station, and achieves the requirement of accurately predicting load value of heat station after providing relevant input parameters. The patent considers more parameters, is difficult to realize, and corresponds to one-time network to adjust the time-by-time heat, and does not consider the inertia and hysteresis of heat supply; still rely on existing control strategies, do not propose any new control method.
Patent application number 201811005079.1, "a heat load prediction method for heat exchange station", calculates heat index per unit area under six different typical climates according to six different typical climates and historical data of heating power station under corresponding meteorological conditions for 24 hours; and the second step is to calculate the time-by-time heat load of 24 hours in the future according to the converted heat index and weather forecast conditions and convert the time-by-time heat load into the secondary side water supply temperature of the heating power station. The patent selects 6 typical climates, is not representative, and the historical heat load data under the climatic conditions is not necessarily reasonable, and can have the problems of excessive heat supply or insufficient heat supply.
Based on various problems existing in the existing heat station heat load prediction method, an online heat station heat load prediction method is established, and the significance is great and necessary.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an on-line prediction method for the heat load of a heat station, which can solve the problem of hydraulic imbalance of a courtyard pipe network connected with the heat station, solve the problem that the heat load of the heat station cannot be accurately predicted on line at present, and finally solve the problem of heat supply of the heat station according to the needs.
In order to achieve the above purpose, the invention adopts the following technical scheme:
an on-line prediction method for heat load of a heating power station comprises the following steps:
step S1, a room temperature monitoring module is arranged in a typical heat user room connected with each heating station, the room temperature is monitored, and room temperature data are stored;
s2, carrying out hydraulic balance adjustment on a courtyard pipe network of each heating station to enable the indoor temperature of a heating user to reach the local specified indoor temperature in a heating period;
s3, selecting a typical heating power station, and acquiring and collecting heat load data of each time period in the typical heating power station;
s4, calculating a typical heat load prediction model of the heating power station according to the data acquired in the S3;
and S5, correcting a typical heat load prediction model according to the historical heat load proportion data relation and the historical heat load data of each heat station to obtain a heat load prediction model, and carrying out online prediction on the heat load of each heat station.
Preferably, the typical hot users in step S1 are the bottom, middle and top users of each unit of the residential heating house.
Preferably, the hydraulic balance of the pipe network in step S2 is adjusted as follows:
carrying out hydraulic balance transformation on each unit of a courtyard pipe network connected with a heating power station, and installing a remotely controllable balance valve, wherein the balance valve is matched with a temperature sensor for monitoring the return water temperature of the unit;
according to the correlation between the indoor temperature of a typical heat user and the return water temperature of the unit, a functional relation between the indoor temperature of the heating period and the return water temperature of the unit is deduced, and then a target value of the return water temperature of the unit is calculated by utilizing the local specified indoor temperature by utilizing the functional relation;
and then, using the difference value of the unit backwater temperature target value and the unit backwater temperature value measured by the temperature sensor matched with the balance valve as a feedback signal, and controlling the opening of the balance valve through PID control, so that the actual value of the unit backwater temperature approaches the unit backwater temperature target value.
Preferably, the functional relation between the indoor temperature and the unit backwater temperature in the pipe network hydraulic balance adjustment is as follows:
in the formula: q h Heating Heat index (W/m) 2 )；A h -heating building area (m) 2 )；t i -room temperature (°c); t is t o -outdoor ambient temperature (°c); t is t oh -locally calculating the temperature (c) outdoors during the heating period; q (Q) rs -the building unit designs the heat supply network water flow (t/h); t (T) g -the building unit designs the water supply temperature (c) of the heat supply network; t (T) ij -the temperature (DEG C) of the return water of the jth unit of the ith building.
Preferably, in step S3, the data collection step is specifically as follows: recording the water circulation time of a courtyard pipe network heat supply network of a heating power station and the room temperature response time of a heat user through on-site experiment, determining the time period between the time point when the water heating temperature of the courtyard pipe network begins to change and the time point when the room temperature of the heat user changes and stabilizes as the PID control action interval time of a primary side regulating door of the heating power station, regulating the primary side regulating door of the heating power station when the integral multiple of one interval time is reached, and maintaining the room temperature of the user constant while the environmental temperature changes; and (3) carrying out a field test, calculating the heat supply load of the heating power station in real time according to the temperature difference of the primary network water supply and return and the water flow of the heating power network, and recording the corresponding outdoor ambient air temperature and solar radiation intensity at the time.
