CN109798646B - Variable air volume air conditioner control system and method based on big data platform - Google Patents
Variable air volume air conditioner control system and method based on big data platform Download PDFInfo
- Publication number
- CN109798646B CN109798646B CN201910095274.6A CN201910095274A CN109798646B CN 109798646 B CN109798646 B CN 109798646B CN 201910095274 A CN201910095274 A CN 201910095274A CN 109798646 B CN109798646 B CN 109798646B
- Authority
- CN
- China
- Prior art keywords
- control
- data platform
- data
- actuator
- prediction model
- 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
Images
Abstract
The invention discloses a variable air volume air conditioner control system and method based on a big data platform, and relates to the technical field of air conditioner control. The control system comprises a control host, an actuator, a sensor and a server data platform. The control host transmits the running state data of the actuator and the sensor to the server data platform; and the server data platform collects data of a plurality of control hosts, runs a neural network intelligent learning program to set parameters of a nonlinear prediction model, and transmits the parameters back to the control hosts. And loading the nonlinear model parameters by the control host, executing a control program to solve an optimization function by using an optimization algorithm based on the nonlinear prediction model according to the control mode, calculating an actuator optimization value, and finishing the control of the air conditioner temperature. The invention is easy to implement in practical engineering, and can simultaneously meet the control requirements of a comfortable air-conditioning system and an industrial air-conditioning system with high-precision control requirement.
Description
Technical Field
The invention relates to the technical field of air conditioner control, in particular to a variable air volume air conditioner control system and method based on a big data platform.
Background
The centralized air-conditioning system is an important part in building equipment, and along with the development of urban modernization, the building energy consumption is also greatly increased. Therefore, an optimal energy saving control of the central air conditioning system is a necessary trend. Due to the defects of the design concept of the current centralized air-conditioning system, the design capacity of most building air-conditioning systems in China obviously exceeds the actual load requirement of buildings, and the optimization and energy-saving operation control of the centralized air-conditioning system is very necessary in order to reduce the energy waste of the part.
In a VAV control system with a remote operation function in the prior art, a control module is connected to a communication module and connected to a client control end. However, the technology only can show advantages in maintenance and debugging, and the actual control method is not improved.
In addition, the invention combines the obvious energy saving of the variable static pressure and the advanced and intuitive combination of the total air volume, and continuously corrects the design rotating speed of the total air volume method by the variable static pressure method, so that the VAV variable air volume system obtains better energy saving effect. However, the optimized energy-saving control device still belongs to feedback closed-loop control. Because building systems all have very strong thermal inertia, the simple feedback system is easy to have problems of instability, overshoot, lag and the like under the condition of large disturbance quantity.
The existing prediction control method of the VAV variable air volume air conditioning system based on the neural network mainly establishes a neural network prediction model of each module, and comprises the following steps: the air conditioning unit air conditioning system comprises an air conditioning area temperature prediction model, a tail end air valve prediction model, an air conditioning unit main air duct pipeline static pressure prediction model, a main air duct air quantity prediction model, an air supply temperature prediction model, a fresh air valve prediction model and an air quality prediction model. During the training process, many sensors are required to be arranged to obtain training data, which substantially increases the construction and operation costs of the system. On the basis of the models, optimization control variables corresponding to the models are respectively calculated by using an optimization algorithm, which is typical multi-single-target optimization, so that a plurality of optimizers simultaneously run on line, the calculation amount is overlarge, and under the condition of large disturbance, the operation of other optimizers is influenced by the calculation error of any loop, so that the optimization is difficult to implement in actual engineering.
The existing control method is mainly used for a comfortable air conditioning system, and has high precision control requirement on industrial air conditioners, so that a more advanced system control method is needed.
Therefore, those skilled in the art are dedicated to developing a variable air volume air conditioner control system and method based on a large data platform, an indoor temperature prediction optimization control program based on an NARX (dynamic network time series prediction) neural network prediction model is built in a control host of the control system, and the NARX neural network prediction model is obtained through training of the server large data platform. The control system can not only meet the control requirement of a comfortable air-conditioning system, but also meet the advanced control system with high precision control requirement for the control requirement of an industrial air-conditioner.
