CN116379576B - Energy-saving bottom line optimizing method for heating air-conditioning system based on big data self-learning - Google Patents
Energy-saving bottom line optimizing method for heating air-conditioning system based on big data self-learning Download PDFInfo
- Publication number
- CN116379576B CN116379576B CN202310555811.7A CN202310555811A CN116379576B CN 116379576 B CN116379576 B CN 116379576B CN 202310555811 A CN202310555811 A CN 202310555811A CN 116379576 B CN116379576 B CN 116379576B
- Authority
- CN
- China
- Prior art keywords
- value
- turning
- temperature
- current
- circulating pump
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 142
- 238000010438 heat treatment Methods 0.000 title claims abstract description 48
- 238000004378 air conditioning Methods 0.000 title claims abstract description 42
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 140
- 238000005265 energy consumption Methods 0.000 claims abstract description 47
- 238000012544 monitoring process Methods 0.000 claims abstract description 34
- 238000004873 anchoring Methods 0.000 claims abstract description 11
- 230000007812 deficiency Effects 0.000 claims abstract description 6
- 238000005070 sampling Methods 0.000 claims description 68
- 238000004364 calculation method Methods 0.000 claims description 48
- 230000002349 favourable effect Effects 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 230000002411 adverse Effects 0.000 claims description 11
- 238000013461 design Methods 0.000 claims description 10
- 230000001105 regulatory effect Effects 0.000 claims description 8
- 230000001960 triggered effect Effects 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 abstract description 4
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 230000009471 action Effects 0.000 description 4
- 239000003795 chemical substances by application Substances 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002898 library design Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000002787 reinforcement Effects 0.000 description 2
- 230000003827 upregulation Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/46—Improving electric energy efficiency or saving
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/80—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air
- F24F11/83—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers
- F24F11/85—Control systems characterised by their outputs; Constructional details thereof for controlling the temperature of the supplied air by controlling the supply of heat-exchange fluids to heat-exchangers using variable-flow pumps
-
- 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)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the technical field of energy-saving methods of heating and air conditioning systems, in particular to a method for optimizing an energy-saving bottom line of a heating and air conditioning system based on big data self-learning, which comprises the following steps: step one: establishing a least disadvantageous bottom line method of the circulating pump frequency according to a set rule; step two: according to the initialized characteristic model and the reference result of the step one, an intelligent monitoring method for the heat supply experience deficiency is established to serve as a basis for anchoring the current heat supply demand; self-feature learning can be perfected according to human intervention; step three: learning and iterating to find the optimal temperature of hot water outlet in different temperature intervals; step four: and in different temperature intervals, learning and iterating to find the optimal combination of the hot water outlet temperature and the circulating pump frequency, so that the energy consumption of the circulating pump under the current supply and demand conditions is the lowest. The invention aims to realize the automatic control of the energy-saving bottom line optimizing method of the heat source air conditioning system by establishing big data self-learning logic through the fusion of the supply side, the demand side and the environmental data.
Description
Technical Field
The invention relates to the technical field of energy-saving methods of heating and air conditioning systems, in particular to a method for optimizing an energy-saving bottom line of a heating and air conditioning system based on big data self-learning.
Background
The demand load of the general building heat supply air conditioning system is smaller than the design load, and the air conditioning system is required to operate under partial load in most of time according to the influence of factors such as different temperature and humidity environments in heating seasons. Therefore, according to the changes of meteorological conditions and the load of the tail end air conditioner, the reasonable hot water supply temperature is determined, and the operation of changing the water temperature to the water temperature by dividing the boundary between the regions, namely, adopting different hot water outlet temperatures of the boiler in different environmental condition segments, the operation energy consumption can be reduced, and the purpose of energy-saving operation is achieved.
The typical heating air conditioning system at present mainly comprises a main machine room at a supply side, a back transmission pipeline, a fan coil at a demand side and the like, wherein the main machine room mainly comprises a heat source system, a hot water circulating system and the like, and mainly comprises equipment components such as a boiler 100, a circulating pump 200, a water collector 300, a water separator 400, a regulating valve, a switching valve and the like. A typical host machine room structure is shown in fig. 1.
The energy consumption of the whole heating air conditioning system mainly comprises the power consumption of a boiler on the main machine side, the power consumption of a circulating pump, the power consumption of a fan in a tail end fan coil, and the like, wherein the power consumption on the main machine side accounts for a main part, so that the regulation and control of the power consumption data on the main machine side are key to the energy-saving control of the heating air conditioning system.
At present, whether the air conditioning system manufacturer or the third party energy-saving transformation service provider exists in the market, the control modes of the host side can be classified into two types:
the first is a fuzzy matching control method, which realizes a fuzzy matching calculation method on a site automatic control system and operates the fuzzy matching calculation method, and mainly adjusts the hot water outlet temperature of a boiler, the opening number of a circulating pump, the operating frequency and the like according to key parameters such as the temperature difference, the pressure difference, the flow and the like of water supply and return in the system, thereby realizing the self-adaptive adjustment operation of the system in a standard working condition boundary.
The second type is a manual experience control method, which sets the starting number and the running frequency of a circulating pump in a certain time period and the starting number and the water outlet temperature of a boiler according to the factors of seasons, environment, management reality and the like, so as to realize the self-adaptive adjustment operation of the system in manual experience setting.
Both of the above approaches can achieve a degree of energy saving control, but have some drawbacks and limitations.
The whole heating air conditioning system is basically energy supply and use, basically follows energy conservation, controls the starting and frequency modulation of a circulating pump and the starting and temperature adjustment of a boiler, and the core is the bottom line demand of an anchoring end, so that an optimal knowledge model for controlling the combination is searched for and a control calculation method is established. Therefore, how to actively quantify the demand of the anchoring terminal on the energy supply days under different environments, dynamically cooperatively controlling the optimal balance working condition of the terminal side and the host side, and searching and controlling the optimal setting combination on the host side on the basis of the demand, so that the total energy consumption of the system is the lowest, is the key for evaluating the control logic.
The first mode is based on the temperature difference, pressure difference, flow and the like of backwater, the temperature difference, the pressure difference and the like are known to be feedback variables of the change of the tail end energy using superposition environment, and are very core reference factors for control, but the method has obvious hysteresis, and is generally transmitted to a host side to have delay of half an hour or more, and after capturing the change factors, the host side triggers a control action, the state of the tail end possibly has changed, the control at the moment obviously cannot guarantee that the host side and the tail end side are in the optimal energy-saving operation working condition, and meanwhile, because the mode cannot quantify the tail end requirement, only balance control under the mode of relative feedback quantity can be realized;
the second type of mode is manual strategy control, which is simpler than the previous first type of control mode, has thicker granularity, can not be dynamically regulated and controlled according to the non-communication environment condition, has a control refining effect which is inferior to that of the first type, and can not ensure that the host side and the tail end side are in the optimal energy-saving operation working condition.
The two modes are not used for capturing and collecting the tail end data, and the tail end side energy consumption requirement cannot be defined quantitatively, so that the supply and demand coordination cannot be achieved, and the purpose of automatic control of the energy consumption base line is achieved.
Then, whether a data fusion platform can be established from the perspective of big data fusion based on cross-border thinking or not, firstly, two-side data are opened, different temperature and humidity environments are searched on the basis, a single energy supply day is taken as a unit, the maximum demand is anchored based on the end-side demand change, a knowledge model is set by correspondingly establishing an optimal control combination with the host side, reinforcement learning logic is assisted, self-learning is carried out in a 'trial and error' mode, and the self-control of the energy-saving bottom line optimizing method of the heating air-conditioning system based on big data self-learning is realized.
Disclosure of Invention
The invention mainly solves the defects and limitations of the fuzzy matching control method and the manual experience control method of the existing heat source air conditioning system, namely, because the data flows of the environment at both supply and demand sides are not communicated and shared, the control granularity is thicker because the rule is established only by self-lag feedback data or the manual configuration rule is identified by experience, and the total energy bias redundancy of each energy supply day is sufficient, so that the total energy consumption of the heat source system is greatly wasted. The invention aims to realize the automatic control of the energy-saving bottom line optimizing method of the heat source air conditioning system by establishing big data self-learning logic through the fusion of the supply side, the demand side and the environmental data.