Preferably, the data collection period in step S3 is one heating season.
Preferably, in step S4, the exemplary heat station thermal load prediction model method is specifically as follows:
after achieving hydraulic balance and reaching the standard of the room temperature of a heat user, calculating historical heat load of the heating power station according to the temperature of the water supply and return and the flow meter; according to the collected data, a thermal power station thermal load calculation model is obtained through machine self-learning, and the thermal power station thermal load calculation model is substituted into each parameter value to obtain the thermal power station thermal load; the historical heat load of the heating power station is equal to the calculated heat load of the heating power station; wherein the calculation formula is as follows:
Q L ＝1.16×Q tz ×(t tg -t th )
Q L ＝Q J
in the formula: q (Q) L -thermal station historical thermal load (MW); q (Q) tz -yard pipe network heat supply network water flow (t/h); t is t tg -yard pipe network heat supply water supply temperature (°c); t is t th -yard pipe network heat supply network water backwater temperature (DEG C); PX (PX) ijk -a hot user average temperature value (°c); t is t i -the heating period locally prescribes the indoor temperature (°c); t is t o -outdoor ambient temperature (°c); r is R a -solar radiation intensity (W/m 2); r is R a.o -solar radiation intensity (W/m 2) under design conditions; q (Q) J -the thermal station calculates the thermal load (MW); q h Heating Heat index (W/m) 2 )；A h -heating building area (m) 2 ) The method comprises the steps of carrying out a first treatment on the surface of the η -adjustment coefficient (%); delta-thermal load correction value (MW);
according to the formula, the adjustment coefficient eta and the thermal load correction value delta can be obtained, and a typical thermal power station thermal load calculation model is finally obtained.
Preferably, the step of correcting the model in step S5 is specifically as follows:
calculating heat load proportion data among all heat stations of all time nodes, and storing the heat load proportion data of all time nodes and the actual heat load of the corresponding time nodes in time sequence;
then, the heat load proportion data of the earliest time node is taken, the predicted heat load of a typical heat station is calculated through a heat load prediction model of the typical heat station, then, the predicted heat load of other heat stations is obtained according to the heat load proportion data to form a predicted heat load curve, then, the predicted heat load curve is compared with an actual heat load curve formed by the actual heat loads of all heat stations, and then, the heat load prediction model of the typical heat station is adjusted to enable the predicted heat load curve to be identical with the actual heat load curve;
and then continuously taking heat load proportion data and actual heat load according to the time sequence, continuously adjusting a typical heat load prediction model of the heat station, and finally correcting the heat load prediction model into a heat load prediction model of the heat station to predict the heat load of each heat station.
Preferably, the method further comprises the following steps: and S6, searching an optimal thermal load prediction model.
Preferably, the specific steps of the step S6 are as follows:
firstly programming a thermal load prediction model into a system, calculating the thermal load of a heating power station in real time according to the real-time outdoor ambient air temperature and solar radiation intensity, and heating, and then judging whether the thermal load prediction model is successfully established by comparing whether the difference between the actual room temperature and the target room temperature is within +/-1.5 ℃;
if the difference value between the actual room temperature and the target room temperature is within the range of +/-1.5 ℃, the thermal load prediction model is considered reasonable to be shaped, and the thermal load of each heating power station is predicted on line; if the difference between the actual room temperature and the target room temperature is larger than 1.5 ℃, the method is considered unreasonable, the method enters a step S4 to correct the thermal load prediction model, and then steps S5 and S6 are carried out again until the difference between the actual room temperature and the target room temperature is within +/-1.5 ℃, model optimizing is finished, the thermal load prediction model is shaped, and the thermal load of each thermal station is predicted on line.
