CN110779173A - Model-free optimized operation control method for water chilling unit based on reinforcement learning - Google Patents
Model-free optimized operation control method for water chilling unit based on reinforcement learning Download PDFInfo
- Publication number
- CN110779173A CN110779173A CN201911107402.0A CN201911107402A CN110779173A CN 110779173 A CN110779173 A CN 110779173A CN 201911107402 A CN201911107402 A CN 201911107402A CN 110779173 A CN110779173 A CN 110779173A
- Authority
- CN
- China
- Prior art keywords
- latest
- chilling unit
- score
- temperature
- water chilling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- F24F11/64—Electronic processing using pre-stored data
-
- 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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
- F24F2110/12—Temperature of the outside air
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/20—Humidity
- F24F2110/22—Humidity of the outside air
Abstract
A model-free optimization operation control method for a water chilling unit based on reinforcement learning is characterized by obtaining the latest system operation state data, calculating the latest operation score and recording the latest operation score; obtaining a plurality of historical operating records; comparing whether the operation condition of the previous record is close to that of the latest record, if so, executing a model-free optimizing process, and if not, inquiring whether a history record close to the operation condition of the latest record exists in the history operation records; if a historical record close to the latest recorded operation condition does not exist in the historical operation records, the chilled water outlet temperature set point of the water chilling unit is adjusted to a nominal value, if the historical operation records do not exist, the chilled water outlet temperature set point of the water chilling unit is adjusted to the chilled water outlet temperature value with the highest operation score in the historical record, and a model-free optimization process is executed.
Description
Technical Field
The invention relates to the field of control of water chilling units, in particular to a model-free optimal operation control method of a water chilling unit based on reinforcement learning.
Background
For many buildings, it is indispensable to construct an air conditioning system, wherein controlling a chiller in the air conditioning system is a very important link, generally, the air conditioning system will keep historical data of the chiller so as to regulate and control the chiller, but for a newly-built building and a building air conditioning system without historical data, lack of historical data of the chiller will cause the regulation and control of the chiller to become more difficult, and therefore, how to solve the problem of controlling the newly-built building air conditioning system and the chiller without historical operating data is a key point at present.
Disclosure of Invention
The invention aims to provide a model-free optimal operation control method of a water chilling unit based on reinforcement learning, aiming at the defects in the background art, and the optimal operation control of the water chilling unit in a newly-built building air conditioning system or a building air conditioning system without historical operation data can be realized without using known historical data and equipment performance models.
In order to achieve the purpose, the invention adopts the following technical scheme:
a model-free optimization operation control method for a water chilling unit based on reinforcement learning comprises the following specific steps:
step A: acquiring latest system operation state data, wherein the system operation state data comprises a plurality of state variables, calculating latest operation scores, and recording the latest operation scores and the state variables;
executing the step A at preset time intervals to obtain a plurality of historical operating records;
and B: comparing whether the operation condition of the previous record is close to that of the latest record, namely comparing whether the change of the state variable is less than 5%; if yes, executing a model-free optimizing process, and controlling the water chilling unit according to the result of the model-free optimizing process; if not, inquiring whether a historical record close to the operation condition of the latest record exists in the historical operation records or not;
and C: if the historical operating record does not have a historical record close to the latest recorded operating condition, adjusting the chilled water outlet temperature set point of the water chilling unit to a nominal value, if the historical operating record does not have a historical record close to the latest recorded operating condition, adjusting the chilled water outlet temperature set point of the water chilling unit to the chilled water outlet temperature value with the highest operating score in the historical record, and executing a model-free optimization process.
Preferably, the model-free optimization process includes the following specific steps:
step B1: waiting for the power of the machine room to be stable, and recording the latest operation working condition and operation score;
step B2: calculating the deviation between the actual value and the set point of each temperature point of the water chilling unit, judging whether the weighted mean of all the deviations is less than 0, if so, indicating that excessive cooling is generated, the outlet water temperature of the chilled water is required to be increased, the adjustment direction is one-way, and the outlet water temperature set point of the chilled water of the water chilling unit is increased by 0.2 ℃; if not, the cold supply excess is not generated, and the set point of the outlet water temperature of the chilled water of the water chilling unit is randomly adjusted up or down by 0.2 ℃.
