CN113623719A - Heat exchange station prediction control method based on effective room temperature detection - Google Patents
Heat exchange station prediction control method based on effective room temperature detection Download PDFInfo
- Publication number
- CN113623719A CN113623719A CN202110700109.6A CN202110700109A CN113623719A CN 113623719 A CN113623719 A CN 113623719A CN 202110700109 A CN202110700109 A CN 202110700109A CN 113623719 A CN113623719 A CN 113623719A
- Authority
- CN
- China
- Prior art keywords
- heating
- temperature
- room temperature
- neural network
- stage
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 title claims abstract description 15
- 238000010438 heat treatment Methods 0.000 claims abstract description 118
- 238000013528 artificial neural network Methods 0.000 claims abstract description 76
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 61
- 210000000349 chromosome Anatomy 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000002068 genetic effect Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000033228 biological regulation Effects 0.000 claims description 10
- 230000006641 stabilisation Effects 0.000 claims description 8
- 238000011105 stabilization Methods 0.000 claims description 8
- 230000035772 mutation Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000014759 maintenance of location Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000008400 supply water Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005265 energy consumption Methods 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000013021 overheating Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Air Conditioning Control Device (AREA)
- Steam Or Hot-Water Central Heating Systems (AREA)
Abstract
The invention discloses a heat exchange station prediction control method based on effective room temperature detection, which relates to the technical field of heat exchange station heating control.A heating stage is divided into a heating initial stage, a heating stable stage and a heating final stage, effective room temperature feedback control is adopted in the heating initial stage and the heating final stage, heating adjusting parameters calculated according to outdoor meteorological parameters are combined with effective room temperature feedback control to operate in the heating stable stage, operating data in the heating stable stage is used as basic data of neural network training to train a neural network, and the trained neural network predicts the temperature and the heat load of secondary network water supply in the next time period; according to the characteristics of the heat exchange station in the whole heating period, feedback control is applied to the newly-built heat exchange station and the initial and final stages of heating operation, and a method combining feedback control and prediction control is performed in the stable heating period, so that the room temperature is controlled in a reasonable range in the whole heating period, the fluctuation of the room temperature of heating is reduced, and heat supply according to needs is realized.
Description
Technical Field
The invention relates to the technical field of heat exchange station heating control, in particular to a heat exchange station prediction control method based on effective room temperature detection.
Background
China's heat supply secondary network is mainly centralized regulation, the traditional control method is manually regulated according to a heat supply curve, the regulation process is carried out according to experience, and in order to ensure that the heat demand of users is met, the phenomenon of excessive overheating is obvious, the room temperature fluctuation is large, and the heat comfort quality is poor. The rise of heat supply prediction control based on machine learning provides an effective technical means for improving heat supply quality and reducing energy consumption. However, the prediction control based on machine learning needs big data support, and under the working conditions that a newly-built heat exchange station and a heat supply system are changed, the outdoor temperature at the initial stage and the final stage of heat supply is high, and the heat demand is unstable, the predicted outdoor meteorological parameters can not accurately reflect the real-time working conditions, the randomness is strong, and accurate prediction control cannot be provided under the conditions. Therefore, under the conditions of lack of data support and large working condition change, the on-demand heating of the system is difficult to realize only by means of prediction control.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a heat exchange station prediction control method based on effective room temperature detection.
The technical scheme adopted by the invention for solving the technical problem is as follows: a heat exchange station prediction control method based on effective room temperature detection is characterized in that a heating stage is divided into a heating initial stage, a heating stable stage and a heating final stage. Effective room temperature feedback control is adopted in the initial stage and the final stage of heating, heating regulation parameters calculated according to outdoor meteorological parameters are combined with the effective room temperature feedback control to operate in the heating stable period, operating data in the heating stable period are used as basic data of neural network training to train a neural network, and the trained neural network predicts the temperature and the heat load of secondary network water supply in the next time period.
Further, the heating stage is divided into an initial heating stage, a stable heating stage and a final heating stage: the outdoor temperature is higher than 5 ℃ for more than 8 hours in one day or a plurality of days after the local heating is started are taken as the initial heating period; the outdoor temperature is higher than 5 ℃ for more than 8 hours in one day or a plurality of days before the local heating is finished in one continuous week is the final heating stage, and the time period between the initial heating stage and the final heating stage is the heating stabilization stage.
Further, the effective room temperature feedback control adopted in the initial stage and the final stage of heating comprises the following steps:
s1, establishing an effective room temperature extraction calculation model of the heat exchange station:
selecting representative users to carry out room temperature detection, wherein the heating area of the representative users is not less than 3% of the total heating area, transmitting the room temperature to a centralized control unit through a wireless transmission module, carrying out data cleaning calculation through the centralized control unit, selecting the arithmetic average temperature of reasonable low-temperature users as the effective room temperature control calculation temperature, and selecting the reasonable low-temperature users participating in calculation as the room temperature of residents with the room temperature not higher than 20 ℃ and not lower than 16 ℃.