Compared with the prior art, the invention has the beneficial effects that:
step S1 is to realize indoor room temperature monitoring of a heat user, step S2 is to solve the problem of hydraulic balance of a courtyard pipe network, the rest steps only enter specific heat load prediction, a room temperature monitoring device is installed in a typical heat user, the hydraulic power of the courtyard pipe network is leveled, so that the problem of uneven heat supply, cold and heat cannot occur, the heat load distribution is ensured as required, the historical heat load and corresponding boundary condition parameters under the condition can be used as training data of a heat load prediction model of the typical heat station, and the model correction in step S5 is used to obtain an accurate heat load prediction model, so that the heat load of each heat station can be predicted, the accuracy and the reliability of the prediction model are fully ensured, the heat load of each heat station can be accurately predicted, and the uneven heat supply heat loss between the heat stations and between buildings is greatly reduced.
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 needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a heat load online prediction method of a heating station in embodiment 1 of the invention;
fig. 2 is a flowchart of a heat load online prediction method of a heat station in embodiment 2 of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. 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.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
As shown in fig. 1, the embodiment of the invention provides an on-line prediction method for heat load of a heating power station, which comprises the following steps:
step S1, a room temperature monitoring module is arranged in a typical heat user room connected with each heating station, the room temperature is monitored, and room temperature data are stored;
s2, carrying out hydraulic balance adjustment on a courtyard pipe network of each heating station to enable the indoor temperature of a heating user to reach the local specified indoor temperature in a heating period;
s3, selecting a typical heating power station, and acquiring and collecting heat load data of each time period in the typical heating power station;
s4, calculating a typical heat load prediction model of the heating power station according to the data acquired in the S3;
and S5, correcting a typical heat load prediction model according to the historical heat load proportion data relation and the historical heat load data of each heat station to obtain a heat load prediction model, and carrying out online prediction on the heat load of each heat station.
Specifically, the typical heat users in step S1 are users such as the bottom layer, the middle layer and the top layer of each unit of the residential heating house, because the bottom layer building, the middle layer building and the top layer building of each building are slightly different, the users of the bottom layer, the middle layer and the top layer are respectively adopted as typical users, the room temperature is measured, the hydraulic balance effect of the subsequent pipe network is better, and the room temperature monitoring module in step S1 can be a monitoring device such as a temperature sensor.
Specifically, the hydraulic balance of the pipe network in step S2 is adjusted as follows: carrying out hydraulic balance transformation on each unit of a courtyard pipe network connected with a heating power station, and installing a remotely controllable balance valve, wherein the balance valve is matched with a temperature sensor for monitoring the return water temperature of the unit;
according to the correlation between the indoor temperature of a typical heat user and the return water temperature of the unit, a functional relation between the indoor temperature of the heating period and the return water temperature of the unit is deduced, and then a target value of the return water temperature of the unit is calculated by utilizing the local specified indoor temperature by utilizing the functional relation;
and then, using the difference value of the unit backwater temperature target value and the unit backwater temperature value measured by the temperature sensor matched with the balance valve as a feedback signal, and controlling the opening of the balance valve through PID control, so that the actual value of the unit backwater temperature approaches the unit backwater temperature target value.
The functional relation between the indoor temperature and the unit backwater temperature in the pipe network hydraulic balance adjustment is as follows:
in the formula: q h Heating Heat index (W/m) 2 )；A h -heating building area (m) 2 )；t i -room temperature (°c); t is t o -outdoor ambient temperature (°c); t is t oh -locally calculating the temperature (c) outdoors during the heating period; q (Q) rs -the building unit designs the heat supply network water flow (t/h); t (T) g -the building unit designs the water supply temperature (c) of the heat supply network; t (T) ij -the temperature (DEG C) of the return water of the jth unit of the ith building.
Specifically, in step S3, the data collection step is specifically as follows: recording the water circulation time of a courtyard pipe network heat supply network of a heating power station and the room temperature response time of a heat user through on-site experiment, determining the time period between the time point when the water heating temperature of the courtyard pipe network begins to change and the time point when the room temperature of the heat user changes and stabilizes as the PID control action interval time of a primary side regulating door of the heating power station, regulating the primary side regulating door of the heating power station when the integral multiple of one interval time is reached, and maintaining the room temperature of the user constant while the environmental temperature changes; when the field test is carried out, the heat supply load of the heating power station is calculated in real time according to the temperature difference of the water supply and return and the water flow of the heating power network, and the corresponding outdoor ambient air temperature and solar radiation intensity at the time are recorded; the data collection period in the step S3 is a heating season, so that collected data is enough, and based on the step S1 and the step S2, the collected data is more accurate, so that the data forming the thermal load prediction model can be used, and the thermal load prediction model is more accurate.