In order to solve the technical problems, the invention provides a heat supply air conditioning system energy-saving bottom line optimizing method based on big data self-learning, which comprises the following steps:
step one: according to a set rule, a method for establishing the bottom line with the least adverse frequency of the circulating pump is established, the calculation result of the method is used as the bottom frequency of the circulating pump, and a circulating pump frequency control model is maintained; the space conditions can be manually supplemented to optimize the calculation result of the method;
the most disadvantageous bottom line method comprises the following steps:
starting;
s101: judging whether the central air conditioner host is started, if so, turning to S102, otherwise turning to S301;
s102: judging whether the record of the state=0 of the knowledge base (1) meets 5 records, if so, updating the highest numerical value of the circulating pump frequency of the 5 records to a field of < least-favored space minimum frequency > of the model base (2), turning to S301, otherwise turning to S103;
s103: judging whether the lowest temperature value of the current day is correspondingly recorded in the knowledge base (1), if so, turning to S301, otherwise turning to S104;
s104: judging whether the sampling library (2) has manually recorded data records, if so, turning to S106, otherwise turning to S105;
s105: judging that the current indoor air conditioner on-rate is more than or equal to 80%, if yes, turning to S106, otherwise turning to S301;
S106: memorizing the current hot water outlet temperature and the circulating pump frequency, setting the hot water outlet temperature as a control upper limit value, setting the circulating pump frequency as a highest value, and turning to S107;
s107: transferring the least unfavorable space interface, if the judging result is=0, transferring to S108, if the judging result is=1, recording the optimal frequency value=the current-period frequency value+1Hz, transferring to S201, otherwise transferring to S301;
s108: updating the current data to the knowledge base (1), setting the status field to-1, and turning to S109;
s109: judging whether the frequency-1 of the circulating pump is larger than or equal to the control lower limit value, if so, setting the current frequency of the circulating pump to be-1 Hz, turning to S107, otherwise, recording the optimal frequency value = control lower limit value, turning to S201;
s201: updating the current data and the optimal frequency value to a knowledge base (1), setting the current record state field as 1, setting the last record state field from-1 to 0, restoring and memorizing the current hot water outlet temperature and the circulating pump frequency, and turning to S301;
s301: ending;
step two: according to the initialized characteristic model and the reference result of the step one, an intelligent monitoring method for the heat supply experience deficiency is established to serve as a basis for anchoring the current heat supply demand; self-feature learning can be perfected according to human intervention;
the intelligent monitoring method for the insufficient heat supply experience comprises the following steps:
Starting;
s101: judging whether the running frequency of the circulating pump is larger than or equal to a bottom line value obtained by a bottom line method with the least adverse frequency of the circulating pump, if so, turning to S102, otherwise, outputting-1, and turning to S301;
s102: judging whether the sampling library (4) has unprocessed records with the state=0, if so, turning to S103, otherwise turning to S201;
s103: judging whether the set temperature of all room air conditioners in the untreated record is higher than 20 ℃, if so, turning to S105, otherwise turning to S104;
s104: uniformly setting the set temperature of the room air conditioner to be less than 20 ℃ to 26 ℃, and turning to S105 after 15 minutes;
s105: judging whether the indoor temperature of the air conditioner in all rooms is more than or equal to 20 ℃, if so, outputting 10, updating the current operation parameter data to a sampling library (8), wherein the field state of the < characteristic rule calculation result > is 10, and turning to S301; otherwise, outputting 11, namely updating the current operation parameter data to a sampling library (8), wherein the field state of the < feature rule calculation result > is 11, and turning to S301;
s201: judging the proportion of the number of air conditioners with the current set temperature being more than 20 ℃ and the indoor temperature being less than 20 ℃ to the total number, if the current set temperature is more than 1%, updating the current operation parameter data to a sampling library (5), turning to S202, otherwise outputting 20, updating the current operation parameter data to the sampling library (8), turning to S301, wherein the field state of the < characteristic rule calculation result > is 20;
S202: judging whether the current average indoor set temperature is less than 20 ℃, if yes, updating the current operation parameter data to a sampling library (6), turning to S203, otherwise outputting 20, updating the current operation parameter data to a sampling library (8), and turning to S301, wherein the field state of the < feature rule calculation result > is 20;
s203: judging that the quantity of the set temperature of the air conditioner is manually up-regulated in the last 30 minutes and accounts for the proportion of the total quantity, if the quantity is more than 1%, updating the current operation parameter data to a sampling library (7), turning to S204, otherwise outputting 20, updating the current operation parameter data to the sampling library (8), and turning to S301, wherein the field state of the < feature rule calculation result > is 20;
s204: updating the current operation parameter data to a sampling library (8), wherein the field state of the < feature rule calculation result > is 21, outputting 21, and turning to S301;
s301: ending;
step three: in different temperature intervals, learning and iterating to find the optimal temperature of hot water outlet, so that the outlet water temperature meeting the current supply and demand conditions is the lowest, and maintaining a knowledge base and an optimal model; in the control operation stage, the method is adjusted in a linkage way along with the intelligent monitoring method for insufficient heat supply experience;
the hot water outlet temperature base line intelligent optimizing method comprises the following steps:
Starting;
s101: judging whether a central air conditioning system host is started or not, if so, turning to S102, otherwise, turning to S201;
s102: judging whether the current lowest temperature has matched records in the knowledge base (3), if not, turning to S1021, if so, turning to S1022, otherwise turning to S201;
s1021: judging whether a record which is smaller than the current minimum temperature and is matched with the current minimum temperature exists in the knowledge base (3), if not, the current hot water outlet temperature value is initially a control upper limit value, and if so, the current hot water outlet temperature value is initially a knowledge record parameter value corresponding to the closest temperature value, and turning to S103;
s1022: taking the latest knowledge record, judging whether the corresponding hot water temperature field value is less than or equal to the control lower limit value, if so, initially setting the current hot water outlet temperature value as the control lower limit value, and if not, initially setting the current hot water outlet temperature value as the hot water temperature field value of-0.5 ℃, and turning to S103;
s103: setting the frequency value of the circulating pump as a control upper limit value, and turning to S104 after 30 minutes;
s104: invoking < insufficient heating experience monitoring method >, turning to S1041 if the result is equal to 11 or 21, and turning to S1042 if the result is equal to 10 or 20;
s1041: updating the current operation parameter data to a knowledge base (3), wherein the current record < state > field value is 1, the last adjacent record < state > field value is 0, simultaneously, synchronously updating the record corresponding to the < state > field updated to 0 to a model base (1), updating the corresponding < hot water optimal water outlet temperature > field to the corresponding water outlet temperature value, updating the < state > field value to 1, and turning to S201;
S1042: if the central air conditioning system host is shut down, the step S105 is carried out, and if not, the step S104 is carried out;
s105: updating the current operation parameter data to a knowledge base (3), wherein the current record < state > field value is-1, and turning to S201;
s201: ending;
step four: based on the knowledge base and the model in the third step, an intelligent optimizing method for the energy consumption bottom line of the circulating pump is established, and in different temperature intervals, the optimal combination of the hot water outlet temperature and the circulating pump frequency is learned and iterated to find out, so that the energy consumption of the circulating pump under the current supply and demand condition is the lowest, and the method is adjusted in a linkage way along with the intelligent optimizing method for the hot water outlet temperature bottom line;
the intelligent optimizing method for the energy consumption base line of the circulating pump comprises the following steps:
starting;
s101: judging whether a central air conditioning system host is started or not, if so, turning to S102, otherwise, turning to S201;
s102: judging whether the current lowest temperature has matched records in the knowledge base (4), if not, turning to S1021, if so, turning to S1022, otherwise turning to S201;
s1021: judging whether a record which is smaller than the current minimum temperature and is matched with the current minimum temperature exists in the knowledge base (4), if not, the current circulating pump frequency value is initially a control upper limit value, if so, the current circulating pump frequency value is initially a knowledge record parameter value corresponding to the closest temperature value, and turning to S103;
S1022: taking the latest knowledge record, judging whether the corresponding circulating pump frequency field value-2 Hz is less than or equal to the control lower limit value, if so, initializing the current circulating pump frequency value as the control lower limit value, and if not, initializing the current circulating pump frequency value as the corresponding recorded circulating pump frequency field value-2 Hz, and turning to S103;
s103: taking a water outlet temperature value corresponding to a field of which the current lowest temperature corresponds to the (hot water optimal water outlet temperature) of the model library (1), setting the hot water outlet temperature value to be a corresponding water outlet temperature value, and turning to S104;
s104: invoking < insufficient heating experience monitoring method >, turning to S1041 if the result is equal to 11 or 21, and turning to S1042 if the result is equal to 10 or 20;
s1041: updating the current operation parameter data to a sampling library (1), simultaneously updating a knowledge base (4), wherein the field value of the corresponding current record < heating experience calculation result > is 11 or 21 corresponding to S104, the field value of the current record < state > is 1, and updating the field value of the last adjacent record < state > to 0, and turning to S201;
s1042: updating the current operation parameter data to a sampling library (1), judging whether a central air conditioning system host is powered off or not at intervals of 30 minutes, if so, calculating the current day energy consumption value, updating the current operation parameter data to a knowledge base (4), and meanwhile, recording the current field value of the current record < heating experience calculation result > as 10 or 20 corresponding to S104, turning to S105, otherwise turning to S104;
S105: taking an adjacent record on the knowledge base (4) to obtain a corresponding field value of < daily energy consumption of the circulating pump >, if the field value is larger than the calculated daily energy consumption value corresponding to S1042, updating the field value of the current record < state > of the knowledge base (4) to be-1, otherwise, updating the field value of the current record < state > of the knowledge base (4) to be 1, updating the field value of the previous adjacent record < state > to be 0, and turning to S201;
s201: and (5) ending.