S2, establishing a feedback control model of the heat exchange station based on the effective room temperature;
the heat exchange station detects the effective room temperature as a control target, the water supply flow of the secondary network is adjusted according to the heating adjustment curve through outdoor meteorological parameters, the water supply temperature curve of the secondary network is further adjusted, and the water supply temperature of the secondary network is corrected through the difference between the effective room temperature detected by the heat exchange station and the indoor effective temperature set value.
Further, the specific step of step S2 is: the control platform of the heat exchange station provides outdoor temperature T through outdoor weather forecast according to the heating regulation curvewCalculating the temperature T of the water supply of the secondary networkgWater supply temperature T through secondary networkgInfluencing the effective Room temperature Tn. Calculating the indoor effective temperature set value TbnWith an effective room temperature TnContrast difference Δ T ═ Tbn-TnJudging whether the delta T is in the set temperature range, controlling the opening of a primary side valve or the rotating speed of a water pump through PID to control and adjust the water supply flow of a secondary network when the delta T exceeds the set value, and correcting and calculating the water supply temperature T of the secondary networkgSecondary water supply temperature curveThe following formula:
in the formula: t isgSupplying water to the secondary network at a temperature; t isnAt an effective room temperature; t iswThe outdoor temperature; b is a radiator index;
is a relative flow ratio; t isgThe' is a set value of the temperature of the water supply of the secondary network; t ish' is the set value of the backwater temperature; t isn' is the indoor temperature set point ℃; t isw' is the outdoor temperature set point ℃; f (Δ T) is a function of the effective room temperature and the indoor effective temperature setpoint.
Further, the operation of the heating regulation parameter calculated according to the outdoor meteorological parameter in combination with the effective room temperature feedback control in the heating stabilization period comprises the following steps:
s3, establishing an optimized neural network prediction model;
establishing a GA _ BP neural network, optimizing the initialization weight and the threshold of the BP neural network through a GA algorithm, wherein the required sample data comprises: temperature T of secondary net water supplygSecondary network flow G, effective room temperature TnOutdoor temperature TwThermal load Q;
s4, calculating heat supply parameters through a neural network prediction model, and calculating the temperature T of the secondary network supplied watergAnd the heat load Q is a predicted value, the flow G of the secondary network and the indoor effective temperature set value TbnOutdoor temperature TwSecondary network water supply temperature history TgThe value is an input value, and the water supply temperature parameter is controlled through a neural network prediction model;
s5, selecting the training data of the neural network, selecting the initial stage data of the heating stable period as the initial training value, inputting the operation data of the heating stable period into the neural network model in a rolling way for training, correcting the neural network, gradually improving the prediction precision, and setting the value T of the indoor effective temperaturebnWith an effective room temperature TnDifference between Δ T is carried outJudging, if delta T is kept within the set range of +/-1 ℃, the neural network prediction model is in a stable prediction control stage, and if the effective room temperature T appears continuously for a long time in the prediction control stagenExceeds the indoor effective temperature set value TbnAnd within the error range, performing prediction control in the period in combination with effective room temperature feedback control, taking the operation data in the period as supplementary data, updating the neural network prediction model data, continuing to train the neural network, and returning to the step S4 to continue prediction control after the operation data is used as supplementary data.
Further, the optimizing the initialization weight and the threshold of the BP neural network by the GA algorithm includes:
(1) initializing a BP neural network, and determining a network topological structure and training learning rules of the BP neural network;
(2) according to the network topology: the input layer → the hidden layer → the weight and the threshold number of the output layer determine the chromosome length of the genetic algorithm;
(3) initializing a genetic algorithm population and coding chromosomes;
(4) determining a fitness function of the BP neural network, and taking an error derivative based on an output node of the neural network as the fitness function;
(5) selecting genetic operation, sequencing according to the fitness function value of individuals in a group by adopting an optimal retention selection mode, and preferentially selecting the individuals with larger fitness function values to be inherited to the next generation;
(6) performing genetic operation intersection and mutation, wherein individuals adopt real number coding, and the intersection adopts a real number intersection method to perform intersection mutation on parent chromosomes to generate a offspring chromosome set;
(7) and (5) repeating the steps (5) and (6), continuously evolving the chromosomes until the fitness meets the target requirement, and decoding to obtain the optimized initial weight and threshold.
Has the advantages that: (1) the effective room temperature extraction and control ensure the heating quality and improve the thermal comfort of users;
(2) the implementation of prediction control in the heating stabilization period is combined with effective room temperature feedback control, and the method has higher practicability for building and reconstructing the heat exchange station;
(3) reasonably selecting training data according to heating stages, and rolling and training a neural network to improve the prediction precision of the neural network;
(4) and meanwhile, the temperature and the heat load of the secondary network water supply are predicted, and effective guarantee is provided for energy-saving operation and reasonable scheduling of the system.