Disclosure of Invention
In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is how to design an advanced control system and method that can be easily implemented in practical engineering, and can not only meet the requirements of comfortable air conditioning systems, but also meet the control requirements of industrial air conditioners with very high precision control requirements.
In order to achieve the purpose, the invention provides an air volume variable air conditioner control system based on a big data platform.
The control system comprises a control host, an actuator, a sensor and a server data platform, and the temperature is adjusted according to a control mode;
the control host comprises a CPU arithmetic unit, a memory, an I/O data interface, an RS485 communication interface, a 4G communication interface, a WAN communication interface and a power supply; the memory stores an indoor temperature prediction optimization control program based on a nonlinear prediction model, and the control program uses an optimization algorithm to solve an optimization function for calculating an optimized value of the actuator;
the server data platform is provided with a neural network intelligent learning program based on big data and used for setting parameters of the nonlinear prediction model;
the control host and the actuator are connected through the I/O data interface or the RS485 communication interface;
the control host and the sensor are connected through the I/O data interface;
the control host is connected with the server data platform through the 4G communication interface in a wireless network mode, or is connected with the server data platform through the WAN communication interface in a wired network mode;
the control host has a transparent transmission function and transmits the running state data of the actuator and the sensor to the server data platform through the 4G communication interface or the WAN communication interface.
Further, the non-linear predictive model is a NARX neural network predictive model; the parameters of the NARX neural network prediction model comprise input vector weight coefficients and neuron bias coefficients; the optimization algorithm is one of a particle swarm algorithm, a genetic algorithm, a differential evolution algorithm, an immune algorithm, an ant colony algorithm, a simulated annealing algorithm, a tabu search algorithm and a random search algorithm;
the optimization function is:
F3＝ffan(k) (4)
yr(k+i)＝αiy(k)+(1-αi)S,i＝1,...,P (5)
in equations (1) to (5), n is the room number, and y (k) is the actual system output, i.e., the room return air temperature (in degrees centigrade);
is the predicted value of the room return air temperature (centigrade); y isr(k + i) is a reference trajectory; d is the valve opening, D belongs to [0,100 ]](ii) a (percent system); f. offanIs the fan frequency, ffan∈[fmin,fmax](Hz); p is the predicted step number; w1, w2 and w3 are weight coefficients; equation 5 gives the reference trajectory, where S is the room temperature setpoint and α is the softening coefficient (0 < α < 1).
Further, the actuators comprise an electric air valve actuator and a fan variable frequency controller integrated in the VAV box, and the sensors comprise a plurality of temperature sensors;
the electric air valve actuator is connected with the control host through the I/O data interface;
the fan frequency conversion controller is connected with the control host through the RS485 communication interface;
the temperature sensor is connected with the control host through the I/O data interface;
one temperature sensor is arranged at the air supply outlet, and the other temperature sensors are arranged in each room area.
Further, the control system provides two predictive control modes, a high-precision control mode and an energy-saving control mode.
Further, the I/O data interface supports a current range of 4mA to 20mA, and supports a voltage range including 0V to 10V, and 0V to 5V.
Further, the RS485 interface supports modbusRTU, modbusASCIII and PPI serial port protocols.
Further, the server data platform receives data of one or more control hosts to complete deployment of the big data platform.