Specifically, in step S4, the method for predicting the thermal load of a typical thermal station is specifically as follows:
after achieving hydraulic balance and reaching the standard of the room temperature of a heat user, calculating historical heat load of the heating power station according to the temperature of the water supply and return and the flow meter; according to the collected data, a thermal power station thermal load calculation model is obtained through machine self-learning, and the thermal power station thermal load calculation model is substituted into each parameter value to obtain the thermal power station thermal load; the historical heat load of the heating power station is equal to the calculated heat load of the heating power station; wherein the calculation formula is as follows:
Q L ＝1.16×Q tz ×(t tg -t th )
Q L ＝Q J
in the formula: q (Q) L -thermal station historical thermal load (MW); q (Q) tz -yard pipe network heat supply network water flow (t/h); t is t tg -yard pipe network heat supply water supply temperature (°c); t is t th -yard pipe network heat supply network water backwater temperature (DEG C); PX (PX) ijk -a hot user average temperature value (°c); t is t i -the heating period locally prescribes the indoor temperature (°c); t is t o -outdoor ambient temperature (°c); r is R a -solar radiation intensity (W/m 2); r is R a.o -solar radiation intensity (W/m 2) under design conditions; q (Q) J -the thermal station calculates the thermal load (MW); q h -heating Heat index (W)/m 2 )；A h -heating building area (m) 2 ) The method comprises the steps of carrying out a first treatment on the surface of the η -adjustment coefficient (%); delta-thermal load correction value (MW);
according to the formula, the adjustment coefficient eta and the thermal load correction value delta can be obtained, and a typical thermal power station thermal load calculation model is finally obtained.
Specifically, the step of correcting the model in step S5 is specifically as follows: firstly, calculating historical heat load of each heating power station according to the temperature of water supply and return and a flow meter, storing the heat load proportion data of each heating power station of each time node according to time nodes, and storing the proportion data of all the time nodes and the actual heat load of the corresponding time node according to time sequence; then, the heat load proportion data of the earliest time node is taken, the predicted heat load of a typical heat station is calculated through a heat load prediction model of the typical heat station, then, the predicted heat load of other heat stations is obtained according to the heat load proportion data to form a predicted heat load curve, then, the predicted heat load curve is compared with an actual heat load curve formed by the actual heat loads of all heat stations, and then, the heat load prediction model of the typical heat station is adjusted to enable the predicted heat load curve to be identical with the actual heat load curve; and then continuously taking heat load proportion data and actual heat load according to the time sequence, continuously adjusting a typical heat load prediction model of the heat station, and finally correcting the heat load prediction model into a heat load prediction model of the heat station to predict the heat load of each heat station.
The method grasps the key environmental factors which influence the heat load, gets rid of factors which are difficult to master such as building characteristics, air humidity, wind direction, wind speed and the like and puzzles industry personnel, accurately and effectively predicts the heat load of the heat station, and the heat load of the heat station is mainly dynamically adjusted along with the outdoor environmental temperature change in winter and the solar radiation intensity condition, and the two variables can be monitored in real time on line, so that the intelligent on-line prediction of the heat load of the heat station can be realized.
Meanwhile, the first large step of the heat load prediction method is to realize room temperature monitoring, specifically, the step S1, the second large step is to solve the problem of hydraulic balance of a courtyard pipe network, specifically, the step S2, and the third large step is to enter specific heat load prediction, specifically, the steps S4 and S5; the room temperature monitoring device is installed in a typical heat user home, the hydraulic power of a courtyard pipe network is leveled, the problem of uneven heat and cold supply does not occur, and the heat load distribution is guaranteed, so that the historical heat load and corresponding boundary condition parameters under the condition can be used as training data of a prediction model, the accuracy and the reliability of the prediction model are fully guaranteed, the heat load of each heat station can be accurately predicted, and uneven heat supply heat loss between the heat stations and between buildings is greatly reduced.