Drawings
FIG. 1: a heat exchange station heating staging control mode;
FIG. 2: an effective room temperature feedback control schematic diagram of the heat exchange station;
FIG. 3: a schematic diagram of a neural network training process;
FIG. 4: optimizing a neural network schematic diagram;
FIG. 5: the prediction control of the heat exchange station is combined with an effective room temperature feedback control schematic diagram.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Example 1
A heat exchange station predictive control method based on effective room temperature detection improves the overall room temperature stability of central heating users and reduces the operation energy consumption, firstly, the heating characteristics are distinguished by heating stages so as to improve the precision of predictive control; the method comprises the steps that a heat supply user which is controlled in a centralized mode in a heat exchange station is provided with a wireless sensing room temperature detection device on a typical heat user, room temperature data are detected in real time, overheating users and unreasonable low-temperature users are eliminated, and effective room temperature representing the whole heat supply system is extracted through a probability statistical method. The effective room temperature is compared with the detected effective room temperature, the heat supply parameters of the heat exchange station are controlled, the detected effective room temperature fluctuates within a reasonable range of the set effective room temperature, the thermal comfort is improved, and the rate of the heat user of the whole heating system which is not guaranteed meets the requirements. The invention realizes the stable, reasonable and energy-saving operation of the whole heating period of the heating system according to the mode of combining the thermal working condition characteristics, the feedback control and the prediction control of the heating system.
Heating staging division:
as shown in figure 1, as the outdoor meteorological parameters at the beginning and end of heating are higher, and the system inspection condition exists at the beginning of heating, the heating regulation curve is invalid, the room temperature is too high, the fluctuation is large, the energy is wasted, the thermal comfort is reduced, the regularity of the formed running data is not strong, the fluctuation is large, the interference is caused to the later prediction control, and the prediction precision of the neural network model is influenced. Therefore, according to the characteristics of small thermal imbalance phenomenon in the initial and final heating periods and strong regularity in the stable heating period, the effective room temperature feedback is applied to control the water supply temperature in the initial and final heating periods so as to achieve the purposes of saving energy and stabilizing the room temperature. And the prediction control is carried out in the heating stable period, and the neural network training needs less data and has high precision. The heating staging method comprises the steps that when the temperature exceeds 8 hours in one day after the outdoor temperature is continuously maintained for one week and is higher than 5 ℃, or the temperature is at the beginning and the end of heating according to the days after the local heating is started and the days before the heating is finished, and the middle time period of the beginning and the end of heating is the middle heating period or the stable heating period.
Establishing an effective room temperature extraction calculation model of the heat exchange station;
selecting representative users for room temperature detection, wherein the heating area of the representative users is not less than 3% of the total heating area, transmitting the room temperature to a centralized control unit through a wireless transmission module, performing data cleaning calculation through the centralized control unit, selecting a reasonable low-temperature user arithmetic average temperature as an effective room temperature control calculation temperature, and selecting the reasonable low-temperature users participating in calculation as low-temperature residents who have room temperature not higher than 20 ℃ and not less than 16 ℃ and have faults removed or stop supplying; and troubleshooting the low-temperature residents at the temperature lower than 16 ℃.
Establishing a feedback control model of the heat exchange station based on the effective room temperature:
the heat exchange station detects the effective room temperature as a control target, the water supply flow of the secondary network is adjusted according to a heating adjustment curve through outdoor meteorological parameters, and then a water supply temperature curve of the secondary network is adjusted, and the water supply temperature of the secondary network is corrected through the difference between the effective room temperature detected by the heat exchange station and an indoor effective temperature set value, so that the indoor temperature is always kept in a reasonable range to operate. The feedback control model is mainly applied to the initial stage and the final stage of heating, feedback control is carried out when the deviation between the detected effective room temperature and the set effective room temperature is large in the stable heating stage, and the operation data in the period is used as the training data of the neural network to correct the neural network.
As shown in fig. 2, the feedback control of the heat exchange station specifically includes: the control platform of the heat exchange station provides outdoor temperature T through outdoor weather forecast according to the heating regulation curvewCalculating the temperature T of the water supply of the secondary networkgWater supply temperature T through secondary networkgInfluencing the effective Room temperature TnCalculating the indoor effective temperature set value TbnWith an effective room temperature TnContrast difference Δ T ═ Tbn-TnJudging whether the delta T is in the set temperature range, and correcting and calculating the temperature T of the water supply of the secondary network if the delta T exceeds the set valuegThe opening degree of a primary side valve or the rotating speed of a water pump is controlled by PID to control the water supply flow of a secondary network, and the temperature curve of the water supply of the secondary network is as follows:
in the formula: t isgSupplying water to the secondary network at a temperature; t isnAt an effective room temperature; t iswThe outdoor temperature; b is a radiator index;
is a relative flow ratio; t isgThe' is a set value of the temperature of the water supply of the secondary network; t ish' is the set value of the backwater temperature; t isn' is the indoor temperature set point ℃; t isw' is the outdoor temperature set point ℃; f (Δ T) is a function of the effective room temperature and the indoor effective temperature setpoint.