The invention also provides a variable air volume air conditioner control method based on the big data platform, which is applied to the variable air volume air conditioner control system based on the big data platform and comprises the following steps:
step one, determining the weight of the optimization function in the control host, and setting the control mode;
step two, the control host obtains the actuator data through the I/O data interface or the RS485 communication interface, and reads the sensor data through the I/O data interface;
step three, the control host transmits the actuator data and the sensor data to the server data platform through the 4G communication interface or the WAN communication interface;
on the server data platform, running the big data-based neural network intelligent learning program by using the sensor data and the actuator data uploaded by the host computer, and training the nonlinear prediction model to obtain the trained parameters of the nonlinear prediction model;
fifthly, transmitting the trained parameters of the nonlinear prediction model back to the control host from the server data platform;
step six, the control host machine completes the configuration of the nonlinear prediction model by using the trained parameters of the nonlinear prediction model, then uses the optimization algorithm to solve the optimization function based on the nonlinear prediction model, and calculates to obtain the optimized value of the actuator at the next moment;
and step seven, the control host adjusts the action of the actuator through the RS-485 communication interface and the I/O data interface to complete the optimized control at the next moment.
Further, repeating the second step to the fifth step every other model training period; and repeating the step six and the step seven every other control period.
Further, the model training period is at least 1 month; the control period is 5 minutes to 20 minutes.
In a preferred embodiment of the invention, an indoor temperature prediction optimization control program based on an NARX (dynamic neural network time series prediction) neural network prediction model is built in a control host of the control system, and the NARX neural network prediction model is obtained by training a server big data platform. The control system can provide two prediction control modes according to actual needs, namely a high-precision control mode taking temperature control precision as a target and an energy-saving control mode taking minimum energy consumption as a target. By applying the control method to the control system, the temperature can be controlled according to a predictive control mode.
Compared with the prior art, the invention has the beneficial technical effects that: by using the variable air volume air conditioner control system and method based on the big data platform, the cloud big data platform deployment of the variable air volume air conditioner system can be conveniently realized, and a big data foundation is laid for establishing a high-precision NARX neural network prediction model. In addition, the variable air volume air conditioning control system based on the big data platform can realize high-precision indoor temperature control and optimized energy-saving control of the variable air volume air conditioning system according to an optimization target, and is suitable for optimized control of a comfortable variable air volume air conditioning system and an industrial variable air volume air conditioning system.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of the apparatus of the present invention.
The system comprises a control host, a 2-CPU arithmetic unit, a 3-memory, a 4-I/O data port, a 5-RS485 communication interface, a 6-4G communication interface, a 7-WAN communication interface, an 8-power supply, a 9-server data platform, a 10-electric air valve actuator, a 11-temperature sensor and a 12-fan variable frequency controller, wherein the control host is connected with the control host through a network.
Detailed Description
The technical contents of the preferred embodiments of the present invention will be more clearly and easily understood by referring to the drawings attached to the specification. The present invention may be embodied in many different forms of embodiments and the scope of the invention is not limited to the embodiments set forth herein.
In the drawings, structurally identical elements are represented by like reference numerals, and structurally or functionally similar elements are represented by like reference numerals throughout the several views. The size and thickness of each component shown in the drawings are arbitrarily illustrated, and the present invention is not limited to the size and thickness of each component. The thickness of the components may be exaggerated where appropriate in the figures to improve clarity.
As shown in fig. 1, the embodiment of the present invention includes a control host 1, a CPU operator 2, a memory 3, an I/O data port 4, an RS485 communication interface 5, a 4G communication interface 6, a WAN communication interface 7, a power supply 8, a server data platform 9, an electric air valve actuator 10, a temperature sensor 11, and a fan frequency conversion controller 12.