Preferably, the process of calculating the latest running score comprises:
the latest running score, i.e. the total score, is calculated using the formula one:
U＝u
comfort×W
comfort+u
energy×W
enerhy；
wherein:
u represents the latest running score, i.e. the total score;
u
comfortrepresenting a comfort score;
W
comfortrepresenting the weight taken up by the comfort score;
u
energyrepresenting the energy consumption score of the water chilling unit;
W
energyand expressing the weight occupied by the water chilling unit energy consumption score.
Preferably, the method comprises using the deviation of the actual temperature of the wind system from the set point as an argument of the comfort score;
calculating a comfort score using formula two;
wherein:
u
comfortrepresenting a comfort score;
n represents the number of wind system temperature points;
e
ian absolute value indicating a deviation between a set point of the ith temperature point and a value of an actual temperature value;
w
irepresenting the weight corresponding to the ith temperature point;
a represents a coefficient, a-0.02165;
b represents a coefficient, b-1.5330;
exp denotes an exponential function.
Preferably, the method comprises the step of calculating the weight corresponding to the ith temperature point by using a formula III;
wherein:
w
irepresenting the weight corresponding to the ith temperature point;
Q
iindicating the nominal rated heat exchange capacity of the end equipment where the ith temperature point is located;
Σ Q represents the sum of the nominal heat exchange ratings of the end equipment where all temperature points are located.
Preferably, the method comprises the following step of calculating the energy consumption score of the water chilling unit by using the formula four:
wherein:
p is the real-time total power of the refrigeration machine room;
u
energyenergy consumption scoring for representing refrigeration machine room；
P
maxRepresenting the nominal maximum power of the refrigeration machine room.
Preferably, the system operation state data includes a plurality of state variables, specifically, outdoor temperature, outdoor humidity, time, whether the work day is present, real-time total power of the machine room, real-time total cooling capacity of the machine room, chilled water outlet temperature of the chiller, outlet air temperature set value of each air conditioning unit, outlet air temperature measured value of each air conditioning unit, return air temperature set value of each fan coil, and return air temperature measured value of each fan coil.
Preferably, comparing whether the operation condition of the previous record is close to that of the latest record includes judging whether the outdoor temperature, the outdoor humidity and the total cold change of the machine room are less than 5% in the previous record and the latest record.
Preferably, the process of querying whether a history record close to the latest recorded operation condition exists in the history operation records is as follows:
and acquiring the indoor temperature, the outdoor humidity and the total cooling capacity of the machine room of each historical record in the historical operation records, comparing the indoor temperature, the outdoor humidity and the total cooling capacity of the machine room with the current latest record, and judging whether the deviation of the three variables is less than 5% or not, wherein if the deviation is less than 5%, the historical record is closest to the operation working condition of the latest record.
Drawings
FIG. 1 is a chart of historical operating data of the present invention;
FIG. 2 is a diagram of the comfort score function of the present invention;
FIG. 3 is a graph of the energy consumption scoring function of the present invention;
FIG. 4 is an optimization flow diagram of the present invention;
FIG. 5 is a model-free optimization flow diagram of the present invention.
Detailed Description
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings.
The orientation of the embodiment is based on the attached drawings of the specification.
The invention discloses a model-free optimal operation control method of a water chilling unit based on reinforcement learning, which comprises the following specific steps as shown in figure 4:
step A: acquiring latest system operation state data from a building automation system, wherein the system operation state data comprises a plurality of state variables, as shown in fig. 1, the state data comprises outdoor temperature, outdoor humidity, time, whether a working day is, real-time total power of a machine room, real-time total cooling capacity of the machine room, chilled water outlet temperature of a water chilling unit, an outlet air temperature set value of each air conditioning unit, an outlet air temperature measured value of each air conditioning unit, an return air temperature set value of each fan coil and a return air temperature measured value of each fan coil;
calculating the latest operation score by using formulas I to IV, and recording the latest operation score and the state variable;
the latest running score, i.e. the total score, is calculated using the formula one:
U＝u
comfort×W
comfort+u
energy×W
energy；
wherein:
u represents the latest running score, i.e. the total score;
u
comfortrepresenting a comfort score;
W
comfortrepresenting the weight taken up by the comfort score;
u
energyrepresenting the energy consumption score of the water chilling unit;
W
energyrepresenting the weight occupied by the water chilling unit energy consumption score;
the weighted values are set according to different requirements of a building manager on comfort and energy consumption, the sum of the weighted values is 1, namely W
comfort+W
energy＝1。
Preferably, the method comprises using the deviation of the actual temperature of the wind system from the set point as an argument of the comfort score;
calculating a comfort score using formula two;
wherein:
u
comfortrepresenting a comfort score;
n represents the number of wind system temperature points;
e
ian absolute value indicating a deviation between a set point of the ith temperature point and a value of an actual temperature value;
w
irepresenting the weight corresponding to the ith temperature point;
a represents a coefficient, a-0.02165;
b represents a coefficient, b-1.5330;
exp denotes an exponential function.