Establishing an optimized neural network prediction model:
establishing a GA _ BP (genetic algorithm combined with back propagation) neural network, optimizing the initialization weight and threshold of the BP neural network through the GA algorithm, and avoiding the situation that the prediction is inaccurate due to the fact that the neural network is trapped in local optimization, wherein the required sample data comprises: temperature T of secondary net water supplygSecondary network flow G, effective room temperature TnOutdoor temperature TwThermal load Q;
calculating heat supply parameters through a neural network prediction model:
water supply temperature T with secondary networkgAnd the heat load Q is a predicted value, the flow G of the secondary network and the indoor effective temperature set value TbnOutdoor temperature TwSecondary network water supply temperature history TgThe value is an input value, and the water supply temperature parameter is controlled through a neural network prediction model, so that the indoor temperature fluctuates in a reasonable range.
Selecting neural network training data:
selecting initial stage data of heating stable period as training initial value, rolling inputting operation data of heating stable period into neural network model for training, correcting neural network, gradually improving prediction accuracy, and setting value T of indoor effective temperaturebnWith an effective room temperature TnThe difference value delta T between the two is judged, if the delta T is kept within the set range of +/-1 ℃, the neural network prediction model is in a stable prediction control stage, and if the effective room temperature T appears continuously for a long time in the prediction control stagenExceeds the indoor effective temperature set value TbnAnd within the error range, performing prediction control in the period in combination with effective room temperature feedback control, taking the operation data in the period as supplementary data, updating the prediction model data of the neural network, continuing to train the neural network, and continuing to perform prediction control after the operation data is completed.
As in fig. 3, the neural network training process: the input parameter of the neural network is the outdoor temperature TwIndoor effective room temperature (effective room temperature T)nIndoor effective temperature set value T for trainingbnPredictive), secondary grid supply water temperature TgThe flow G and the heat load Q of the secondary network are output as predicted values of the temperature of the water supply of the secondary network
And heat load prediction
And predicting the temperature of the supply water of the secondary network, wherein the thermal load prediction provides reference for primary side scheduling in order to ensure stable room temperature operation. Because the predicted temperature and heat load of the secondary network are influenced by the parameters of the previous time period, the relationship of the given predicted parameters is shown in formulas 2 and 3Determining the relation between the prediction parameters and the input parameters by the over-correlation coefficient R;
in the formula:
the outdoor temperature, the effective room temperature and the secondary network flow in the neural network training input parameters are historical values at a single moment, and the secondary network water supply temperature and the heat load are parameters of the previous period. And the value of N in the period of time is determined by a correlation coefficient R, and the value of R is not less than 0.4. The calculation method of the R value is shown as a formula 4;
where p and q represent different variables, n represents the number of variables p and q, -1. ltoreq. R.ltoreq.1, the larger the absolute value of R the stronger the correlation, and R.ltoreq.0 the uncorrelated.
As shown in fig. 4: optimizing the initial weight and the threshold of the BP neural network by a GA algorithm so as to prevent the BP neural network from falling into local optimum, wherein the optimization process of the genetic transmission algorithm on the BP neural network is as follows:
(1) initializing a BP neural network, and determining a network topological structure and training learning rules of the BP neural network;
(2) according to the network topology: the input layer → the hidden layer → the weight and the threshold number of the output layer determine the chromosome length of the genetic algorithm;
(3) initializing a genetic algorithm population and coding chromosomes;
(4) determining a fitness function of the BP neural network, and taking an error derivative based on an output node of the neural network as the fitness function;
(5) selecting genetic operation, sequencing according to the fitness function value of individuals in a group by adopting an optimal retention selection mode, and preferentially selecting the individuals with larger fitness function values to be inherited to the next generation;
(6) performing genetic operation intersection and mutation, wherein individuals adopt real number coding, and the intersection adopts a real number intersection method to perform intersection mutation on parent chromosomes to generate a offspring chromosome set;
(7) and (5) repeating the steps (5) and (6), continuously evolving the chromosomes until the fitness meets the target requirement, and decoding to obtain the optimized initial weight and threshold.
As shown in fig. 5, the predictive control of the heat exchange station combines the feedback control principle: on the basis of the original effective room temperature feedback control, a neural network prediction model is added in a control platform, the control is carried out by means of mainly predictive control and secondarily feedback control in the heating stabilization period, and the feedback control only occurs when the deviation between the indoor effective temperature set value and the detected effective room temperature exceeds the allowable range. The operation process of the heat exchange station also changes along with the change of the equipment performance and the heat user, and real-time meteorological parameters can not be truly reflected by meteorological prediction, so certain deviation can be brought to the operation. When the accuracy of the water supply predicted temperature is evaluated, the difference value delta T between the indoor effective temperature set value and the detected effective room temperature is compared to directly judge the action target, so that the condition that the model is unstable due to complex dynamic disturbance in the operation process and deviation existing in meteorological prediction in operation can be avoided.