Preferably, in the method of the bottom line with the least adverse frequency of the circulating pump, the design principle is as follows:
the lower the running frequency of the circulating pump is, the lower the pressure is, the lower the flow rate of the supplied backwater is, the most unfavorable heat supply points of the building are easy to cause complaints due to insufficient heat supply, and the most unfavorable frequency base line value of the circulating pump can be anchored by quantitatively identifying the possibility of complaints according to any one of the following identification interface rules;
manual identification interface: establishing a least advantageous space pool by manual input, and judging whether the spaces can reach the room temperature condition of 20 ℃ or not by monitoring and identifying the system;
automatic identification interface: the most unfavorable space startup probability can be ensured under the condition of a certain startup probability > =80%, and the judgment can be carried out by sampling the absolute quantity of the threshold of the room temperature <20 ℃ and the set temperature >20 ℃ to be > 1%;
the two interfaces need to sample to obtain knowledge records under 5 temperature conditions, and the highest frequency is taken as a bottom line frequency value.
Preferably, the method further comprises the following steps:
on the premise of manual data input, the room temperature of the manual input space must be completely met under the condition that the manual identification interface is standard; if no data is manually input, the interface is automatically identified to trigger an unfavorable boundary, the last favorable result is returned, and 5 records under different temperature conditions are acquired.
Preferably, the calculation steps of the most unfavorable spatial interfaces are as follows:
starting;
s101: judging whether the sampling library (2) has manually recorded data records, if so, turning to S201, otherwise, S102;
s102: judging that the current indoor air conditioner on-rate is more than or equal to 80%, if yes, turning to S103, otherwise turning to S301;
s103: judging that the current hot water outlet temperature reaches the control upper limit value, if yes, turning to S104, otherwise turning to S301;
s104: identifying a space with the room temperature of the current indoor air conditioner being less than or equal to 20 ℃ and the set temperature being greater than or equal to 20 ℃ for 30 minutes, identifying the space with the room temperature of the current indoor air conditioner being less than or equal to 20 ℃ and the set temperature being greater than or equal to 20 ℃ again, updating the latest space data to a sampling library (3) to S105 if the space data identified in the last two times are consistent, otherwise, continuing to carry out S104 cycle identification judgment;
s105: judging the proportion of the number of the air conditioners identified in the step S104 to the total number, outputting 0 if the proportion is less than or equal to 1%, otherwise outputting 1, and turning to the step S401;
S201: judging that the current hot water outlet temperature reaches the control upper limit value, if yes, turning to S202, otherwise turning to S301;
s202: uniformly setting the set temperature of the air conditioner of all the spaces which are manually input to 26 ℃, continuously waiting for 30 minutes, outputting 0 if the indoor temperature is equal to or higher than 20 ℃, otherwise outputting 1, and turning to S401;
s301: output-1, go to S401;
s401: and (5) ending.
Preferably, in the method for monitoring insufficient heating experience, the method further comprises the following design principle:
on one energy supply day, in order to avoid insufficient heat supply, namely, the heat supply requirement of the lowest point of the temperature enthalpy value in one day needs to be ensured, the following two kinds of interface rules can be identified manually and automatically on the premise of ensuring the operation safety of the boiler:
manual identification interface: manually updated conditions of insufficient heat supply space reaching standards, namely, all room temperature > =20 ℃ and set temperature > =20 ℃;
automatic identification interface: comprehensive identification is performed according to the following dimensional characteristic data:
result data one: data for room temperature <20 ℃ and set temperature >20 ℃ space, initializing feature rule = absolute amount >1%;
result data two: average room temperature, highest room temperature and lowest room temperature data, with initialization feature rule = average room temperature <20 ℃;
Behavior data one: the temperature signal data is set up by manual touch control, and the initialization characteristic rule = absolute quantity is more than 1%.
Preferably, in the hot water outlet temperature base line intelligent optimizing method, the method further comprises the following design principle:
in a central air conditioner on-off energy supply day period, the temperature range is definite, the enthalpy value changes in a certain interval, and only the lowest energy at the lowest point of the enthalpy value is ensured to ensure the energy in the enthalpy value change process of the day, so that the bottom line value of the hot water outlet temperature is found.
Under the condition that the heating demand of the highest point is certain in one energy supply day interval, the user can experience (cannot cause user complaints) and only needs to anchor through insufficient heating demand experience monitoring, and the learning iteration searches out the hot water outlet temperature to find the bottom line value.
Preferably, the method further comprises the following steps:
and executing the method by taking the day as a period, judging that the knowledge record state for identifying the lowest temperature matching on the same day is a 1 unfavorable value, stopping executing, if the knowledge record state is a-1 favorable value, continuing learning, and adjusting the corresponding water outlet temperature according to the following rule:
if the lowest temperature on the day is less than the knowledge record of the temperature value in the knowledge base (3), the initial value refers to the knowledge record parameter value corresponding to the closest temperature value, and if not, the initial value is the upper limit temperature of hot water control.
The outlet water temperature is regulated by taking an initial value or a current knowledge value as the amplitude of-0.5 ℃ until the outlet water temperature is a controllable lower limit temperature value;
and when the calculation result of the heat supply experience shortage method is 11 or 21, updating the current record state of the knowledge base to be 1, wherein the previous record state is a 0 base line value, otherwise, maintaining the record state of the knowledge base to be a-1 favorable value.
Preferably, in the method for intelligently optimizing the energy consumption base line of the circulating pump, the method further comprises the following design principle:
firstly, fixing the frequency of a circulating pump at a maximum value, and searching for the lowest value of the temperature of the outlet water of the anchored hot water;
secondly, fixing a hot water outlet temperature base line value, continuing fine tuning iteration frequency, anchoring through comprehensive monitoring of insufficient heat supply experience and energy consumption change of the circulating pump, and learning and iterating a frequency value corresponding to the lowest energy consumption value of the circulating pump on the premise of guaranteeing heat supply;
and finally, iteratively searching out the lowest value of the hot water outlet temperature and the minimum value of the circulating pump frequency under the condition that a certain low temperature value corresponds to the lowest daily enthalpy value, and obtaining the optimal combination value of the hot water outlet temperature and the circulating pump frequency.
Preferably, the method further comprises the following steps:
and executing the method by taking the day as a period, stopping executing the method when the knowledge record state matched between the lowest temperatures of the day is a 1 unfavorable value, and continuing learning if the knowledge record state is the-1 favorable value until the state is updated to be a 0 baseline value, wherein the corresponding circulating pump frequency is adjusted according to the following rule:
If the lowest temperature on the same day is recorded in the knowledge base (4) with knowledge less than the temperature value, the initial value refers to the knowledge record parameter value corresponding to the closest temperature value, and if not, the initial value is the highest circulating pump frequency.
The frequency of the circulating pump is adjusted by taking an initial value or a current knowledge value of-2 Hz as an amplitude until the frequency is a controllable lower limit value of the circulating pump;
the whole optimizing process takes the monitoring result of insufficient heat supply experience and the energy consumption value variation as learning reward basis, and the frequency boundary of the bottom-finding circulating pump is detected until the boundary of insufficient heat supply experience or the energy consumption variation boundary is triggered.
The invention has the following beneficial effects:
the invention breaks through the traditional energy-saving control or manual experience control mode of the heat source air-conditioning system with fuzzy matching of hysteresis quality based on the energy-saving mode that the energy-saving base line realizes the energy supply on demand and the coordination of supply and demand on demand, so as to solve the problems of anchoring the energy-saving base line on the energy-supply day under different temperature and humidity changes, searching a set knowledge model with optimal energy consumption of a host side, establishing a reinforced self-learning method, excavating an energy-saving space under the existing management control mode, realizing the unification of energy-saving experience and energy-saving benefit, and realizing the energy-saving emission reduction and carbon reduction peak-reaching of a booster building.
Drawings
Fig. 1 is a typical mainframe room configuration diagram of the present invention.
Fig. 2 is a block diagram of the method of the present invention.
In the figure: 100-boiler, 200-circulating pump, 300-water collector, 400-water separator.
Description of the embodiments
The invention is described in further detail below with reference to the drawings and the specific examples. Advantages and features of the invention will become more apparent from the following description and from the claims. It should be noted that the drawings are in a very simplified form and are all to a non-precise scale, merely for convenience and clarity in aiding in the description of embodiments of the invention.
The embodiment of the invention comprises the following parts:
1. the method aims at:
the method is oriented to a heating air-conditioning system scene, takes energy supply days as a unit, establishes a knowledge base with unified control parameters with a user base line, a safety base line and an energy consumption base line, and is assisted by an adjustment-feedback-analysis reinforcement learning method so as to form a system energy-saving base line optimal knowledge model, and realizes optimal base line energy-saving AI control of the heating air-conditioning system.
The method structure (see fig. 2).
The method is defined as follows:
(1) the method comprises the following steps:
the whole self-control scheme involves the main method:
1) The least adverse bottom line method (one-time calculation method) of the circulating pump frequency;
2) An intelligent monitoring method (a self-learning method and an anchor point method) for insufficient heat supply experience;
3) An intelligent optimizing method (self-learning method) of a hot water outlet temperature base line;
4) An intelligent optimizing method (self-learning method) for the energy consumption bottom line of a circulating pump.