Preferably, the method comprises the step of calculating the weight corresponding to the ith temperature point by using a formula III;
wherein:
w
irepresenting the weight corresponding to the ith temperature point;
Q
iindicating the nominal rated heat exchange capacity of the end equipment (air conditioning unit or fan coil) where the ith temperature point is located;
Σ Q represents the sum of the nominal rated heat exchange capacity of the end equipment (air conditioning unit or fan coil) where all temperature points are located.
The comfort score function diagram of a single temperature point is shown in fig. 2, and when the actual temperature value is not deviated from the set point, the comfort score is 1, and when the deviation between the set temperature value and the set point is more than or equal to 5 ℃, the comfort score is 0.
Preferably, the method comprises the following step of calculating the energy consumption score of the water chilling unit by using the formula four:
wherein:
p is the real-time total power of the refrigeration machine room;
u
energyexpressing the energy consumption score of the refrigeration machine room;
P
maxrepresents a nominal maximum power of the refrigeration machine room;
the functional diagram corresponding to the formula four is shown in fig. 3, when the total power of the refrigeration machine room is 0, the energy consumption score is 1, and when the total power of the refrigeration machine room reaches the nominal maximum power, the energy consumption score is 0.
Executing the step A at preset time intervals to obtain a plurality of historical operating records;
and B: and comparing whether the operation working conditions of the previous record and the latest record are close to each other, namely judging whether the outdoor temperature, the outdoor humidity and the total cold quantity of the machine room change by less than 5 percent or not in the previous record and the latest record. (ii) a If yes, executing a model-free optimizing process, and controlling the water chilling unit according to the result of the model-free optimizing process; if not, inquiring whether a history record close to the operation condition of the latest record exists in the history operation records, namely acquiring the indoor temperature, the outdoor humidity and the total cooling capacity of the machine room of each history record in the history operation records, comparing with the current latest record, judging whether the deviation of the three variables is less than 5%, and if so, judging that the operation condition of the history record is closest to the operation condition of the latest record;
and C: if the historical operating record does not have a historical record close to the latest recorded operating condition, adjusting the chilled water outlet temperature set point of the water chilling unit to a nominal value, if the historical operating record does not have a historical record close to the latest recorded operating condition, adjusting the chilled water outlet temperature set point of the water chilling unit to the chilled water outlet temperature value with the highest operating score in the historical record, and executing a model-free optimization process.
Preferably, as shown in fig. 5, the specific steps of the model-free optimization process are as follows:
step B1: waiting for the machine room power to be stable (namely the range of all power data points is less than 1% of the mean value in one minute), and recording the latest operation working condition and operation score;
step B2: calculating the deviation of the actual value and the set point of each temperature point of the water chilling unit, judging whether the weighted mean of all the deviations is less than 0, if so, indicating that excessive cooling is generated, the outlet water temperature of chilled water should be increased, the adjustment direction is one-way, increasing the outlet water temperature set point of the chilled water of the water chilling unit by 0.2 ℃, and at the moment, improving the outlet water temperature skill of the chilled water of the water chilling unit to save energy consumption and also improve indoor comfort; if not, the excessive cooling is not generated, the set point of the outlet water temperature of the chilled water of the water chilling unit is randomly adjusted up or down by 0.2 ℃, if the set point is adjusted up by 0.2 ℃, the energy consumption score is increased, the comfort level score is decreased, and if the set point is adjusted down by 0.2 ℃, the energy consumption score is decreased, and the comfort level score is increased.