The CPU arithmetic unit 2, the memory 3, the I/O data interface 4, the RS485 communication interface 5, the 4G communication interface 6, the WAN communication interface 7 and the power supply 8 are arranged in the control host 1. A plurality of electric air valve actuators 10 are integrated in the VAV box for collecting and controlling the opening of each air valve, and are connected with the input and output ends of the I/O data port 4. A plurality of temperature sensors 11(1 temperature sensor is arranged at the air supply outlet and is used for measuring the air supply temperature, and other temperature sensors are arranged in each room area and are used for measuring the indoor temperature) are connected with the input end of the I/O data port 4. The fan frequency conversion controller 12 is connected with the RS485 interface 5. The 4G communication interface 6 is connected with the server data platform 9 through a wireless network, and the WAN communication interface 7 is connected with the server data platform 9 through a wired network. The I/O data interface 4 in the control host 1 supports physical signals of 4-20 mA, 0-10V/0-5V and the like, can be connected with various sensors, actuators and other devices, the RS485 interface 5 supports serial port protocols of modbusRTU, modbusSCII, PPI and the like, and the WAN interface and the 4G interface are communicated with the server data platform 9 in a wired and wireless mode respectively, so that the running state data of the device layer is transmitted to the server data platform 9 for storage. The memory 3 is internally provided with an indoor temperature prediction optimization control program based on a NARX neural network prediction model. The server data platform 9 is installed with a big data-based neural network intelligent learning program for setting the input vector weight coefficient of the NARX neural network prediction model in the memory 3 and the bias coefficient of the neuron.
The VAV box air valve opening degree signal data obtained by an electric air valve actuator 10 and each temperature signal data obtained by a temperature sensor 11 are transmitted into a control host 1 through an input end of an I/O data port 4, fan frequency signal data in a fan frequency conversion controller 12 are transmitted into the control host 1 through an RS485 interface 5, the signal data are transmitted into a server data platform 9 through a 4G communication interface 6 or a WAN communication interface 7 of the control host 1, when the data quantity meets certain requirements, a neural network intelligent learning program in the server data platform 9 carries out online learning according to the obtained data, an input vector weight coefficient and a bias coefficient of a neuron of a NARX neural network prediction model are set, and then the set coefficients are returned to the NARX neural network prediction model in a memory 3 through the 4G communication interface 6 or the WAN communication interface 7, an indoor temperature prediction optimization control program based on a NARX neural network prediction model in the memory 3 starts to work, and according to the air supply temperature, the return air temperature, the fan frequency and the recent historical time values of the opening degrees of the air valves, the optimal values of the fan frequency and the opening degrees of the air valves at the next time are predicted by utilizing an optimization algorithm (such as a particle swarm algorithm PSO).
In this embodiment, when the control system is designed, the optimization function is obtained by the following equation:
the optimization function is:
F3＝ffan(k) (4)
yr(k+i)＝αiy(k)+(1-αi)S,i＝1,...,P (5)
in formulas (1) to (5), n is a room number. y (k) is the actual system output, i.e., room return air temperature (in degrees Celsius);
is the predicted value of the room return air temperature (centigrade); y isr(k + i) is a reference trajectory; d is the valve opening, D belongs to [0,100 ]](ii) a (percent system); f. offanIs the fan frequency, ffan∈[fmin,fmax](Hz); p is the predicted step number; w1, w2 and w3 are weight coefficients; equation 5 gives the reference trajectory, where S is the room temperature setpoint and α is the softening coefficient (0 < α < 1).
The control system of the embodiment can provide two prediction control modes according to actual needs, namely a high-precision control mode taking temperature control precision as a target and an energy-saving control mode taking minimum energy consumption as a target. When w1 is 1, w2 is 0 and w3 is 0, the control system is in a high-precision optimization control mode, namely, the high-precision temperature control is taken as an optimization target; when w1 is 0.5, w2 is 0.25 and w3 is 0.25, the control system is in an energy-saving optimization control mode, namely, the optimization target of minimizing the total energy consumption of the system is taken.
The present embodiment is controlled by using a control method including the steps of:
step one, determining the weight of the optimization function in the control host, and setting the control mode;
step two, the control host obtains the actuator data through the I/O data interface or the RS485 communication interface, and reads the sensor data through the I/O data interface;
step three, the control host transmits the actuator data and the sensor data to the server data platform through the 4G communication interface or the WAN communication interface;
on the server data platform, running the big data-based neural network intelligent learning program by using the sensor data and the actuator data uploaded by the host computer, and training the nonlinear prediction model to obtain the trained parameters of the nonlinear prediction model;
fifthly, transmitting the trained parameters of the nonlinear prediction model back to the control host from the server data platform;
step six, the control host machine completes the configuration of the nonlinear prediction model by using the trained parameters of the nonlinear prediction model, then uses the optimization algorithm to solve the optimization function based on the nonlinear prediction model, and calculates to obtain the optimized value of the actuator at the next moment;
and step seven, the control host adjusts the action of the actuator through the RS-485 communication interface and the I/O data interface to complete the optimized control at the next moment.