The description is as follows:
the primary calculation method comprises the following steps: the independent calculation method can independently start operation. In the optimizing stage, only a single execution is needed to obtain a result according to a determined rule, and the triggering execution of the human intervention state is supported.
The self-learning method comprises the following steps: the independent calculation method can independently start operation. In the optimizing stage, the 'bottom detection' self-learning execution needs to be circulated until rule boundaries are triggered or adverse results appear.
The anchor point method comprises the following steps: in the optimizing stage, the method can be called by other methods, and can be used as an optimizing anchor point reference to support the triggering execution of the human intervention state.
(2) The combination step:
the first step: and establishing a least disadvantageous bottom line method of the circulating pump frequency according to a set rule, taking a calculation result of the method as the bottommost frequency of the circulating pump, and maintaining a circulating pump frequency control model. The spatial conditions may be manually supplemented to optimize the method results.
And a second step of: and (3) establishing an intelligent monitoring method for the insufficient heat supply experience according to the initialized characteristic model and the reference result of the step one, and taking the intelligent monitoring method as a basis for anchoring the current heat supply demand. Self-feature learning can be perfected based on human intervention.
And a third step of: and in different temperature intervals, learning and iterating to find the optimal temperature of hot water outlet, so that the outlet temperature under the current supply and demand conditions is the lowest. And maintaining a knowledge base and an optimal model. In the control operation stage, the method is adjusted in a linkage way along with the intelligent monitoring method for insufficient heat supply experience.
Fourth step: based on the knowledge base and the model in the third step, an intelligent optimizing method for the energy consumption base line of the circulating pump is established, and the optimal combination of the hot water outlet temperature and the circulating pump frequency is searched for in a learning and iteration mode in different temperature intervals, so that the energy consumption of the circulating pump under the current supply and demand conditions is the lowest. The method is adjusted in a linkage way along with an intelligent optimizing method of a hot water outlet temperature base line.
Knowledge base design:
(1) a circulating pump frequency knowledge base (1)) for short:
comprises parameters such as project, temperature, update time, turn-on probability, hot water outlet temperature, circulating pump frequency, identification mode (1: manual, 2: automatic), state (-1: favorable value, 0: bottom line value, 1: unfavorable value), etc.
(2) A heat supply experience deficiency feature library (short for knowledge base (2)):
the method comprises the parameters of project, room temperature <20 ℃ and set temperature >20 ℃ (absolute variable quantity and relative variable quantity), average room temperature (absolute variable quantity and relative variable quantity), manual temperature up-regulating signals (absolute variable quantity and relative variable quantity) and the like.
(3) A hot water temperature knowledge base (3)) for short:
including parameters such as project, (day) minimum temperature, corresponding date, real-time temperature, update time, hot water temperature, circulating pump frequency, heating experience calculation result (11 or 21: insufficient, 10 or 20: sufficient), status (-1: favorable value 0: floor value 1: unfavorable value), etc.
(4) Knowledge base of energy consumption of circulating pump (knowledge base (4)):
including parameters such as project, (day) minimum temperature, update time, hot water temperature, circulation pump frequency, circulation pump (day) energy consumption, heat supply quantity, experience calculation result (11 or 21: insufficient, 10 or 20: sufficient), state (-1: favorable value 0: floor value 1: unfavorable value), etc.
Sample library design:
(1) a system operation condition sampling library (simply referred to as a sampling library (1)):
the system comprises parameters such as project, real-time temperature, sampling time, circulating pump frequency, hot water outlet return water temperature and the like.
(2) The least favorable space manual sampling library (simply referred to as a sampling library (2)):
including parameters such as item, time of occurrence, (space) device number, (space) device name, date of operation, operator, etc.
(3) The least favorable spatial index sampling library (simply referred to as sampling library (3)):
Parameters including items, sampling time, (space) device number, (space) device name, indoor temperature, set temperature, and the like.
(4) Insufficient heat supply experience space manual sampling library (short for sampling library (4)):
including parameters such as project, day minimum temperature, time of occurrence, (space) equipment number, (space) equipment name, indoor temperature, set temperature, operation date, operator, status (0: to-be-processed 1: processed), etc.
(5) Heating experience (room temperature <20 ℃ and set temperature >20 ℃) index sampling library (5)) for short:
the system comprises parameters such as items, a day minimum temperature, sampling time, (space) equipment numbers, (space) equipment names, indoor temperature, set temperature and the like.
(6) The heating experience (average, highest, lowest room temperature) index sampling library (6) for short):
including project, day minimum temperature, sampling time, average room temperature, maximum room temperature, minimum room temperature, etc.
(7) Index sampling library (7) for short) for heat supply experience (manual touch control up-regulation set temperature signal):
the system comprises parameters such as items, a day minimum temperature, sampling time, (space) equipment numbers, (space) equipment names, indoor temperature, set temperature and the like.
(8) A heat supply experience sampling calculation library (simply referred to as a sampling library (8)):
the system comprises parameters such as the lowest daily temperature, the real-time temperature, the corresponding date, the frequency of a circulating pump, the temperature of hot water outlet, the temperature of hot water return, the room temperature of <20 ℃ and the set temperature of >20 ℃ (absolute change amount and relative change amount), the average room temperature (absolute change amount and relative change amount), a temperature up-regulating signal by manual touch (absolute change amount and relative change amount), a characteristic rule calculation result (11 or 21: insufficient, 10 or 20: sufficient) and the like.
Model library design:
(1) a system optimal model library (simply referred to as model library (1)):
the method comprises the parameters of project, day minimum temperature, hot water optimal outlet temperature, circulating pump optimal frequency, update time, state (1: effective, 0: ineffective) and the like.
(2) Pump variable frequency control model library (2)) for short:
includes parameters such as project, lower control limit frequency, upper control limit frequency, and minimum frequency satisfying least advantageous space.
The method comprises the following steps:
1. the least adverse bottom line method for the circulating pump frequency is as follows:
(1) concept: the water circulation pressure is insufficient due to the insufficient frequency of the circulating pump on the premise that the temperature of the hot water outlet meets the requirement, and the indoor space temperature cannot meet the set requirement. The frequency bottom line is the lowest set frequency value of the circulating pump corresponding to the heat supply requirement for ensuring the least unfavorable space on the premise of reasonable heat supply.
(2) Principle of: the lower the running frequency of the circulating pump is, the lower the pressure is, the lower the flow rate of the supplied water is, the most unfavorable heat supply point of the building is easy to cause complaints due to insufficient heat supply, and the most unfavorable frequency base line value of the circulating pump can be anchored by quantitatively identifying the possibility of complaints according to any one of the following two identification interface rules.
Manual identification interface: the least advantageous space pool is established by manual input, and the system monitors and identifies whether the space can reach the room temperature condition of 20 ℃ or not.
Automatic identification interface: the judgment can be performed by sampling the room temperature <20 ℃ and setting the absolute value of the threshold of the temperature >20 ℃ to be >1% under the condition of a certain opening probability (> = 80% >) (ensuring the least favorable space opening probability).
The two interfaces need to sample to obtain knowledge records under 5 temperature conditions, and the highest frequency is taken as a bottom line frequency value.
(3) The implementation process comprises the following steps:
the actions are as follows: a frequency;
status: least-emptiness interface calculation results;
a loop body: on the premise of manual data input, the room temperature of the manual input space must be completely met under the condition that the manual recognition interface is used as the standard, if no manual data input is performed, the automatic recognition interface is used for triggering an unfavorable boundary, the last favorable result is returned, and the records under 5 different temperature conditions are acquired.
(4) The flow steps are as follows:
1) Calculation of the most unfavorable spatial interfaces: the flow steps are as follows:
starting;
s101: judging whether the sampling library (2) has manually recorded data records, if so, turning to S201, otherwise, S102;
s102: judging that the current indoor air conditioner on-rate is more than or equal to 80%, if yes, turning to S103, otherwise turning to S301;
s103: judging that the current hot water outlet temperature reaches the control upper limit value, if yes, turning to S104, otherwise turning to S301;
s104: identifying a space with the room temperature of the current indoor air conditioner being less than or equal to 20 ℃ and the set temperature being greater than or equal to 20 ℃ for 30 minutes, identifying the space with the room temperature of the current indoor air conditioner being less than or equal to 20 ℃ and the set temperature being greater than or equal to 20 ℃ again, updating the latest space data to a sampling library (3) to S105 if the space data identified in the last two times are consistent, otherwise, continuing to carry out S104 cycle identification judgment;
s105: judging the proportion of the number of the air conditioners identified in the step S104 to the total number, outputting 0 if the proportion is less than or equal to 1%, otherwise outputting 1, and turning to the step S401;
s201: judging that the current hot water outlet temperature reaches the control upper limit value, if yes, turning to S202, otherwise turning to S301;
s202: uniformly setting the set temperature of the air conditioner of all the spaces which are manually input to 26 ℃, continuously waiting for 30 minutes, outputting 0 if the indoor temperature is equal to or higher than 20 ℃, otherwise outputting 1, and turning to S401;
S301: output-1, go to S401;
s401: and (5) ending.