The technical principle of the present invention is described above in connection with specific embodiments. The description is made for the purpose of illustrating the principles of the invention and should not be construed in any way as limiting the scope of the invention. Based on the explanations herein, those skilled in the art will be able to conceive of other embodiments of the present invention without inventive effort, which would fall within the scope of the present invention.
Claims (9)
1. A model-free optimization operation control method for a water chilling unit based on reinforcement learning is characterized by comprising the following steps: the method comprises the following specific steps:
step A: acquiring latest system operation state data, wherein the system operation state data comprises a plurality of state variables, calculating latest operation scores, and recording the latest operation scores and the state variables;
executing the step A at preset time intervals to obtain a plurality of historical operating records;
and B: comparing whether the operation condition of the previous record is close to that of the latest record, namely comparing whether the change of the state variable is less than 5%; if yes, executing a model-free optimizing process, and controlling the water chilling unit according to the result of the model-free optimizing process; if not, inquiring whether a historical record close to the operation condition of the latest record exists in the historical operation records or not;
and C: if the historical operating record does not have a historical record close to the latest recorded operating condition, adjusting the chilled water outlet temperature set point of the water chilling unit to a nominal value, if the historical operating record does not have a historical record close to the latest recorded operating condition, adjusting the chilled water outlet temperature set point of the water chilling unit to the chilled water outlet temperature value with the highest operating score in the historical record, and executing a model-free optimization process.
2. The model-free optimized operation control method for the water chilling unit based on reinforcement learning is characterized by comprising the following steps of:
the model-free optimization process comprises the following specific steps:
step B1: waiting for the power of the machine room to be stable, and recording the latest operation working condition and operation score;
step B2: calculating the deviation between the actual value and the set point of each temperature point of the water chilling unit, judging whether the weighted mean of all the deviations is less than 0, if so, indicating that excessive cooling is generated, the outlet water temperature of the chilled water is required to be increased, the adjustment direction is one-way, and the outlet water temperature set point of the chilled water of the water chilling unit is increased by 0.2 ℃; if not, the cold supply excess is not generated, and the set point of the outlet water temperature of the chilled water of the water chilling unit is randomly adjusted up or down by 0.2 ℃.
3. The model-free optimized operation control method for the water chilling unit based on reinforcement learning is characterized by comprising the following steps of:
the process comprises the following steps of calculating the latest running score:
the latest running score, i.e. the total score, is calculated using the formula one:
U＝u
comfort×W
comfort+u
energy×W
energy；
wherein:
u represents the latest running score, i.e. the total score;
u
comfortrepresenting a comfort score;
W
comfortrepresenting the weight taken up by the comfort score;
u
energyrepresenting the energy consumption score of the water chilling unit;
W
energyand expressing the weight occupied by the water chilling unit energy consumption score.
4. The model-free optimized operation control method for the water chilling unit based on reinforcement learning is characterized by comprising the following steps of:
including using the deviation of the actual temperature of the wind system from the set point as an independent variable of the comfort score;
calculating a comfort score using formula two;
wherein:
u
comfortrepresenting a comfort score;
n represents the number of wind system temperature points;
e
ian absolute value indicating a deviation between a set point of the ith temperature point and a value of an actual temperature value;
w
irepresenting the weight corresponding to the ith temperature point;
a represents a coefficient, a-0.02165;
b represents a coefficient, b-1.5330;
exp denotes an exponential function.
5. The model-free optimized operation control method for the water chilling unit based on reinforcement learning is characterized by comprising the following steps of:
calculating the weight corresponding to the ith temperature point by using a formula III;
wherein:
w
irepresenting the weight corresponding to the ith temperature point;
Q
iindicating the nominal rated heat exchange capacity of the end equipment where the ith temperature point is located;
Σ Q represents the sum of the nominal heat exchange ratings of the end equipment where all temperature points are located.
6. The model-free optimized operation control method for the water chilling unit based on reinforcement learning is characterized by comprising the following steps of:
the method comprises the following steps of calculating the energy consumption score of the water chilling unit by using a formula IV:
wherein:
p is the real-time total power of the refrigeration machine room;
u
energyexpressing the energy consumption score of the refrigeration machine room;
P
maxrepresenting the nominal maximum power of the refrigeration machine room.
7. The model-free optimized operation control method for the water chilling unit based on reinforcement learning is characterized by comprising the following steps of:
the system operation state data comprises a plurality of state variables, specifically, outdoor temperature, outdoor humidity, time, working day, real-time total power of the machine room, real-time total cooling capacity of the machine room, chilled water outlet temperature of the water chiller, outlet air temperature set value of each air conditioning unit, outlet air temperature measured value of each air conditioning unit, return air temperature set value of each fan coil, and return air temperature measured value of each fan coil.
8. The model-free optimized operation control method for the water chilling unit based on reinforcement learning of claim 7 is characterized in that:
and comparing whether the operation working conditions of the previous record and the latest record are close to each other, wherein the comparison comprises judging whether the outdoor temperature, the outdoor humidity and the total cold quantity of the machine room change by less than 5 percent.
9. The model-free optimized operation control method for the water chilling unit based on the reinforcement learning of claim 7 is characterized in that:
the process of inquiring whether a historical record close to the latest recorded operation condition exists in the historical operation records is as follows:
and acquiring the indoor temperature, the outdoor humidity and the total cooling capacity of the machine room of each historical record in the historical operation records, comparing the indoor temperature, the outdoor humidity and the total cooling capacity of the machine room with the current latest record, and judging whether the deviation of the three variables is less than 5% or not, wherein if the deviation is less than 5%, the historical record is closest to the operation working condition of the latest record.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911107402.0A CN110779173A (en) | 2019-11-13 | 2019-11-13 | Model-free optimized operation control method for water chilling unit based on reinforcement learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911107402.0A CN110779173A (en) | 2019-11-13 | 2019-11-13 | Model-free optimized operation control method for water chilling unit based on reinforcement learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110779173A true CN110779173A (en) | 2020-02-11 |
Family
ID=69390826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911107402.0A Pending CN110779173A (en) | 2019-11-13 | 2019-11-13 | Model-free optimized operation control method for water chilling unit based on reinforcement learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110779173A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113704071A (en) * | 2021-07-30 | 2021-11-26 | 济南浪潮数据技术有限公司 | Method, device, equipment and readable medium for predicting health condition of server |
| CN117032348A (en) * | 2023-10-10 | 2023-11-10 | 郯城众一科环化工有限公司 | Chemical reaction kettle temperature control method, system, equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924470A (en) * | 2005-09-02 | 2007-03-07 | 浙江工业大学 | Air conditioner controller with comfortable, energy-saving and healthy functions |
| CN103994551A (en) * | 2014-05-28 | 2014-08-20 | 施晓亚 | Energy management method and system |
| CN105320184A (en) * | 2014-11-26 | 2016-02-10 | 华北电力大学 | Intelligent monitoring system of indoor environment of building |
| CN105352108A (en) * | 2015-09-29 | 2016-02-24 | 中国电力科学研究院 | Load optimization control method based on air conditioner electricity utilization mode |
| KR101691555B1 (en) * | 2016-06-08 | 2016-12-30 | 주식회사 세컨드찬스 | HDDLESS computer management system |
| CN106918116A (en) * | 2017-02-24 | 2017-07-04 | 青岛海尔空调电子有限公司 | A kind of control method of the base station air conditioner of many air supply patterns |
| JP2018071811A (en) * | 2016-10-25 | 2018-05-10 | 三菱電機ビルテクノサービス株式会社 | Air conditioning control device and program |
| CN109341014A (en) * | 2018-09-30 | 2019-02-15 | 广东美的制冷设备有限公司 | Air conditioner and its control method, device |
| CN109827299A (en) * | 2019-04-03 | 2019-05-31 | 广州星辰热能股份有限公司 | Based on Internet of Things air-treatment unit adjusting method, device, system and medium |
| CN110410960A (en) * | 2019-07-31 | 2019-11-05 | 广州市特沃能源管理有限公司 | A kind of fan coil forecast Control Algorithm |
-
2019
- 2019-11-13 CN CN201911107402.0A patent/CN110779173A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924470A (en) * | 2005-09-02 | 2007-03-07 | 浙江工业大学 | Air conditioner controller with comfortable, energy-saving and healthy functions |
| CN103994551A (en) * | 2014-05-28 | 2014-08-20 | 施晓亚 | Energy management method and system |
| CN105320184A (en) * | 2014-11-26 | 2016-02-10 | 华北电力大学 | Intelligent monitoring system of indoor environment of building |
| CN105352108A (en) * | 2015-09-29 | 2016-02-24 | 中国电力科学研究院 | Load optimization control method based on air conditioner electricity utilization mode |
| KR101691555B1 (en) * | 2016-06-08 | 2016-12-30 | 주식회사 세컨드찬스 | HDDLESS computer management system |
| JP2018071811A (en) * | 2016-10-25 | 2018-05-10 | 三菱電機ビルテクノサービス株式会社 | Air conditioning control device and program |
| CN106918116A (en) * | 2017-02-24 | 2017-07-04 | 青岛海尔空调电子有限公司 | A kind of control method of the base station air conditioner of many air supply patterns |
| CN109341014A (en) * | 2018-09-30 | 2019-02-15 | 广东美的制冷设备有限公司 | Air conditioner and its control method, device |
| CN109827299A (en) * | 2019-04-03 | 2019-05-31 | 广州星辰热能股份有限公司 | Based on Internet of Things air-treatment unit adjusting method, device, system and medium |
| CN110410960A (en) * | 2019-07-31 | 2019-11-05 | 广州市特沃能源管理有限公司 | A kind of fan coil forecast Control Algorithm |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113704071A (en) * | 2021-07-30 | 2021-11-26 | 济南浪潮数据技术有限公司 | Method, device, equipment and readable medium for predicting health condition of server |
| CN117032348A (en) * | 2023-10-10 | 2023-11-10 | 郯城众一科环化工有限公司 | Chemical reaction kettle temperature control method, system, equipment and storage medium |
| CN117032348B (en) * | 2023-10-10 | 2024-01-09 | 郯城众一科环化工有限公司 | Chemical reaction kettle temperature control method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4435533B2 (en) | Heat source system and control device | |
| CN108375175B (en) | Air conditioner system control method and device | |
| CN105605753B (en) | Fresh air air-supply temperature control system based on multi-connected machine and new blower fan composite air conditioner system | |
| CN104713197A (en) | Central air conditioning system optimizing method and system based on mathematic model | |
| WO2019057036A1 (en) | Method for controlling temperature and humidity of air-conditioner, and air-conditioner | |
| CN109917646B (en) | System and method for optimizing operation of regional cooling and heating equipment | |
| WO2023030522A1 (en) | Data center air conditioning system diagnosis method and apparatus | |
| CN114963414B (en) | Intelligent air conditioning system regulating and controlling device based on AI data analysis | |
| CN110779173A (en) | Model-free optimized operation control method for water chilling unit based on reinforcement learning | |
| CN111059727A (en) | Frequency control method for air conditioner compressor | |
| CN112503746A (en) | Control method of cold source system of power station house based on machine learning and particle swarm algorithm | |
| EP4328788A1 (en) | Method and apparatus for calculating energy efficiency of refrigerating machine room, and electronic device | |
| CN212720195U (en) | Cooling water system control device based on system overall energy efficiency ratio COP is best | |
| CN113701321A (en) | Energy-saving frequency conversion control method for central air-conditioning water pump | |
| CN115307280A (en) | Control method and controller of multi-split air conditioning system, air conditioning system and medium | |
| CN200975766Y (en) | Cold quantity regulation system of region centralization cold feeding | |
| CN114659237A (en) | Air conditioner energy efficiency supervision method based on Internet of things | |
| CN110686350A (en) | Control method for predicting self-regulating temperature in real time based on BP neural network, computer readable storage medium and air conditioner | |
| CN110953684B (en) | Control method of air conditioner cooling system and air conditioner | |
| CN112628958B (en) | Air conditioner control method and air conditioner | |
| KR102144674B1 (en) | The Control Strategy of Cooling Tower by Real-time Performance Analysis | |
| CN112728739B (en) | Method and device for determining set value of air supply temperature of air conditioning box based on algorithm prediction | |
| CN110953649A (en) | Prospective control method for staged temperature setting of heating temperature control valve | |
| TWI776544B (en) | Energy-saving control method and device for temperature control equipment | |
| JP5062555B2 (en) | Energy saving air conditioning control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200211 |