Example 2
As shown in fig. 2, unlike embodiment 1, this embodiment further includes the steps of: and S6, searching an optimal thermal load prediction model, enabling the difference value between the actual room temperature and the target room temperature to be within +/-1.5 ℃, and then carrying out online prediction on the thermal load of each heating power station as the optimal thermal load prediction model.
Specifically, the specific steps of the step S6 are as follows: firstly programming a thermal load prediction model into a system, calculating the thermal load of a heating power station in real time according to the outdoor air temperature and the solar radiation intensity in real time, and heating, and then judging whether the thermal load prediction model is successfully established by comparing whether the difference between the actual room temperature and the target room temperature is within +/-1.5 ℃; if the difference value between the actual room temperature and the target room temperature is within the range of +/-1.5 ℃, the thermal load prediction model is considered reasonable to be shaped, and the thermal load of each heating power station is predicted on line; if the difference between the actual room temperature and the target room temperature is larger than 1.5 ℃, the method is considered unreasonable, the method enters a step S4 to correct the thermal load prediction model, and then steps S5 and S6 are carried out again until the difference between the actual room temperature and the target room temperature is within +/-1.5 ℃, model optimizing is finished, the thermal load prediction model is shaped, and the thermal load of each thermal station is predicted on line.
By searching the optimal heat load prediction model, the difference value between the actual room temperature and the target room temperature is within +/-1.5 ℃, so that the heat load can be predicted more accurately, the room temperature of residents is closer to the target room temperature, and the uneven heat supply and heat loss between heat stations and buildings are lower.
The above embodiments are only preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, but any insubstantial changes and substitutions made by those skilled in the art on the basis of the present invention are intended to be within the scope of the present invention as claimed.
Claims (10)
1. The on-line prediction method for the heat load of the heating power station is characterized by comprising the following steps of:
step S1, a room temperature monitoring module is arranged in a typical heat user room connected with each heating station, the room temperature is monitored, and room temperature data are stored;
s2, carrying out hydraulic balance adjustment on a courtyard pipe network of each heating station to enable the indoor temperature of a heating user to reach the local specified indoor temperature in a heating period;
s3, selecting a typical heating power station, and acquiring and collecting heat load data of each time period in the typical heating power station;
s4, calculating a typical heat load prediction model of the heating power station according to the data acquired in the S3;
and S5, correcting a typical heat load prediction model of the heat station according to the historical heat load proportion data relation and the historical heat load data of each heat station to obtain a heat load prediction model of the heat station, and carrying out online prediction on the heat load of each heat station.
2. The method for on-line prediction of heat load according to claim 1, wherein the typical heat users in step S1 are the bottom-layer users, middle-layer users and top-layer users of each unit of the residential heating house.
3. The method for on-line prediction of heat load according to claim 2, wherein the hydraulic balance of the pipe network in step S2 is adjusted as follows:
carrying out hydraulic balance transformation on each unit of a courtyard pipe network connected with a heating power station, and installing a remotely controllable balance valve, wherein the balance valve is matched with a temperature sensor for monitoring the return water temperature of the unit;
according to the correlation between the indoor temperature of a typical heat user and the return water temperature of the unit, a functional relation between the indoor temperature of the heating period and the return water temperature of the unit is deduced, and then a target value of the return water temperature of the unit is calculated by utilizing the local specified indoor temperature by utilizing the functional relation;
and then, using the difference value of the unit backwater temperature target value and the unit backwater temperature value measured by the temperature sensor matched with the balance valve as a feedback signal, and controlling the opening of the balance valve through PID control, so that the actual value of the unit backwater temperature approaches the unit backwater temperature target value.
4. The method for online prediction of heat load according to claim 3, wherein the functional relation between the indoor temperature and the unit backwater temperature in the hydraulic balance adjustment of the pipe network is as follows:
in the formula: q h Heating Heat index (W/m) 2 )；A h -heating building area (m) 2 )；t i -room temperature (°c); t is t o -outdoor ambient temperature (°c); t is t oh -locally calculating the temperature (c) outdoors during the heating period; q (Q) rs -the building unit designs the heat supply network water flow (t/h); t (T) g -the building unit designs the water supply temperature (c) of the heat supply network; t (T) ij -the temperature (DEG C) of the return water of the jth unit of the ith building.
5. The method according to claim 1, wherein in step S3, the data collection step is specifically as follows: recording the water circulation time of a courtyard pipe network heat supply network of a heating power station and the room temperature response time of a heat user through on-site experiment, determining the time period between the time point when the water heating temperature of the courtyard pipe network begins to change and the time point when the room temperature of the heat user changes and stabilizes as the PID control action interval time of a primary side regulating door of the heating power station, regulating the primary side regulating door of the heating power station when the integral multiple of one interval time is reached, and maintaining the room temperature of the user constant while the environmental temperature changes; and (3) carrying out a field test, calculating the heat supply load of the heating power station in real time according to the temperature difference of the primary network water supply and return and the water flow of the heating power network, and recording the corresponding outdoor ambient air temperature and solar radiation intensity at the time.
6. The method according to claim 5, wherein the data collection period in step S3 is a heating season.
7. The method according to claim 1, wherein in step S4, the method of a typical heat station heat load prediction model is specifically as follows:
after achieving hydraulic balance and reaching the standard of the room temperature of a heat user, calculating historical heat load of the heating power station according to the temperature of the water supply and return and the flow meter; according to the collected data, a thermal power station thermal load calculation model is obtained through machine self-learning, and the thermal power station thermal load calculation model is substituted into each parameter value to obtain the thermal power station thermal load; the historical heat load of the heating power station is equal to the calculated heat load of the heating power station; wherein the calculation formula is as follows:
Q L ＝1.16×Q tz ×(t tg -t th )
Q L ＝Q J
in the formula: q (Q) L -thermal station historical thermal load (MW); q (Q) tz -yard pipe network heat supply network water flow (t/h); t is t tg -yard pipe network heat supply water supply temperature (°c); t is t th -yard pipe network heat supply network water backwater temperature (DEG C); PX (PX) ijk -a hot user average temperature value (°c); t is t i -the heating period locally prescribes the indoor temperature (°c); t is t o -outdoor ambient temperature (°c); r is R a -solar radiation intensity (W/m 2); r is R a，o -solar radiation intensity (W/m 2) under design conditions; q (Q) J -the thermal station calculates the thermal load (MW); q h Heating Heat index (W/m) 2 )；A h -heating building area (m) 2 ) The method comprises the steps of carrying out a first treatment on the surface of the η -adjustment coefficient (%); delta-heat negativeLoad correction value (MW);
according to the formula, the adjustment coefficient eta and the thermal load correction value delta can be obtained, and a typical thermal power station thermal load calculation model is finally obtained.
8. The method according to claim 1, wherein the step of correcting the model in step S5 is specifically as follows:
firstly, calculating historical heat load of each heating power station according to the temperature of the water supply and return and a flowmeter, and storing according to time nodes;
calculating heat load proportion data among all heat stations of all time nodes, and storing the heat load proportion data of all time nodes and the actual heat load of the corresponding time nodes in time sequence;
then, the heat load proportion data of the earliest time node is taken, the predicted heat load of a typical heat station is calculated through a heat load prediction model of the typical heat station, then, the predicted heat load of other heat stations is obtained according to the heat load proportion data to form a predicted heat load curve, then, the predicted heat load curve is compared with an actual heat load curve formed by the actual heat loads of all heat stations, and then, the heat load prediction model of the typical heat station is adjusted to enable the predicted heat load curve to be identical with the actual heat load curve;
and then continuously taking heat load proportion data and actual heat load according to the time sequence, continuously adjusting a typical heat load prediction model of the heat station, and finally correcting the heat load prediction model into a heat load prediction model of the heat station to predict the heat load of each heat station.
9. The method for on-line prediction of thermal load according to claim 1, further comprising the steps of:
and S6, searching an optimal thermal load prediction model.