2) The least adverse bottom line method of the circulating pump frequency comprises the following steps: the flow steps are as follows:
starting;
s101: judging whether the central air conditioner host is started, if so, turning to S102, otherwise turning to S301;
s102: judging whether the record of the state=0 of the knowledge base (1) meets 5 records, if so, updating the highest frequency value of the frequency of the circulating pump of the 5 records to the field of < least-favored space minimum frequency > of the model base (2), turning to S301, otherwise turning to S103;
s103: judging whether the lowest temperature value of the current day is correspondingly recorded in the knowledge base (1), if so, turning to S301, otherwise turning to S104;
s104: judging whether the sampling library (2) has manually recorded data records, if so, turning to S106, otherwise turning to S105;
s105: judging that the current indoor air conditioner on-rate is more than or equal to 80%, if yes, turning to S106, otherwise turning to S301;
s106: memorizing the current hot water outlet temperature and the circulating pump frequency, setting the hot water outlet temperature as a control upper limit value, setting the circulating pump frequency as a highest value, and turning to S107;
s107: transferring the least unfavorable space interface, if the judging result is=0, transferring to S108, if the judging result is=1, recording the optimal frequency value=the current-period frequency value+1Hz, transferring to S201, otherwise transferring to S301;
S108: updating the current data to the knowledge base (1), setting the status field to-1, and turning to S109;
s109: judging whether the frequency-1 of the circulating pump is larger than or equal to the control lower limit value, if so, setting the current frequency of the circulating pump to be-1 Hz, turning to S107, otherwise, recording the optimal frequency value = control lower limit value, turning to S201;
s201: updating the current data and the optimal frequency value to a knowledge base (1), setting the current record state field as 1, setting the last record state field from-1 to 0, restoring and memorizing the current hot water outlet temperature and the circulating pump frequency, and turning to S301;
s301: and (5) ending.
2. The heat supply experience deficiency monitoring method comprises the following steps:
(1) concept: on the premise that the frequency of the circulating pump is on the bottom line and above by taking one energy supply day as a unit, the heat supply quantity is insufficient due to the insufficient temperature of hot water outlet, and the indoor space temperature cannot meet the set requirement, so that the user experience is affected.
(2) Principle of: on one energy supply day, in order to avoid insufficient heat supply, namely, the heat supply requirement of the lowest point of the temperature (enthalpy value) in one day needs to be ensured, on the premise of ensuring the operation safety of the boiler, the two types of manual and automatic rule interfaces can be used for identifying:
manual identification interface: manually updated conditions of insufficient heating capacity space reaching standards (total room temperature > =20deg.C and set temperature > =20deg.C);
Automatic identification interface: comprehensive identification is carried out according to several dimension characteristic data:
(result data one) data for room temperature <20 ℃ and set temperature >20 ℃ space (initialization feature rule = absolute amount > 1%);
(results data two) average room temperature, highest room temperature, lowest room temperature data (initialization feature rule = average room temperature <20 ℃);
(behavior data-a) human touch up-regulation setting temperature signal data (initialization feature rule=absolute quantity > 1%).
(3) The implementation process comprises the following steps:
environment: the lowest daily temperature;
parameters: the hot water outlet temperature;
and (3) outputting: if the result of calculation of a plurality of characteristic indexes is that the manual data input exists, judging the insufficient output 11 and the sufficient output 10; otherwise, according to the automatic recognition situation, the insufficient output 21 is judged, the sufficient output 20 is judged, and the output-1 cannot be calculated.
An intelligent agent: and when the sampling data is manually updated, the feature calculation result when the sampling data occurs is identified, and the maintenance feature rule model is updated.
(4) The insufficient heat supply experience monitoring method comprises the following steps: the flow steps are as follows:
starting;
s101: judging whether the running frequency of the circulating pump is larger than or equal to a bottom line value obtained by a bottom line method with the least adverse frequency of the circulating pump, if so, turning to S102, otherwise, outputting-1, and turning to S301;
S102: judging whether the sampling library (4) has unprocessed records with the state=0, if so, turning to S103, otherwise turning to S201;
s103: judging whether the set temperature of all room air conditioners in the untreated record is higher than 20 ℃, if so, turning to S105, otherwise turning to S104;
s104: uniformly setting the set temperature of the room air conditioner to be less than 20 ℃ to 26 ℃, and turning to S105 after 15 minutes;
s105: judging whether the indoor temperature of the air conditioner in all rooms is more than or equal to 20 ℃, if so, outputting 10, updating the current operation parameter data to a sampling library (8), wherein the field state of the < characteristic rule calculation result > is 10, and turning to S301; otherwise, outputting 11, namely updating the current operation parameter data to a sampling library (8), wherein the field state of the < feature rule calculation result > is 11, and turning to S301;
s201: judging the proportion of the number of air conditioners with the current set temperature being more than 20 ℃ and the indoor temperature being less than 20 ℃ to the total number, if the current set temperature is more than 1%, updating the current operation parameter data to a sampling library (5), turning to S202, otherwise outputting 20, updating the current operation parameter data to the sampling library (8), turning to S301, wherein the field state of the < characteristic rule calculation result > is 20;
s202: judging whether the current average indoor set temperature is less than 20 ℃, if yes, updating the current operation parameter data to a sampling library (6), turning to S203, otherwise outputting 20, updating the current operation parameter data to a sampling library (8), and turning to S301, wherein the field state of the < feature rule calculation result > is 20;
S203: judging that the quantity of the set temperature of the air conditioner is manually up-regulated in the last 30 minutes and accounts for the proportion of the total quantity, if the quantity is more than 1%, updating the current operation parameter data to a sampling library (7), turning to S204, otherwise outputting 20, updating the current operation parameter data to the sampling library (8), and turning to S301, wherein the field state of the < feature rule calculation result > is 20;
s204: updating the current operation parameter data to a sampling library (8), wherein the field state of the < feature rule calculation result > is 21, outputting 21, and turning to S301;
s301: and (5) ending.
3. The intelligent optimizing method for the hot water outlet temperature base line comprises the following steps:
(1) concept: under different temperature conditions, one energy supply day is taken as a period, so that the minimum heating capacity requirement of the lowest point of the temperature (enthalpy value) in one day is ensured, and the minimum temperature required by hot water outlet is realized on the premise that the frequency of a circulating pump is on a bottom line.
(2) Principle of: in a central air conditioner on-off energy supply day period, the temperature range is definite, the enthalpy value changes in a certain interval, and only the lowest energy at the lowest point of the enthalpy value is ensured to ensure the energy in the enthalpy value change process of the day, so that the bottom line value of the hot water outlet temperature is found. Under the condition that the heating demand of the highest point is certain in one energy supply day interval, the user can experience (cannot cause user complaints) and only needs to anchor through insufficient heating demand experience monitoring, and the learning iteration searches out the hot water outlet temperature to find the bottom line value.
(3) The implementation process comprises the following steps:
environment: the lowest daily temperature;
the actions are as follows: the hot water outlet temperature;
status: monitoring results of insufficient heat supply experience;
an intelligent agent: and executing the method by taking the day as a period, judging that the knowledge record state for identifying the lowest temperature matching on the same day is 1 (unfavorable value), stopping executing, if the knowledge record state is-1 (favorable value), continuing learning, and adjusting the corresponding water outlet temperature according to the following rule:
if the lowest temperature on the day is less than the knowledge record of the temperature value in the knowledge base (3), the initial value refers to the knowledge record parameter value corresponding to the closest temperature value, and if not, the initial value is the upper limit temperature of hot water control.
And the outlet water temperature is regulated by taking an initial value or a current knowledge value as the amplitude of-0.5 ℃ until the outlet water temperature is a controllable lower limit temperature value.
And when the calculation result of the heat supply experience shortage method is 11 or 21, updating the current record state of the knowledge base to be 1, wherein the previous record state is 0 (base line value), otherwise, maintaining the record state of the knowledge base to be-1 (favorable value).
(4) The hot water outlet temperature base line intelligent optimizing method comprises the following steps: the flow steps are as follows:
starting;
s101: judging whether a central air conditioning system host is started or not, if so, turning to S102, otherwise, turning to S201;
s102: judging whether the current lowest temperature has matched records in the knowledge base (3), if not, turning to S1021, if so, turning to S1022, otherwise turning to S201;
S1021: judging whether a record which is smaller than the current minimum temperature and is matched with the current minimum temperature exists in the knowledge base (3), if not, the current hot water outlet temperature value is initially a control upper limit value, and if so, the current hot water outlet temperature value is initially a knowledge record parameter value corresponding to the closest temperature value, and turning to S103;
s1022: taking the latest knowledge record, judging whether the corresponding hot water temperature field value is less than or equal to the control lower limit value, if so, initially setting the current hot water outlet temperature value as the control lower limit value, and if not, initially setting the current hot water outlet temperature value as the hot water temperature field value of-0.5 ℃, and turning to S103;
s103: setting the frequency value of the circulating pump as a control upper limit value, and turning to S104 after 30 minutes;
s104: invoking < insufficient heating experience monitoring method >, turning to S1041 if the result is equal to 11 or 21, and turning to S1042 if the result is equal to 10 or 20;
s1041: updating the current operation parameter data to a knowledge base (3), wherein the current record < state > field value is 1, the last adjacent record < state > field value is 0, simultaneously, synchronously updating the record corresponding to the < state > field updated to 0 to a model base (1), updating the corresponding < hot water optimal water outlet temperature > field to the corresponding water outlet temperature value, updating the < state > field value to 1, and turning to S201;
S1042: if the central air conditioning system host is shut down, the step S105 is carried out, and if not, the step S104 is carried out;
s105: updating the current operation parameter data to a knowledge base (3), wherein the current record < state > field value is-1, and turning to S201;
s201: and (5) ending.