The overall control flow summarized by the invention is that feedback control is adopted at the beginning and the end of heating, and the purpose of saving energy is achieved by further reducing the water supply temperature or reducing the flow through the feedback control. In the early and late stages of heating, due to the fact that outdoor temperature is high, heating operation data are not obvious in regularity, interference is caused to prediction control of a neural network, and prediction accuracy is affected. In the primary stage of starting to operate in the heating stable period, the heating regulation parameters calculated according to outdoor meteorological parameters are still combined with effective room temperature feedback control to operate, and the parameters operated in the period are used as basic data of neural network training to train the neural network. Well-trained neural network forecasts outdoor temperature T through weatherwIndoor effective temperature set value TbnSecondary network flow G, heat load Q and secondary water supply temperature historical value TgPredicting the temperature T of the secondary network water supply in the next time periodgAnd a thermal load Q. Setting indoor effective temperature T during prediction operationbnAnd detecting the effective room temperature TnAs a comparison value, if the temperature difference Δ T between the two is kept within a set range of ± 1 ℃, the neural networkThe net prediction model is in a stable prediction control phase. If the detected effective room temperature exceeds the error range of the set value continuously and long-term appears in the prediction control stage, a prediction control and feedback control mode is implemented in the period, the operation data in the period is used as the sample data of the updated neural network, the neural network is updated on the basis of the previous neural network training, and the prediction control is returned to continue. In the heating stabilization period, the neural network prediction model can accurately predict the water supply control temperature, so that the heating is more stable, the corresponding energy consumption can be simultaneously predicted, accurate guidance is provided for one-time network scheduling, and the energy-saving purpose of accurate control and heating as required is realized.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (6)
1. A heat exchange station prediction control method based on effective room temperature detection is characterized in that a heating stage is divided into a heating initial stage, a heating stable stage and a heating final stage, effective room temperature feedback control is adopted in the heating initial stage and the heating final stage, heating adjusting parameters calculated according to outdoor meteorological parameters are combined with the effective room temperature feedback control to operate in the heating stable stage, operating data in the heating stable stage are used as basic data of neural network training to train a neural network, and the trained neural network predicts the temperature and the heat load of secondary network water supply in the next time period.
2. The predictive control method for the heat exchange station based on the effective room temperature detection as claimed in claim 1, wherein the heating stage is divided into a heating initial stage, a heating stabilization stage and a heating final stage as follows: the outdoor temperature is higher than 5 ℃ for more than 8 hours in one day or a plurality of days after the local heating is started are taken as the initial heating period; the outdoor temperature is higher than 5 ℃ for more than 8 hours in one day or a plurality of days before the local heating is finished in one continuous week is the final heating stage, and the time period between the initial heating stage and the final heating stage is the heating stabilization stage.
3. The predictive control method for the heat exchange station based on the effective room temperature detection as claimed in claim 1, wherein the feedback control of the effective room temperature in the initial heating stage and the final heating stage comprises:
s1, establishing an effective room temperature extraction calculation model of the heat exchange station:
selecting representative users to carry out room temperature detection, wherein the heating area of the representative users is not less than 3% of the total heating area, transmitting the room temperature to a centralized control unit through a wireless transmission module, carrying out data cleaning calculation through the centralized control unit, selecting the arithmetic average temperature of reasonable low-temperature users as the effective room temperature control calculation temperature, and selecting the reasonable low-temperature users participating in calculation as the temperature of residents with the room temperature not higher than 20 ℃ and not lower than 16 ℃.
S2, establishing a feedback control model of the heat exchange station based on the effective room temperature;
the heat exchange station detects the effective room temperature as a control target, the water supply flow of the secondary network is adjusted according to the heating adjustment curve through outdoor meteorological parameters, the water supply temperature curve of the secondary network is further adjusted, and the water supply temperature of the secondary network is corrected through the difference between the effective room temperature detected by the heat exchange station and the indoor effective temperature set value.
4. The method for predictive control of a heat exchange station based on effective room temperature detection as claimed in claim 3, wherein the specific steps of the step S2 are as follows: the control platform of the heat exchange station provides outdoor temperature T through outdoor weather forecast according to the heating regulation curvewCalculating the temperature T of the water supply of the secondary networkgWater supply temperature T through secondary networkgInfluencing the effective Room temperature TnCalculating the indoor effective temperature set value TbnWith an effective room temperature TnContrast difference Δ T ═ Tbn-TnJudging whether the delta T is in the set temperature range, controlling the opening of a primary side valve or the rotating speed of a water pump to control and regulate the water supply flow of a secondary network through PID if the delta T is beyond the set value, and correcting and calculatingTemperature T of secondary net water supplygThe temperature curve of the supply water of the secondary net is as follows:
in the formula: t isgSupplying water to the secondary network at a temperature; t isnAt an effective room temperature; t iswThe outdoor temperature; b is a radiator index;
is a relative flow ratio; t isgThe' is a set value of the temperature of the water supply of the secondary network; t ish' is the set value of the backwater temperature; t isn' is the indoor temperature set point ℃; t isw' is the outdoor temperature set point ℃; f (Δ T) is a function of the effective room temperature and the indoor effective temperature setpoint.