The second and third steps are repeated every other model training period (at least 1 month), and the fourth and fifth steps are repeated every other control period (5-20 minutes).
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (9)
1. A variable air volume air conditioner control system based on a big data platform is characterized by comprising a control host, an actuator, a sensor and a server data platform, wherein the temperature is adjusted according to a control mode;
the control host comprises a CPU arithmetic unit, a memory, an I/O data interface, an RS485 communication interface, a 4G communication interface, a WAN communication interface and a power supply; the memory stores an indoor temperature prediction optimization control program based on a nonlinear prediction model, and the control program uses an optimization algorithm to solve an optimization function for calculating an optimized value of the actuator;
the server data platform is provided with a neural network intelligent learning program based on big data and used for setting parameters of the nonlinear prediction model;
the control host and the actuator are connected through the I/O data interface or the RS485 communication interface;
the control host and the sensor are connected through the I/O data interface;
the control host is connected with the server data platform through the 4G communication interface in a wireless network mode, or is connected with the server data platform through the WAN communication interface in a wired network mode;
the control host has a transparent transmission function and transmits the running state data of the actuator and the sensor to the server data platform through the 4G communication interface or the WAN communication interface;
the non-linear prediction model is a NARX neural network prediction model;
the parameters of the NARX neural network prediction model comprise input vector weight coefficients and neuron bias coefficients;
the optimization algorithm is one of a particle swarm algorithm, a genetic algorithm, a differential evolution algorithm, an immune algorithm, an ant colony algorithm, a simulated annealing algorithm, a tabu search algorithm and a random search algorithm;
the optimization function is:
F3＝ffan(k) (4)
yr(k+i)＝αiy(k)+(1-αi)S,i＝1,...,P (5)
in equations (1) to (5), n is the room number, and y (k) is the actual system output, i.e., the room return air temperature (in degrees centigrade);
is the predicted value of the room return air temperature (centigrade); y isr(k + i) is a reference trajectory; d is the valve opening, D belongs to [0,100 ]](ii) a (percent system); f. offanIs the fan frequency, ffan∈[fmin,fmax](Hz); p is the predicted step number; w1, w2 and w3 are weight coefficients; equation 5 gives the reference trajectory, where S is the room temperature setpoint and α is the softening coefficient (0)<α<1)。
2. The big data platform based variable air volume air conditioning control system of claim 1, wherein the actuators comprise an electric air valve actuator and a fan variable frequency controller integrated in a VAV box, and the sensors comprise a plurality of temperature sensors;
the electric air valve actuator is connected with the control host through the I/O data interface;
the fan frequency conversion controller is connected with the control host through the RS485 communication interface;
the temperature sensor is connected with the control host through the I/O data interface;
one temperature sensor is arranged at the air supply outlet, and the other temperature sensors are arranged in each room area.
3. The large data platform-based variable air volume air conditioning control system according to claim 1, wherein the control system provides two predictive control modes, a high-precision control mode and an energy-saving control mode.
4. The large data platform-based variable air volume air conditioning control system of claim 1, wherein the I/O data interface supports a current range of 4mA to 20mA, and supports a voltage range including 0V to 10V, and 0V to 5V.
5. The large data platform-based variable air volume air conditioning control system of claim 1, wherein the RS485 interface supports modbusRTU, modbusscii and PPI serial protocols.
6. The variable air volume air-conditioning control system based on the big data platform as claimed in claim 1, wherein the server data platform receives data of one or more control hosts to complete deployment of the big data platform.