4. The intelligent optimizing method for the energy consumption base line of the circulating pump comprises the following steps:
(1) concept: under different temperature conditions, taking one energy supply day as a period, and on the premise that the frequency of the circulating pump is on the bottom line and above, the hot water outlet temperature is already found to be the optimal value, and the optimal combination of the frequencies of the circulating pump is iteratively found, so that the energy consumption of the circulating pump is the lowest within the boundary of the safety barrier.
(2) Principle of:
first, we have fixed the circulation pump frequency at a maximum, looking for the lowest value that anchors out the hot water outlet temperature.
Secondly, fixing a hot water outlet temperature base line value, continuing fine tuning iteration frequency, anchoring through comprehensive monitoring of insufficient heat supply experience and energy consumption change of the circulating pump, and learning and iterating a frequency value corresponding to the lowest energy consumption value of the circulating pump on the premise of guaranteeing heat supply.
Finally, we find out the lowest value of hot water outlet temperature and the minimum value of circulating pump frequency under the condition that a certain low temperature value corresponds to the lowest daily enthalpy value in an iterative way, and obtain the optimal combination value (hot water outlet temperature and circulating pump frequency).
(3) The implementation process comprises the following steps:
environment: the lowest daily temperature and the hot water outlet temperature;
the actions are as follows: circulating pump frequency;
status: monitoring results of insufficient heat supply experience;
an intelligent agent: and executing the method by taking the day as a period, stopping executing the method when the knowledge record state matched with the lowest temperature on the day is 1 (unfavorable value), and if the knowledge record state is-1 (favorable value), continuing learning until the state is updated to be 0 (bottom line value), and adjusting the corresponding circulating pump frequency according to the following rule:
if the lowest temperature on the same day is recorded in the knowledge base (4) with knowledge less than the temperature value, the initial value refers to the knowledge record parameter value corresponding to the closest temperature value, and if not, the initial value is the highest circulating pump frequency.
The frequency of the circulating pump is adjusted by taking the initial value or the current knowledge value of-2 Hz as the amplitude until the lower limit value can be controlled for the circulating pump.
3. The whole optimizing process takes the monitoring result of insufficient heat supply experience and the energy consumption value variation as learning reward basis, and the frequency boundary of the bottom-finding circulating pump is detected until the boundary of insufficient heat supply experience or the energy consumption variation boundary is triggered.
(4) The intelligent optimizing method for the energy consumption base line of the circulating pump comprises the following steps: the flow steps are as follows:
starting;
s101: judging whether a central air conditioning system host is started or not, if so, turning to S102, otherwise, turning to S201;
S102: judging whether the current lowest temperature has matched records in the knowledge base (4), if not, turning to S1021, if so, turning to S1022, otherwise turning to S201;
s1021: judging whether a record which is smaller than the current minimum temperature and is matched with the current minimum temperature exists in the knowledge base (4), if not, the current circulating pump frequency value is initially a control upper limit value, if so, the current circulating pump frequency value is initially a knowledge record parameter value corresponding to the closest temperature value, and turning to S103;
s1022: taking the latest knowledge record, judging whether the corresponding circulating pump frequency field value-2 Hz is less than or equal to the control lower limit value, if so, initializing the current circulating pump frequency value as the control lower limit value, and if not, initializing the current circulating pump frequency value as the corresponding recorded circulating pump frequency field value-2 Hz, and turning to S103;
s103: taking a water outlet temperature value corresponding to a field of which the current lowest temperature corresponds to the (hot water optimal water outlet temperature) of the model library (1), setting the hot water outlet temperature value to be a corresponding water outlet temperature value, and turning to S104;
s104: invoking < insufficient heating experience monitoring method >, turning to S1041 if the result is equal to 11 or 21, and turning to S1042 if the result is equal to 10 or 20;
s1041: updating the current operation parameter data to a sampling library (1), simultaneously updating a knowledge base (4), wherein the field value of the corresponding current record < heating experience calculation result > is 11 or 21 corresponding to S104, the field value of the current record < state > is 1, and updating the field value of the last adjacent record < state > to 0, and turning to S201;
S1042: updating the current operation parameter data to a sampling library (1), judging whether a central air conditioning system host is powered off or not at intervals of 30 minutes, if so, calculating the current day energy consumption value, updating the current operation parameter data to a knowledge base (4), and meanwhile, recording the current field value of the current record < heating experience calculation result > as 10 or 20 corresponding to S104, turning to S105, otherwise turning to S104;
s105: taking an adjacent record on the knowledge base (4) to obtain a corresponding field value of < daily energy consumption of the circulating pump >, if the field value is larger than the calculated daily energy consumption value corresponding to S1042, updating the field value of the current record < state > of the knowledge base (4) to be-1, otherwise, updating the field value of the current record < state > of the knowledge base (4) to be 1, updating the field value of the previous adjacent record < state > to be 0, and turning to S201;
s201: and (5) ending.
The above description is only illustrative of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention, and any alterations and modifications made by those skilled in the art based on the above disclosure shall fall within the scope of the appended claims.
Claims (9)
1. The optimizing method of the energy-saving bottom line of the heating air conditioning system based on big data self-learning is characterized by comprising the following steps:
step one: according to a set rule, a method for establishing the bottom line with the least adverse frequency of the circulating pump is established, the calculation result of the method is used as the bottom frequency of the circulating pump, and a circulating pump frequency control model is maintained; the space condition can be supplemented manually to optimize the calculation result;
The most disadvantageous bottom line method comprises the following steps:
starting;
s101: judging whether the central air conditioner host is started, if so, turning to S102, otherwise turning to S301;
s102: judging whether the records of the state=0 of the knowledge base (1) meet 5 records, if so, updating the frequency average value of the circulating pump of the 5 records to the field of the least-favored space minimum frequency of the model base (2), turning to S301, otherwise turning to S103;
s103: judging whether the lowest temperature value of the current day is correspondingly recorded in the knowledge base (1), if so, turning to S301, otherwise turning to S104;
s104: judging whether the sampling library (2) has manually recorded data records, if so, turning to S106, otherwise turning to S105;
s105: judging that the current indoor air conditioner on-rate is more than or equal to 80%, if yes, turning to S106, otherwise turning to S301;
s106: memorizing the current hot water outlet temperature and the circulating pump frequency, setting the hot water outlet temperature as a control upper limit value, setting the circulating pump frequency as a highest value, and turning to S107;
s107: transferring the least unfavorable space interface, if the judging result is=0, transferring to S108, if the judging result is=1, recording the optimal frequency value=the current-period frequency value+1Hz, transferring to S201, otherwise transferring to S301;
s108: updating the current data to the knowledge base (1), setting the status field to-1, and turning to S109;
S109: judging whether the frequency-1 of the circulating pump is larger than or equal to the control lower limit value, if so, setting the current frequency of the circulating pump to be-1 Hz, turning to S107, otherwise, recording the optimal frequency value = control lower limit value, turning to S201;
s201: updating the current data and the optimal frequency value to a knowledge base (1), setting the current record state field as 1, setting the last record state field from-1 to 0, restoring and memorizing the current hot water outlet temperature and the circulating pump frequency, and turning to S301;
s301: ending;
step two: according to the initialized characteristic model and the reference result of the step one, an intelligent monitoring method for the heat supply experience deficiency is established to serve as a basis for anchoring the current heat supply demand; self-feature learning can be perfected according to human intervention;
the intelligent monitoring method for the insufficient heat supply experience comprises the following steps:
starting;
s101: judging whether the running frequency of the circulating pump is larger than or equal to a bottom line value obtained by a bottom line method with the least adverse frequency of the circulating pump, if so, turning to S102, otherwise, outputting-1, and turning to S301;
s102: judging whether the sampling library (4) has unprocessed records with the state=0, if so, turning to S103, otherwise turning to S201;
s103: judging whether the set temperature of all room air conditioners in the untreated record is higher than 20 ℃, if so, turning to S105, otherwise turning to S104;
S104: uniformly setting the set temperature of the room air conditioner to be less than 20 ℃ to 26 ℃, and turning to S105 after 15 minutes;
s105: judging whether the indoor temperature of the air conditioner in all rooms is more than or equal to 20 ℃, if so, outputting 10, updating the current operation parameter data to a sampling library (8), wherein the field state of the < characteristic rule calculation result > is 10, and turning to S301; otherwise, outputting 11, namely updating the current operation parameter data to a sampling library (8), wherein the field state of the < feature rule calculation result > is 11, and turning to S301;
s201: judging the proportion of the number of air conditioners with the current set temperature being more than 20 ℃ and the indoor temperature being less than 20 ℃ to the total number, if the current set temperature is more than 1%, updating the current operation parameter data to a sampling library (5), turning to S202, otherwise outputting 20, updating the current operation parameter data to the sampling library (8), turning to S301, wherein the field state of the < characteristic rule calculation result > is 20;
s202: judging whether the current average indoor set temperature is less than 20 ℃, if yes, updating the current operation parameter data to a sampling library (6), turning to S203, otherwise outputting 20, updating the current operation parameter data to a sampling library (8), and turning to S301, wherein the field state of the < feature rule calculation result > is 20;
s203: judging that the quantity of the set temperature of the air conditioner is manually up-regulated in the last 30 minutes and accounts for the proportion of the total quantity, if the quantity is more than 1%, updating the current operation parameter data to a sampling library (7), turning to S204, otherwise outputting 20, updating the current operation parameter data to the sampling library (8), and turning to S301, wherein the field state of the < feature rule calculation result > is 20;
S204: updating the current operation parameter data to a sampling library (8), wherein the field state of the < feature rule calculation result > is 21, outputting 21, and turning to S301;
s301: ending;
step three: in different temperature intervals, learning and iterating to find the optimal temperature of hot water outlet, so that the outlet water temperature meeting the current supply and demand conditions is the lowest, and maintaining a knowledge base and an optimal model; in the control operation stage, the method is adjusted in a linkage way along with the intelligent monitoring method for insufficient heat supply experience;
the hot water outlet temperature base line intelligent optimizing method comprises the following steps:
starting;
s101: judging whether a central air conditioning system host is started or not, if so, turning to S102, otherwise, turning to S201;
s102: judging whether the current lowest temperature has matched records in the knowledge base (3), if not, turning to S1021, if so, turning to S1022, otherwise turning to S201;
s1021: judging whether a record which is smaller than the current minimum temperature and is matched with the current minimum temperature exists in the knowledge base (3), if not, the current hot water outlet temperature value is initially a control upper limit value, and if so, the current hot water outlet temperature value is initially a knowledge record parameter value corresponding to the closest temperature value, and turning to S103;
s1022: taking the latest knowledge record, judging whether the corresponding hot water temperature field value is less than or equal to the control lower limit value, if so, initially setting the current hot water outlet temperature value as the control lower limit value, and if not, initially setting the current hot water outlet temperature value as the hot water temperature field value of-0.5 ℃, and turning to S103;
S103: setting the frequency value of the circulating pump as a control upper limit value, and turning to S104 after 30 minutes;
s104: invoking < insufficient heating experience monitoring method >, turning to S1041 if the result is equal to 11 or 21, and turning to S1042 if the result is equal to 10 or 20;
s1041: updating the current operation parameter data to a knowledge base (3), wherein the current record < state > field value is 1, the last adjacent record < state > field value is 0, simultaneously, synchronously updating the record corresponding to the < state > field updated to 0 to a model base (1), updating the corresponding < hot water optimal water outlet temperature > field to the corresponding water outlet temperature value, updating the < state > field value to 1, and turning to S201;
s1042: if the central air conditioning system host is shut down, the step S105 is carried out, and if not, the step S104 is carried out;
s105: updating the current operation parameter data to a knowledge base (3), wherein the current record < state > field value is-1, and turning to S201;
s201: ending;
step four: based on the knowledge base and the model in the third step, an intelligent optimizing method for the energy consumption bottom line of the circulating pump is established, and in different temperature intervals, the optimal combination of the hot water outlet temperature and the circulating pump frequency is learned and iterated to find out, so that the energy consumption of the circulating pump under the current supply and demand condition is the lowest, and the method is adjusted in a linkage way along with the intelligent optimizing method for the hot water outlet temperature bottom line;
The intelligent optimizing method for the energy consumption base line of the circulating pump comprises the following steps:
starting;
s101: judging whether a central air conditioning system host is started or not, if so, turning to S102, otherwise, turning to S201;
s102: judging whether the current lowest temperature has matched records in the knowledge base (4), if not, turning to S1021, if so, turning to S1022, otherwise turning to S201;
s1021: judging whether a record which is smaller than the current minimum temperature and is matched with the current minimum temperature exists in the knowledge base (4), if not, the current circulating pump frequency value is initially a control upper limit value, if so, the current circulating pump frequency value is initially a knowledge record parameter value corresponding to the closest temperature value, and turning to S103;
s1022: taking the latest knowledge record, judging whether the corresponding circulating pump frequency field value-2 Hz is less than or equal to the control lower limit value, if so, initializing the current circulating pump frequency value as the control lower limit value, and if not, initializing the current circulating pump frequency value as the corresponding recorded circulating pump frequency field value-2 Hz, and turning to S103;
s103: taking a water outlet temperature value corresponding to a field of which the current lowest temperature corresponds to the (hot water optimal water outlet temperature) of the model library (1), setting the hot water outlet temperature value to be a corresponding water outlet temperature value, and turning to S104;
s104: invoking < insufficient heating experience monitoring method >, turning to S1041 if the result is equal to 11 or 21, and turning to S1042 if the result is equal to 10 or 20;
S1041: updating the current operation parameter data to a sampling library (1), simultaneously updating a knowledge base (4), wherein the field value of the corresponding current record < heating experience calculation result > is 11 or 21 corresponding to S104, the field value of the current record < state > is 1, and updating the field value of the last adjacent record < state > to 0, and turning to S201;
s1042: updating the current operation parameter data to a sampling library (1), judging whether a central air conditioning system host is powered off or not at intervals of 30 minutes, if so, calculating the current day energy consumption value, updating the current operation parameter data to a knowledge base (4), and meanwhile, recording the current field value of the current record < heating experience calculation result > as 10 or 20 corresponding to S104, turning to S105, otherwise turning to S104;
s105: taking an adjacent record on the knowledge base (4) to obtain a corresponding field value of < daily energy consumption of the circulating pump >, if the field value is larger than the calculated daily energy consumption value corresponding to S1042, updating the field value of the current record < state > of the knowledge base (4) to be-1, otherwise, updating the field value of the current record < state > of the knowledge base (4) to be 1, updating the field value of the previous adjacent record < state > to be 0, and turning to S201;
s201: and (5) ending.
2. The optimizing method of energy-saving bottom line of heating air conditioning system based on big data self-learning as set forth in claim 1, wherein in the method of bottom line with the least adverse frequency of the circulating pump, the following design principle is further included:
The lower the running frequency of the circulating pump is, the lower the pressure is, the lower the flow rate of the supplied backwater is, the most unfavorable heat supply points of the building are easy to cause complaints due to insufficient heat supply, and the most unfavorable frequency base line value of the circulating pump can be anchored by quantitatively identifying the possibility of complaints according to any one of the following identification interface rules;
manual identification interface: establishing a least advantageous space pool by manual input, and judging whether the spaces can reach the room temperature condition of 20 ℃ or not by monitoring and identifying the system;
automatic identification interface: the most unfavorable space startup probability can be ensured under the condition of a certain startup probability > =80%, and the judgment can be carried out by sampling the absolute quantity of the threshold of the room temperature <20 ℃ and the set temperature >20 ℃ to be > 1%;
the two interfaces need to sample to obtain knowledge records under 5 temperature conditions, and the highest frequency is taken as a bottom line frequency value.
3. The optimizing method of the energy-saving bottom line of the heating air conditioning system based on big data self-learning as set forth in claim 2, further comprising the following process:
on the premise of manual data input, the room temperature of the manual input space must be completely met under the condition that the manual identification interface is standard; if no data is manually input, the interface is automatically identified to trigger an unfavorable boundary, the last favorable result is returned, and 5 records under different temperature conditions are acquired.
4. The optimizing method of the energy-saving bottom line of the heating and air conditioning system based on big data self-learning as set forth in any one of claims 1 to 3, wherein the computing steps of the least favorable space interface are as follows:
starting;
s101: judging whether the sampling library (2) has manually recorded data records, if so, turning to S201, otherwise, S102;
s102: judging that the current indoor air conditioner on-rate is more than or equal to 80%, if yes, turning to S103, otherwise turning to S301;
s103: judging that the current hot water outlet temperature reaches the control upper limit value, if yes, turning to S104, otherwise turning to S301;
s104: identifying a space with the room temperature of the current indoor air conditioner being less than or equal to 20 ℃ and the set temperature being greater than or equal to 20 ℃ for 30 minutes, identifying the space with the room temperature of the current indoor air conditioner being less than or equal to 20 ℃ and the set temperature being greater than or equal to 20 ℃ again, updating the latest space data to a sampling library (3) to S105 if the space data identified in the last two times are consistent, otherwise, continuing to carry out S104 cycle identification judgment;
s105: judging the proportion of the number of the air conditioners identified in the step S104 to the total number, outputting 0 if the proportion is less than or equal to 1%, otherwise outputting 1, and turning to the step S401;
s201: judging that the current hot water outlet temperature reaches the control upper limit value, if yes, turning to S202, otherwise turning to S301;
S202: uniformly setting the set temperature of the air conditioner of all the spaces which are manually input to 26 ℃, continuously waiting for 30 minutes, outputting 0 if the indoor temperature is equal to or higher than 20 ℃, otherwise outputting 1, and turning to S401;
s301: output-1, go to S401;
s401: and (5) ending.
5. The optimizing method of the energy-saving bottom line of the heating air conditioning system based on big data self-learning as set forth in claim 1, wherein in the heating experience deficiency monitoring method, the following design principle is further included:
on one energy supply day, in order to avoid insufficient heat supply, namely, the heat supply requirement of the lowest point of the temperature enthalpy value in one day needs to be ensured, the following two kinds of interface rules can be identified manually and automatically on the premise of ensuring the operation safety of the boiler:
manual identification interface: manually updated conditions of insufficient heat supply space reaching standards, namely, all room temperature > =20 ℃ and set temperature > =20 ℃;
automatic identification interface: comprehensive identification is performed according to the following dimensional characteristic data:
result data one: data for room temperature <20 ℃ and set temperature >20 ℃ space, initializing feature rule = absolute amount >1%;
result data two: average room temperature, highest room temperature and lowest room temperature data, with initialization feature rule = average room temperature <20 ℃;
Behavior data one: the temperature signal data is set up by manual touch control, and the initialization characteristic rule = absolute quantity is more than 1%.
6. The optimizing method of the energy-saving bottom line of the heating air conditioning system based on big data self-learning as set forth in claim 1, wherein in the intelligent optimizing method of the hot water outlet temperature bottom line, the method further comprises the following design principle:
the method is characterized in that the energy supply day period is started and closed in a central air conditioner, the temperature range is definite, the enthalpy value changes in a certain interval, the energy in the enthalpy value change process of the day is ensured, and only the bottommost energy at the lowest point of the enthalpy value is ensured, so that the bottom line value of the water outlet temperature of the hot water is found;
under the condition that the heating demand of the highest point is certain in one energy supply day interval, the user can experience the energy consumption, anchoring is only needed through insufficient heating experience monitoring, and the learning iteration finds out the hot water outlet temperature to find the bottom line value.
7. The method for optimizing an energy-saving bottom line of a heating and air conditioning system based on big data self-learning as set forth in claim 6, further comprising the steps of:
and executing the method by taking the day as a period, judging that the knowledge record state for identifying the lowest temperature matching on the same day is a 1 unfavorable value, stopping executing, if the knowledge record state is a-1 favorable value, continuing learning, and adjusting the corresponding water outlet temperature according to the following rule:
If the lowest temperature of the day is in the knowledge base (3) and has knowledge records smaller than the temperature value, the initial value refers to the knowledge record parameter value corresponding to the closest temperature value, and if the lowest temperature of the day is not the highest temperature of hot water control;
the outlet water temperature is regulated by taking an initial value or a current knowledge value as the amplitude of-0.5 ℃ until the outlet water temperature is a controllable lower limit temperature value;
and when the calculation result of the heat supply experience shortage method is 11 or 21, updating the current record state of the knowledge base to be 1, wherein the previous record state is a 0 base line value, otherwise, maintaining the record state of the knowledge base to be a-1 favorable value.
8. The method for optimizing the energy-saving bottom line of the heating air conditioning system based on big data self-learning as set forth in claim 1, wherein the method for intelligently optimizing the energy consumption bottom line of the circulating pump is characterized by further comprising the following design principle:
firstly, fixing the frequency of a circulating pump at a maximum value, and searching for the lowest value of the temperature of the outlet water of the anchored hot water;
secondly, fixing a hot water outlet temperature base line value, continuing fine tuning iteration frequency, anchoring through comprehensive monitoring of insufficient heat supply experience and energy consumption change of the circulating pump, and learning and iterating a frequency value corresponding to the lowest energy consumption value of the circulating pump on the premise of guaranteeing heat supply;
And finally, iteratively searching out the lowest value of the hot water outlet temperature and the minimum value of the circulating pump frequency under the condition that a certain low temperature value corresponds to the lowest daily enthalpy value, and obtaining the optimal combination value of the hot water outlet temperature and the circulating pump frequency.
9. The optimizing method of the energy-saving bottom line of the heating and air conditioning system based on big data self-learning as set forth in claim 8, further comprising the following process:
and executing the method by taking the day as a period, stopping executing the method when the knowledge record state matched between the lowest temperatures of the day is a 1 unfavorable value, and continuing learning if the knowledge record state is the-1 favorable value until the state is updated to be a 0 baseline value, wherein the corresponding circulating pump frequency is adjusted according to the following rule:
if the lowest temperature on the same day is in the knowledge base (4) and has knowledge records smaller than the temperature value, the initial value refers to the knowledge record parameter value corresponding to the closest temperature value, and if the initial value is not the highest frequency of the circulating pump;
the frequency of the circulating pump is adjusted by taking an initial value or a current knowledge value of-2 Hz as an amplitude until the frequency is a controllable lower limit value of the circulating pump;
the whole optimizing process takes the monitoring result of insufficient heat supply experience and the energy consumption value variation as learning reward basis, and the frequency boundary of the bottom-finding circulating pump is detected until the boundary of insufficient heat supply experience or the energy consumption variation boundary is triggered.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310555811.7A CN116379576B (en) | 2023-05-17 | 2023-05-17 | Energy-saving bottom line optimizing method for heating air-conditioning system based on big data self-learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310555811.7A CN116379576B (en) | 2023-05-17 | 2023-05-17 | Energy-saving bottom line optimizing method for heating air-conditioning system based on big data self-learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116379576A CN116379576A (en) | 2023-07-04 |
CN116379576B true CN116379576B (en) | 2023-10-17 |
Family
ID=86963590
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310555811.7A Active CN116379576B (en) | 2023-05-17 | 2023-05-17 | Energy-saving bottom line optimizing method for heating air-conditioning system based on big data self-learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116379576B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104315673A (en) * | 2014-09-16 | 2015-01-28 | 珠海格力电器股份有限公司 | Fuzzy control system and method for central air conditioner |
CN107192003A (en) * | 2017-05-24 | 2017-09-22 | 青岛海尔空调器有限总公司 | method and device for heating regulation |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107166504A (en) * | 2017-04-18 | 2017-09-15 | 青岛海尔空调器有限总公司 | Method of heating regulation and device |
-
2023
- 2023-05-17 CN CN202310555811.7A patent/CN116379576B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104315673A (en) * | 2014-09-16 | 2015-01-28 | 珠海格力电器股份有限公司 | Fuzzy control system and method for central air conditioner |
CN107192003A (en) * | 2017-05-24 | 2017-09-22 | 青岛海尔空调器有限总公司 | method and device for heating regulation |
Also Published As
Publication number | Publication date |
---|---|
CN116379576A (en) | 2023-07-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108386971B (en) | Energy-saving automatic control system of central air conditioner | |
CN109890176B (en) | Device for optimizing energy consumption efficiency of machine room based on artificial intelligence | |
Hagras et al. | An intelligent agent based approach for energy management in commercial buildings | |
WO2014153552A1 (en) | Building power management systems | |
CN111520812B (en) | Method and system for estimating room temperature of heat supply residents | |
CN114963414B (en) | Intelligent air conditioning system regulating and controlling device based on AI data analysis | |
CN105674487B (en) | Dynamic hydraulic balance adjusting method for central air conditioning system | |
CN109059195A (en) | For cutting down the control method and control system of the central air-conditioning of network load peak value | |
CN114322208B (en) | Intelligent park air conditioner load regulation and control method and system based on deep reinforcement learning | |
CN116085936A (en) | Intelligent energy management system, equipment and medium for central air conditioner energy station | |
Petrie et al. | Energy efficient control methods of HVAC systems for smart campus | |
US20140379139A1 (en) | Systems and methods for balancing an electrical grid with networked buildings | |
CN115682324A (en) | Energy-saving optimization control method, device, equipment and storage medium for central air-conditioning system | |
CN115081220A (en) | Adjusting method and system for high-energy-efficiency central air-conditioning system | |
CN116379576B (en) | Energy-saving bottom line optimizing method for heating air-conditioning system based on big data self-learning | |
CN114706315A (en) | Intelligent device control system, method and storage medium | |
CN114234289A (en) | Multi-working-condition tail end air conditioning system, control method and control device | |
CN116817424B (en) | Air conditioner energy-saving control system and method based on artificial intelligence | |
CN116963461A (en) | Energy saving method and device for machine room air conditioner | |
CN114995543A (en) | Method and device for controlling environment adjusting equipment through Artificial Intelligence (AI) | |
Korolev et al. | Development of the temperature prediction algorithm for smart thermostat | |
JPH02187554A (en) | Airconditioning control system based on building monitor and control device | |
CN115451550B (en) | Central air conditioning system total energy consumption base line optimizing algorithm based on optimal supply and demand balance | |
CN118153353B (en) | Dynamic simulation optimizing method and related device for air conditioner | |
CN117329665B (en) | Air conditioner indoor linkage control method and system based on intelligent AI algorithm |
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 |