5. The predictive control method for a heat exchange station based on efficient room temperature sensing as claimed in claim 3, wherein said operating with heating regulation parameters calculated from outdoor meteorological parameters in combination with efficient room temperature feedback control during heating stabilization period comprises:
s3, establishing an optimized neural network prediction model;
establishing a GA _ BP neural network, optimizing the initialization weight and the threshold of the BP neural network through a GA algorithm, wherein the required sample data comprises: temperature T of secondary net water supplygSecondary network flow G, effective room temperature TnOutdoor temperature TwThermal load Q;
s4, calculating heat supply parameters through a neural network prediction model, and calculating the temperature T of the secondary network supplied watergAnd the heat load Q is a predicted value, the flow G of the secondary network and the indoor effective temperature set value TbnOutdoor temperature TwSecondary network water supply temperature history TgThe value is an input value, and the water supply temperature parameter is controlled through a neural network prediction model;
s5, selecting the training data of the neural network, and selecting the initial stage data of the heating stable period as the training initialRolling the operation data of heating stable period into the neural network model for training, correcting the neural network, gradually increasing the prediction precision, and setting the indoor effective temperaturebnWith an effective room temperature TnThe difference value delta T between the two is judged, if the delta T is kept within the set range of +/-1 ℃, the neural network prediction model is in a stable prediction control stage, and if the effective room temperature T appears continuously for a long time in the prediction control stagenExceeds the indoor effective temperature set value TbnAnd within the error range, performing prediction control in the period in combination with effective room temperature feedback control, taking the operation data in the period as supplementary data, updating the neural network prediction model data, continuing to train the neural network, and returning to the step S4 to continue prediction control after the operation data is used as supplementary data.
6. The method as claimed in claim 5, wherein the optimizing the initialization weight and the threshold of the BP neural network by the GA algorithm comprises:
(1) initializing a BP neural network, and determining a network topological structure and training learning rules of the BP neural network;
(2) according to the network topology: the input layer → the hidden layer → the weight and the threshold number of the output layer determine the chromosome length of the genetic algorithm;
(3) initializing a genetic algorithm population and coding chromosomes;
(4) determining a fitness function of the BP neural network, and taking an error derivative based on an output node of the neural network as the fitness function;
(5) selecting genetic operation, sequencing according to the fitness function value of individuals in a group by adopting an optimal retention selection mode, and preferentially selecting the individuals with larger fitness function values to be inherited to the next generation;
(6) performing genetic operation intersection and mutation, wherein individuals adopt real number coding, and the intersection adopts a real number intersection method to perform intersection mutation on parent chromosomes to generate a offspring chromosome set;
(7) and (5) repeating the steps (5) and (6), continuously evolving the chromosomes until the fitness meets the target requirement, and decoding to obtain the optimized initial weight and threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110700109.6A CN113623719B (en) | 2021-06-23 | 2021-06-23 | Heat exchange station prediction control method based on effective room temperature detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110700109.6A CN113623719B (en) | 2021-06-23 | 2021-06-23 | Heat exchange station prediction control method based on effective room temperature detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113623719A true CN113623719A (en) | 2021-11-09 |
| CN113623719B CN113623719B (en) | 2022-08-19 |
Family
ID=78378327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110700109.6A Expired - Fee Related CN113623719B (en) | 2021-06-23 | 2021-06-23 | Heat exchange station prediction control method based on effective room temperature detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113623719B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114165825A (en) * | 2021-11-26 | 2022-03-11 | 南京国之鑫科技有限公司 | Heat supply regulation and control system and method for heat exchange station |
| CN114396646A (en) * | 2021-12-27 | 2022-04-26 | 大连海心信息工程有限公司 | Heat exchange station intelligent control method based on user effective room temperature |
| CN114777191A (en) * | 2022-04-19 | 2022-07-22 | 山东科技大学 | Heating system household valve regulating and controlling method based on neural network algorithm |
| CN114857659A (en) * | 2022-06-02 | 2022-08-05 | 南京工业大学 | Heat exchange station secondary network water supply temperature control algorithm based on segmented RC model |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101074790A (en) * | 2006-05-17 | 2007-11-21 | 大连金太阳科技开发有限公司 | Combined regulating method for heating room by heating net as resource |
| CN104791903A (en) * | 2015-04-30 | 2015-07-22 | 北京上庄燃气热电有限公司 | Intelligent heating network dispatching system |
| CN105805822A (en) * | 2016-03-24 | 2016-07-27 | 常州英集动力科技有限公司 | Heat supply energy saving control method and system based on neural network prediction |
| JP2016161251A (en) * | 2015-03-04 | 2016-09-05 | アズビル株式会社 | Peak power development prediction device and prediction method |
| CN107239859A (en) * | 2017-06-05 | 2017-10-10 | 国网山东省电力公司电力科学研究院 | The heating load forecasting method of Recognition with Recurrent Neural Network is remembered based on series connection shot and long term |
| CN107491020A (en) * | 2017-08-13 | 2017-12-19 | 中清源环保节能有限公司 | A kind of central heating intelligence managing and control system |
| JP2017223394A (en) * | 2016-06-14 | 2017-12-21 | 株式会社東芝 | Heat demand restraint device, heat demand restraint method, and program |
| CN108256672A (en) * | 2017-12-27 | 2018-07-06 | 北京四方继保自动化股份有限公司 | A kind of central heating system the whole network balance adjusting method |
| CN109340899A (en) * | 2018-10-10 | 2019-02-15 | 哈尔滨工业大学 | The prediction technique of severe cold area winter indoor thermal comfort temperature based on hot adaptability |
| CN109740803A (en) * | 2018-12-24 | 2019-05-10 | 北京航天智造科技发展有限公司 | A kind of heating network operation optimization method of data-driven |
| KR102046280B1 (en) * | 2019-03-28 | 2019-11-18 | 주식회사 알리오코리아 | Air flow controlling apparatus working as the air circulator or ventilation apparatus |
| CN110909904A (en) * | 2018-09-17 | 2020-03-24 | 济南热力集团有限公司 | Terminal user load prediction system based on wireless interconnection and data mining technology |
| KR20200092478A (en) * | 2019-01-09 | 2020-08-04 | 영남대학교 산학협력단 | Method for controlling economizer air conditioning system |
| CN112128841A (en) * | 2020-09-29 | 2020-12-25 | 河北工业大学 | Whole-network balance adjusting method based on load prediction and room temperature feedback correction |
| CN112541213A (en) * | 2020-12-02 | 2021-03-23 | 北京工业大学 | Modeling method of water temperature prediction model of heating system and water temperature control strategy |
| CN112594758A (en) * | 2020-11-21 | 2021-04-02 | 唐山曹妃甸热力有限公司 | Heat supply prediction method, device, equipment and storage medium |
| CN112712189A (en) * | 2019-10-25 | 2021-04-27 | 北京市热力集团有限责任公司 | Heat supply demand load prediction method |
-
2021
- 2021-06-23 CN CN202110700109.6A patent/CN113623719B/en not_active Expired - Fee Related
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101074790A (en) * | 2006-05-17 | 2007-11-21 | 大连金太阳科技开发有限公司 | Combined regulating method for heating room by heating net as resource |
| JP2016161251A (en) * | 2015-03-04 | 2016-09-05 | アズビル株式会社 | Peak power development prediction device and prediction method |
| CN104791903A (en) * | 2015-04-30 | 2015-07-22 | 北京上庄燃气热电有限公司 | Intelligent heating network dispatching system |
| CN105805822A (en) * | 2016-03-24 | 2016-07-27 | 常州英集动力科技有限公司 | Heat supply energy saving control method and system based on neural network prediction |
| JP2017223394A (en) * | 2016-06-14 | 2017-12-21 | 株式会社東芝 | Heat demand restraint device, heat demand restraint method, and program |
| CN107239859A (en) * | 2017-06-05 | 2017-10-10 | 国网山东省电力公司电力科学研究院 | The heating load forecasting method of Recognition with Recurrent Neural Network is remembered based on series connection shot and long term |
| CN107491020A (en) * | 2017-08-13 | 2017-12-19 | 中清源环保节能有限公司 | A kind of central heating intelligence managing and control system |
| CN108256672A (en) * | 2017-12-27 | 2018-07-06 | 北京四方继保自动化股份有限公司 | A kind of central heating system the whole network balance adjusting method |
| CN110909904A (en) * | 2018-09-17 | 2020-03-24 | 济南热力集团有限公司 | Terminal user load prediction system based on wireless interconnection and data mining technology |
| CN109340899A (en) * | 2018-10-10 | 2019-02-15 | 哈尔滨工业大学 | The prediction technique of severe cold area winter indoor thermal comfort temperature based on hot adaptability |
| CN109740803A (en) * | 2018-12-24 | 2019-05-10 | 北京航天智造科技发展有限公司 | A kind of heating network operation optimization method of data-driven |
| KR20200092478A (en) * | 2019-01-09 | 2020-08-04 | 영남대학교 산학협력단 | Method for controlling economizer air conditioning system |
| KR102046280B1 (en) * | 2019-03-28 | 2019-11-18 | 주식회사 알리오코리아 | Air flow controlling apparatus working as the air circulator or ventilation apparatus |
| CN112712189A (en) * | 2019-10-25 | 2021-04-27 | 北京市热力集团有限责任公司 | Heat supply demand load prediction method |
| CN112128841A (en) * | 2020-09-29 | 2020-12-25 | 河北工业大学 | Whole-network balance adjusting method based on load prediction and room temperature feedback correction |
| CN112594758A (en) * | 2020-11-21 | 2021-04-02 | 唐山曹妃甸热力有限公司 | Heat supply prediction method, device, equipment and storage medium |
| CN112541213A (en) * | 2020-12-02 | 2021-03-23 | 北京工业大学 | Modeling method of water temperature prediction model of heating system and water temperature control strategy |
Non-Patent Citations (2)
| Title |
|---|
| FRAUKE OLDEWURTEL: "Use of model predictive control and weather forecasts for energy efficient building climate control", 《ENERGY AND BUILDINGS》, vol. 45, 31 December 2012 (2012-12-31), pages 15 - 27, XP028355630, DOI: 10.1016/j.enbuild.2011.09.022 * |
| YICHI ZHANG: "Field tests on the operational energy consumption of Chinese district heating systems and evaluation of typical associated problems", 《ENERGY & BUILDINGS》, vol. 224, 1 July 2020 (2020-07-01), pages 110269 - 110285 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114165825A (en) * | 2021-11-26 | 2022-03-11 | 南京国之鑫科技有限公司 | Heat supply regulation and control system and method for heat exchange station |
| CN114396646A (en) * | 2021-12-27 | 2022-04-26 | 大连海心信息工程有限公司 | Heat exchange station intelligent control method based on user effective room temperature |
| CN114396646B (en) * | 2021-12-27 | 2023-04-07 | 大连海心信息工程有限公司 | Heat exchange station intelligent control method based on user effective room temperature |
| CN114777191A (en) * | 2022-04-19 | 2022-07-22 | 山东科技大学 | Heating system household valve regulating and controlling method based on neural network algorithm |
| CN114857659A (en) * | 2022-06-02 | 2022-08-05 | 南京工业大学 | Heat exchange station secondary network water supply temperature control algorithm based on segmented RC model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113623719B (en) | 2022-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113623719B (en) | Heat exchange station prediction control method based on effective room temperature detection | |
| CN112128841B (en) | Whole-network balance adjusting method based on load prediction and room temperature feedback correction | |
| CN109270842B (en) | Bayesian network-based regional heat supply model prediction control system and method | |
| CN108916986B (en) | Information physical fusion secondary pipe network variable flow hydraulic balance regulation and control method and system | |
| CN112186811B (en) | AGC unit dynamic optimization method based on deep reinforcement learning | |
| CN110878959B (en) | Building temperature control method and system based on model predictive control | |
| CN109948824A (en) | A method of thermal substation thermic load is predicted using mode identification technology | |
| CN110673482B (en) | Power station coal-fired boiler intelligent control method and system based on neural network prediction | |
| CN117093823B (en) | Factory energy consumption management method based on data analysis | |
| CN111811016B (en) | Method and system for adjusting hydraulic balance among units of heating unit | |
| CN113110057A (en) | Heating power station energy-saving control method based on artificial intelligence and intelligent decision system | |
| CN116907036A (en) | Deep reinforcement learning water chilling unit control method based on cold load prediction | |
| CN114484556B (en) | Water supply temperature regulation and control method based on target energy consumption management and control | |
| CN107247407B (en) | Big data self-learning correction control system and method based on cloud architecture | |
| CN116436033A (en) | Temperature control load frequency response control method based on user satisfaction and reinforcement learning | |
| CN112330012A (en) | Building energy consumption prediction method and equipment based on transfer learning | |
| CN113110056B (en) | Heat supply intelligent decision-making method and intelligent decision-making machine based on artificial intelligence | |
| CN114722693A (en) | Optimization method of two-type fuzzy control parameter of water turbine regulating system | |
| CN113390126B (en) | Heating station online dynamic regulation and control device and method based on room temperature feedback | |
| CN116149401B (en) | System and method for controlling outlet temperature of heat exchanger of compressed air energy storage power station | |
| CN105511270B (en) | A kind of PID controller parameter optimization method and system based on coevolution | |
| CN114282445A (en) | Circulating water system operation optimization method and related equipment | |
| CN115526504A (en) | Energy-saving scheduling method and system for water supply system of pump station, electronic equipment and storage medium | |
| CN111043720B (en) | Low-cost robustness adjustment strategy making method of refrigeration system under load uncertainty | |
| CN113203118A (en) | Room temperature control system and room temperature control method based on fuzzy control |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230703 Address after: No. 8 Qingyuan Road, Dalian Development Area, Jinzhou District, Dalian, Liaoning 116600 Patentee after: Dalian Kaire branch of Northeast Electric Power Co., Ltd. of State Power Investment Group Patentee after: National electric investment group Northeast Electric Power Co.,Ltd. Address before: 116600 No. 8 Qingyuan Road, Dalian Economic and Technological Development Zone, Liaoning Province Patentee before: Dalian Kaire branch of Northeast Electric Power Co., Ltd. of State Power Investment Group |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220819 |