7. A variable air volume air conditioner control method based on a big data platform is characterized by being applied to the variable air volume air conditioner control system based on the big data platform as claimed in claim 1, and comprising the following steps:
step one, determining the weight of the optimization function in the control host, and setting the control mode;
step two, the control host obtains the actuator data through the I/O data interface or the RS485 communication interface, and reads the sensor data through the I/O data interface;
step three, the control host transmits the actuator data and the sensor data to the server data platform through the 4G communication interface or the WAN communication interface;
on the server data platform, running the big data-based neural network intelligent learning program by using the sensor data and the actuator data uploaded by the host computer, and training the nonlinear prediction model to obtain the trained parameters of the nonlinear prediction model;
fifthly, transmitting the trained parameters of the nonlinear prediction model back to the control host from the server data platform;
step six, the control host machine completes the configuration of the nonlinear prediction model by using the trained parameters of the nonlinear prediction model, then uses the optimization algorithm to solve the optimization function based on the nonlinear prediction model, and calculates to obtain the optimized value of the actuator at the next moment;
and step seven, the control host adjusts the action of the actuator through the RS485 communication interface and the I/O data interface to complete the optimization control at the next moment.
8. The large data platform-based variable air volume air conditioning control method according to claim 7, characterized in that the steps two to five are repeated every other model training period; and repeating the step six and the step seven every other control period.
9. The large data platform-based variable air volume air conditioning control method according to claim 8, wherein the model training period is at least 1 month; the control period is 5 minutes to 20 minutes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910095274.6A CN109798646B (en) | 2019-01-31 | 2019-01-31 | Variable air volume air conditioner control system and method based on big data platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910095274.6A CN109798646B (en) | 2019-01-31 | 2019-01-31 | Variable air volume air conditioner control system and method based on big data platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109798646A CN109798646A (en) | 2019-05-24 |
| CN109798646B true CN109798646B (en) | 2021-03-30 |
Family
ID=66559227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910095274.6A Active CN109798646B (en) | 2019-01-31 | 2019-01-31 | Variable air volume air conditioner control system and method based on big data platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109798646B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110220288A (en) * | 2019-05-27 | 2019-09-10 | 上海真聂思楼宇科技有限公司 | Central air-conditioning system intelligent optimized control method and device based on big data cloud platform |
| CN111365828A (en) * | 2020-03-06 | 2020-07-03 | 上海外高桥万国数据科技发展有限公司 | Model prediction control method for realizing energy-saving temperature control of data center by combining machine learning |
| CN111536662A (en) * | 2020-04-25 | 2020-08-14 | 南京酷朗电子有限公司 | Network type fresh air system and regulation and control method based on big data analysis |
| CN111561772B (en) * | 2020-07-15 | 2020-10-02 | 上海有孚智数云创数字科技有限公司 | Cloud computing data center precision air conditioner energy-saving control method based on data analysis |
| CN113932351B (en) * | 2021-11-05 | 2023-02-03 | 上海理工大学 | Non-uniform temperature field real-time regulation and control system and method based on artificial intelligence algorithm |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102353119A (en) * | 2011-08-09 | 2012-02-15 | 北京建筑工程学院 | Control method of VAV (variable air volume) air-conditioning system |
| CN103234254A (en) * | 2013-04-12 | 2013-08-07 | 惠州Tcl家电集团有限公司 | Server-based method for optimizing performance parameters of air conditioner, air conditioner and server |
| CN203147984U (en) * | 2013-02-26 | 2013-08-21 | 上海华电源牌环境工程有限公司 | Chilled-water storage energy-saving control system |
| US8996141B1 (en) * | 2010-08-26 | 2015-03-31 | Dunan Microstaq, Inc. | Adaptive predictive functional controller |