10. The method for online prediction of heat load according to claim 7, wherein the step S6 comprises the following specific steps:
firstly programming a thermal load prediction model into a system, calculating the thermal load of a heating power station in real time according to the outdoor air temperature and the solar radiation intensity in real time, and heating, and then judging whether the thermal load prediction model is successfully established by comparing whether the difference between the actual room temperature and the target room temperature is within +/-1.5 ℃;
if the difference value between the actual room temperature and the target room temperature is within the range of +/-1.5 ℃, the thermal load prediction model is considered reasonable to be shaped, and the thermal load of each heating power station is predicted on line; if the difference between the actual room temperature and the target room temperature is larger than 1.5 ℃, the method is considered unreasonable, the method enters a step S4 to correct the thermal load prediction model, and then steps S5 and S6 are carried out again until the difference between the actual room temperature and the target room temperature is within +/-1.5 ℃, model optimizing is finished, the thermal load prediction model is shaped, and the thermal load of each thermal station is predicted on line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310099611.5A CN116822682A (en) | 2023-01-31 | 2023-01-31 | Online prediction method for heat load of heating power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310099611.5A CN116822682A (en) | 2023-01-31 | 2023-01-31 | Online prediction method for heat load of heating power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116822682A true CN116822682A (en) | 2023-09-29 |
Family
ID=88139949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310099611.5A Pending CN116822682A (en) | 2023-01-31 | 2023-01-31 | Online prediction method for heat load of heating power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116822682A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117267782A (en) * | 2023-11-22 | 2023-12-22 | 瑞纳智能设备股份有限公司 | Heat supply control method and device |
-
2023
- 2023-01-31 CN CN202310099611.5A patent/CN116822682A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117267782A (en) * | 2023-11-22 | 2023-12-22 | 瑞纳智能设备股份有限公司 | Heat supply control method and device |
| CN117267782B (en) * | 2023-11-22 | 2024-02-20 | 瑞纳智能设备股份有限公司 | Heat supply control method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3614055B1 (en) | Heat supply regulation method and apparatus | |
| CN109297086B (en) | Heating power station load time-interval rolling prediction and self-adaptive correction method and system | |
| US9606168B2 (en) | Irradiance mapping leveraging a distributed network of solar photovoltaic systems | |
| CN103162346B (en) | Based on central heating supervisory control system and the central heating system control method of cloud service | |
| CN109948824B (en) | Method for predicting heat load of heating power station by using pattern recognition technology | |
| CN114396646B (en) | Heat exchange station intelligent control method based on user effective room temperature | |
| CN103363585A (en) | Regulating method of center heating system in urban area | |
| CN111578368B (en) | Heat supply pipe network hydraulic regulation and control system and intelligent control and heat supply charging method thereof | |
| CN215724029U (en) | Central air conditioning adaptive control system | |
| CN108006809B (en) | Intelligent control navigation method for cooling and heating of distributed energy station | |
| CN110909904A (en) | Terminal user load prediction system based on wireless interconnection and data mining technology | |
| CN116822682A (en) | Online prediction method for heat load of heating power station | |
| CN113446661B (en) | Intelligent and efficient heat supply network operation adjusting method | |
| CN111664502B (en) | Correction method of room temperature correction system | |
| CN112696728B (en) | Control system for balancing electric load and reducing electric capacity increase | |
| CN111765506B (en) | Intelligent pipe network control method and system | |
| CN111928459B (en) | Novel urban complex cooling and heating control device and control method thereof | |
| CN115342409B (en) | Control and regulation method and system for heating system | |
| CN113326633B (en) | All-weather analog simulation system and method for cleaning and heating | |
| CN115585501B (en) | Central heating user side autonomous regulating system and method based on network intelligent control | |
| CN114060903B (en) | Method for identifying energy-saving characteristics of thermal user behaviors of tail-end-adjustable heating system | |
| CN116753560A (en) | Method and system for heating on demand | |
| CN117329665B (en) | Air conditioner indoor linkage control method and system based on intelligent AI algorithm | |
| CN116719361A (en) | Heat supply room temperature regulating and controlling method based on temperature estimation | |
| CN117847618A (en) | Heat supply network source integrated energy storage intelligent regulation 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 |