| CN106777711A (en) * | 2016-12-22 | 2017-05-31 | 石家庄国祥运输设备有限公司 | The method for setting up vehicle-mounted air conditioning system with variable air quantity forecast model |
| CN108151253A (en) * | 2017-12-21 | 2018-06-12 | 中国舰船研究设计中心 | A kind of air quantity variable air conditioner wind pushing temperature automatic compensating method |
-
2019
- 2019-01-31 CN CN201910095274.6A patent/CN109798646B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8996141B1 (en) * | 2010-08-26 | 2015-03-31 | Dunan Microstaq, Inc. | Adaptive predictive functional controller |
| CN102353119A (en) * | 2011-08-09 | 2012-02-15 | 北京建筑工程学院 | Control method of VAV (variable air volume) air-conditioning system |
| CN203147984U (en) * | 2013-02-26 | 2013-08-21 | 上海华电源牌环境工程有限公司 | Chilled-water storage energy-saving control system |
| CN103234254A (en) * | 2013-04-12 | 2013-08-07 | 惠州Tcl家电集团有限公司 | Server-based method for optimizing performance parameters of air conditioner, air conditioner and server |
| CN106777711A (en) * | 2016-12-22 | 2017-05-31 | 石家庄国祥运输设备有限公司 | The method for setting up vehicle-mounted air conditioning system with variable air quantity forecast model |
| CN108151253A (en) * | 2017-12-21 | 2018-06-12 | 中国舰船研究设计中心 | A kind of air quantity variable air conditioner wind pushing temperature automatic compensating method |
Non-Patent Citations (1)
| Title |
|---|
| 《Design and construction of a non-linear model predictive controller for building’s cooling system》;Arash ERFANI等;《Building and Environment》;20180430;正文第237-245页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109798646A (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109798646B (en) | Variable air volume air conditioner control system and method based on big data platform | |
| CN109270842B (en) | Bayesian network-based regional heat supply model prediction control system and method | |
| Homod | Analysis and optimization of HVAC control systems based on energy and performance considerations for smart buildings | |
| CN101861552B (en) | Extremum seeking control with actuator saturation control | |
| Li et al. | Dynamic modeling and control of a direct expansion air conditioning system using artificial neural network | |
| Pfeiffer et al. | Control of temperature and energy consumption in buildings-a review. | |
| Soyguder et al. | Fuzzy adaptive control for the actuators position control and modeling of an expert system | |
| Dai et al. | A decentralized algorithm for optimal distribution in HVAC systems | |
| Li et al. | Rule-based fuzzy control method for static pressure reset using improved Mamdani model in VAV systems | |
| WO2022062339A1 (en) | System and method for controlling air valve of variable air volume cabin unit | |
| CN109990445B (en) | Energy-saving controller and method for variable air volume air conditioning system | |
| CN203396032U (en) | Room temperature control device based on fuzzy self-adaption PID (proportion integration differentiation) | |
| Abdo-Allah et al. | Modeling, analysis, and design of a fuzzy logic controller for an ahu in the sj carew building at memorial university | |
| CN111222191A (en) | Building energy consumption optimization control method and system based on BIM and RFID | |
| Petrie et al. | Energy efficient control methods of HVAC systems for smart campus | |
| CN112032972A (en) | Internet of things central air conditioner self-optimizing control system and method based on cloud computing | |
| CN109857177B (en) | Building electrical energy-saving monitoring method | |
| Zhang et al. | Room temperature and humidity decoupling control of common variable air volume air-conditioning system based on bilinear characteristics | |
| Li et al. | Reinforcement learning-based demand response strategy for thermal energy storage air-conditioning system considering room temperature and humidity setpoints | |
| CN114234384B (en) | Air conditioning optimization control method and system for railway passenger station | |
| CN115935604A (en) | Energy-saving control method and terminal for heating and ventilation system of converter station | |
| Wang et al. | Application of an intelligent PID control in heating ventilating and air-conditioning system | |
| Yang et al. | Modelling and simulation on temperature and humidity decoupling of indoor environment | |
| CN113418288A (en) | Simulation model-based neural network multi-terminal air valve control system and method | |
| Guo et al. | Application of deep reinforcement learning to intelligent distributed humidity 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |