CN113932351B - Non-uniform temperature field real-time regulation and control system and method based on artificial intelligence algorithm - Google Patents
Non-uniform temperature field real-time regulation and control system and method based on artificial intelligence algorithm Download PDFInfo
- Publication number
- CN113932351B CN113932351B CN202111303110.1A CN202111303110A CN113932351B CN 113932351 B CN113932351 B CN 113932351B CN 202111303110 A CN202111303110 A CN 202111303110A CN 113932351 B CN113932351 B CN 113932351B
- Authority
- CN
- China
- Prior art keywords
- air
- temperature
- air supply
- section
- room
- 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
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F7/00—Ventilation
- F24F7/04—Ventilation with ducting systems, e.g. by double walls; with natural circulation
- F24F7/06—Ventilation with ducting systems, e.g. by double walls; with natural circulation with forced air circulation, e.g. by fan positioning of a ventilator in or against a conduit
- F24F7/08—Ventilation with ducting systems, e.g. by double walls; with natural circulation with forced air circulation, e.g. by fan positioning of a ventilator in or against a conduit with separate ducts for supplied and exhausted air with provisions for reversal of the input and output systems
-
- 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
- F24F11/70—Control systems characterised by their outputs; Constructional details thereof
- F24F11/72—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure
- F24F11/74—Control systems characterised by their outputs; Constructional details thereof for controlling the supply of treated air, e.g. its pressure for controlling air flow rate or air velocity
-
- 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
- F24F11/84—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 valves
-
- 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
- F24F11/89—Arrangement or mounting of control or safety devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F7/00—Ventilation
- F24F7/003—Ventilation in combination with air cleaning
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F8/00—Treatment, e.g. purification, of air supplied to human living or working spaces otherwise than by heating, cooling, humidifying or drying
- F24F8/10—Treatment, e.g. purification, of air supplied to human living or working spaces otherwise than by heating, cooling, humidifying or drying by separation, e.g. by filtering
-
- 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
-
- 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)
- Fluid Mechanics (AREA)
- Air Conditioning Control Device (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a non-uniform temperature field real-time regulation and control system and a method based on an artificial intelligence algorithm, wherein the method comprises the following steps: the fresh air pipe comprises a fresh air and return air mixing section, an air filtering section integrally communicated with the fresh air and return air mixing section, a surface cooling section integrally communicated with the air filtering section, a fan section integrally communicated with the surface cooling section and an air outlet section integrally communicated with the fan section, wherein a surface cooler is arranged in the surface cooling section, and a water quantity regulating valve is arranged at an inlet section of the surface cooler; the air supply pipe is communicated with the air outlet section, a plurality of temperature sensors are arranged in the room, and an air supply temperature sensor is arranged in the system air supply pipe; an air return pipe is arranged in the room. According to the invention, the device is more intelligent, high in precision and strong in stability, and can be used for constructing a non-uniform temperature device according to self requirements, thereby solving the defect that most ventilation systems face the indoor single parameter requirement and can only finally construct a consistent indoor parameter environment.
Description
Technical Field
The invention relates to the technical field of ventilation systems, in particular to a non-uniform temperature field real-time regulation and control system and method based on an artificial intelligence algorithm.
Background
The main purpose of the heating, ventilating and air conditioning is to create appropriate environmental parameters (temperature, wind speed, humidity, pollutant concentration, etc.) for the building to ensure the requirements of indoor personnel or equipment. The unreasonable ventilation of the air conditioner brings about a plurality of problems, although the ventilation system is continuously developed by the concept of guaranteeing the requirements, most of the ventilation systems face the indoor single-parameter requirement (such as the indoor design temperature of 26 ℃) and finally the generally consistent indoor parameter environment is created. In many cases, different areas or locations in the same room may have different parameter requirements. As in data centers, the high density of electronic components causes thermal coupling resulting in the presence of high temperature environments. Due to the hardware layout, the thermal load is unevenly distributed in space. Against this background, the object of the present invention is to create a method which makes it possible to solve the problem of inhomogeneous temperature field control. The prior art means is to adopt single-loop feedback control to solve the problem, but the coupling exists among various points in the actual room, and the system is difficult to stabilize.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide the system and the method for regulating and controlling the non-uniform temperature field in real time based on the artificial intelligence algorithm, which are more intelligent, have high precision and strong stability, can construct a non-uniform temperature device according to the self requirement, and solve the defect that most ventilation systems face the requirement of indoor single parameter and can only finally construct a consistent indoor parameter environment at present. To achieve the above objects and other advantages in accordance with the present invention, there is provided a non-uniform temperature field real-time regulation system based on artificial intelligence algorithm, comprising:
the fresh air pipe comprises a fresh air and return air mixing section, an air filtering section integrally communicated with the fresh air and return air mixing section, a surface cooling section integrally communicated with the air filtering section, a fan section integrally communicated with the surface cooling section and an air outlet section integrally communicated with the fan section, wherein a surface cooler is arranged in the surface cooling section, and a water quantity regulating valve is arranged at an inlet section of the surface cooler;
the air supply pipe is communicated with the air outlet section, the air supply pipe is connected with a plurality of branch air supply pipes, the air supply pipe is provided with a plurality of branch air supply pipelines, each branch air supply pipeline is provided with an air supply outlet air valve and a temperature sensor, the branch air supply pipelines are communicated with a room, a plurality of temperature sensors are arranged in the room, a return air pipe is arranged in the room, the temperature sensors are in signal connection with an editable logic controller, and the editable logic controller is in signal connection with an embedded computer, a surface cooler, an air supply outlet air valve, a temperature sensor and a water quantity regulating valve.
Preferably, the temperature sensor is used for reading the indoor temperature and converting a physical signal into an electric signal to be transmitted into the programmable logic controller, and the programmable logic controller is used for converting the obtained electric signal into a digital signal to be transmitted to the embedded computer or the programmable logic controller is used for controlling the sizes of the blast outlet air valve and the surface cooler through the electric signal.
Preferably, the embedded computer is used for completing a control algorithm of the indoor non-uniform environmental field, and digital commands obtained by the algorithm are converted into digital signals and returned to the programmable logic controller.
A non-uniform temperature field real-time regulation and control system method based on an artificial intelligence prediction algorithm comprises the following steps:
s1, presetting the air volume and the water volume change range of an indoor room, and determining an interval;
s2, establishing a physical model required by a simulated thermal environment by using CFD software;
s3, setting boundary conditions for CFD calculation, and selecting a plurality of simulation working conditions required by a prediction algorithm;
s4, extracting data of each working condition, and sorting and calculating the data;
s5, reconstructing new flow field information according to a formula 5, and storing the new flow field information into a text file for subsequent adjustment and analysis;
s6, storing the optimal air supply parameters obtained in the S5 into an embedded computer;
s7, inputting the air supply parameter result to a Programmable Logic Controller (PLC) from an embedded computer in the form of an electric signal;
s8, collecting temperature signals in the user-defined non-uniform temperature field through a thermocouple temperature sensor;
s9, acquiring signals through a temperature sensor and inputting the signals to a PLC;
s10, the temperature value read by the PLC realizes data exchange by using a transmission control protocol through a modbus module in python, and transmits a data signal to the embedded computer;
s11, the embedded computer compares the actual temperature of the room with the actual temperature of the room, and then inputs the corrected result as a signal to obtain the optimal air supply parameter and the optimal working condition value under the required temperature value;
s12, transmitting the corrected data back to the PLC by the same data exchange method as the step S10;
and S13, controlling each branch pipe air valve and each water quantity regulating valve through the PLC by transmitting the result obtained by the algorithm through electric signals, controlling the actual air supply temperature and air supply speed of the room, and finishing closed-loop control.
A non-uniform temperature field real-time regulation and control system method based on an artificial intelligence mechanical learning algorithm comprises the following steps:
s1, presetting air supply parameter boundary conditions of a certain experimental cabin or room environment, namely air supply temperature ranges and air supply speed ranges of air supply outlets, and sequentially designing a plurality of groups of air supply conditions within a prediction range;
and S2, selecting a training set. Setting a first group as an initial training working condition, operating the room air conditioning unit for seven days after the temperature in a room is stable (determined by a temperature sensor in the room), automatically reading and storing data every hour, wherein the stored data are respectively the input end: 4 indoor temperature monitoring points and 1 outdoor temperature; output end: the 4 air supply outlets supply air at different speeds and temperatures. Summarizing the read data set to a PLC and converting the data set into an electric signal for an embedded computer to calculate;
s3, training an output end and an input end by adopting a bp neural network to obtain an initial network;
s4, operating the room air conditioning unit again for seven days by taking the second group as an input parameter within a preset air supply parameter range, automatically reading stored data every hour, and sending obtained output values to each air valve and each water quantity regulating valve to control the room temperature;
s5, merging the first group of monitoring input set output sets and the second group of monitoring input set output sets, optimizing and preprocessing the data sets, eliminating redundant or gross errors and data appearing many times, and training the processed data results to obtain a new network;
s6, operating the room air conditioning unit again for seven days by taking the third group as an input parameter within a preset air supply parameter range, automatically reading stored data every hour, and sending obtained output values to each air valve and a water quantity regulating valve to control the room temperature;
and S7, optimizing the data set to obtain a new network by combining the data results of the S5 and the S6 again, and realizing continuous updating and iteration of the network.
Compared with the prior art, the invention has the beneficial effects that:
(1) The invention is based on the programmable logic controller, according to the feedback instruction of the embedded computer, and then the opening of the air valve and the water valve of the air conditioning unit are controlled through the connection of the wires, and under the combined action of the controlled air valve and the water valve through the air pipe, the water pipe, the air conditioning box and the like, the actual air supply condition (the air supply speed and the air supply temperature of each air supply outlet) sent into a room is obtained, and finally the temperature of the indoor temperature sensor is regulated and controlled to the target range.
(2) According to the invention, data of each sensor monitoring point in a room are summarized by using the editable logic controller, information is input into the embedded AI controller, corresponding air supply parameters are obtained by calculating by using an artificial intelligence algorithm of a non-uniform temperature field, and the temperature between each point in the room is decoupled and analyzed by using the algorithm, so that the real-time regulation and control of the non-uniform temperature field based on the artificial intelligence algorithm are realized.
Drawings
FIG. 1 is a connection diagram of a non-uniform temperature field real-time regulation system of the non-uniform temperature field real-time regulation system and method based on artificial intelligence algorithm according to the present invention;
FIG. 2 is a logic relationship diagram of the non-uniform temperature field real-time regulation system and method based on artificial intelligence algorithm according to the present invention;
FIG. 3 is a block diagram of a monitoring and correcting system flow of an intrinsic orthogonal decomposition method of the non-uniform temperature field real-time regulation and control system and method based on an artificial intelligence algorithm according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, a non-uniform temperature field real-time regulation and control system based on artificial intelligence algorithm includes: the fresh air pipe comprises a fresh air and return air mixing section, an air filtering section integrally communicated with the fresh air and return air mixing section, a surface cooling section integrally communicated with the air filtering section, a fan section integrally communicated with the surface cooling section and an air outlet section integrally communicated with the fan section, a surface cooler is arranged in the surface cooling section, and a water quantity regulating valve is arranged at an inlet section of the surface cooler; the air supply pipe is communicated with the air outlet section and is provided with a plurality of branch air supply pipelines, each branch air supply pipeline is provided with an air supply outlet air valve and an air supply temperature sensor, the branch air supply pipelines are communicated with a room, a plurality of temperature sensors are arranged in the room, one end, far away from the branch air supply pipelines, in the room is connected with an air return pipe, the temperature sensors are in signal connection with an editable logic controller, a cooling water pipe is arranged on the surface air cooler, a cooling water pipe valve is arranged on the cooling water pipe, the editable logic controller is in signal connection with an embedded computer, the surface air cooler, the air supply outlet air valves, the temperature sensors and the cooling water pipe valve, the temperature sensors are firstly arranged at a proper position, and signals are sequentially sent into the editable logic controller and the embeddable computer by starting a system. By means of the existing intelligent algorithm, the control signals obtained through operation are returned to the editable logic controller, and then the opening degrees of air valves and cooling water valves of different air supply outlets are controlled, the air supply speed and the air supply temperature are influenced, and finally the set target non-uniform temperature environment is obtained. The invention is used for building a self-defined non-uniform temperature field in a space, the device has the advantages of self-adaptability of temperature building, high precision, easy installation and strong stability, and the actual air supply condition (the air supply speed and the air supply temperature of each air supply outlet) sent into a room is obtained under the combined action of the controlled air valve and the controlled water valve through the air pipe, the water pipe, the air conditioning box and the like, so that the temperature of the indoor temperature sensor is finally regulated to the target range.
Furthermore, the temperature sensor is used for reading the indoor temperature and converting a physical signal into an electric signal to be transmitted into the programmable logic controller, and the programmable logic controller is used for converting the obtained electric signal into a digital signal to be transmitted to the embedded computer or the programmable logic controller and used for controlling the sizes of the air valve of the air supply outlet and the surface cooler through the electric signal.
Furthermore, the embedded computer is used for completing a control algorithm of the indoor non-uniform environmental field, and digital commands obtained by the algorithm are converted into digital signals and returned to the programmable logic controller.
Example 1
Prediction algorithm
POD method basic principle: according to the method, an environment field in a building is simulated through Computational Fluid Dynamics (CFD) to obtain a small number of data samples, the number of the samples is determined by judging errors between a difference value adjacent sample result and a CFD simulation result, and then a causal relationship between an air supply parameter and an indoor environment field is established through a fluent sample data extraction characteristic by using an intrinsic Orthogonal Decomposition (POD) method, so that the flow field information under any air supply parameter can be reconstructed quickly. On the basis, air supply parameter optimizing calculation is provided according to different target temperatures of a plurality of demand points, namely temperature values of the demand points under all air supply parameters in an interval are reconstructed, the error between the temperature values and the set target temperature is judged, and the optimal air supply parameter meeting the demand is determined.
Prediction-based intelligent control algorithm:
s1, presetting the air volume and the water volume change range of an indoor room, and determining an interval;
s2, establishing a physical model required by a simulated thermal environment by using CFD software;
s3, setting boundary conditions for CFD calculation, and selecting a plurality of simulation working conditions required by a prediction algorithm;
s4, extracting data of each working condition, and sorting and calculating the data, wherein the calculation theory and details are as follows:
first, the flow field variable U in the data may be defined by a boundary parameter (q) 1 ,q 2 ,…q n ) Uniquely determined, then for a sample database consisting of M flow field variables
A set of most representative intrinsic orthogonal bases can be obtained by extracting POD modes
Even if the projection of any vector in the sample database on the orthogonal basis is maximized, namely:
in the formula, λ i The eigenvalues corresponding to the autocovariance matrix composed of the sample data are arranged in the order from big to small, and the magnitude of the eigenvalue represents the energy content of the vector. Thus, there are:
in the formula (I), the compound is shown in the specification,
v is all the modes in the sample database i For the reordered lambda i ，
Is λ i The corresponding feature vector. Since any vector in the database can be projected onto the derived modality, then:
in the formula (I), the compound is shown in the specification,
and solving to obtain modal coefficients corresponding to any group of parameters through the difference values, and linearly combining the modal coefficients with the modal to obtain predicted flow field data. Namely:
and S5, reconstructing new flow field information according to a formula 5, and storing the new flow field information into a text file for subsequent adjustment and analysis.
The optimization formula is defined as:
wherein E is the average error, n is the number of selected reconstruction points, U i Is a reconstructed value of the ith point, V i Is the target value of the ith point. The optimization process finds the air supply parameter when the E value is minimum.
S6, storing the optimal air supply parameters obtained in the S5 into an embedded computer;
s7, inputting the air supply parameter result to a Programmable Logic Controller (PLC) from an embedded computer in the form of an electric signal;
s8, collecting temperature signals in the user-defined non-uniform temperature field through a thermocouple temperature sensor;
s9, acquiring signals through a temperature sensor and inputting the signals to a PLC;
s10, the temperature value read by the PLC realizes data exchange by using a transmission control protocol through a modbus module in python, and a data signal is transmitted to the embedded computer;
s11, the embedded computer compares the actual temperature of the room to obtain a difference value delta t between a preset temperature value and an actual temperature value:
if delta t is less than 0.5 ℃, the algorithm effect is considered to be good, and the optimal air supply parameter and the optimal working condition value under the required temperature value are directly obtained;
if the delta t is more than or equal to 0.5 ℃, correcting the parameters:
T′ m ＝T m -(T c -T m )＝2T m -T c 7
in the formula (II), T' m To a new target temperature, T m Is the original target temperature (desired temperature), T c The measured temperature is used.
Inputting the corrected result as a signal to obtain an optimal air supply parameter and an optimal working condition value under a required temperature value;
s12, transmitting the corrected data back to the PLC by the same data exchange method as the step S9;
and S13, controlling each branch pipe air valve and each water quantity regulating valve through the PLC by transmitting the result obtained by the algorithm through electric signals, controlling the actual air supply temperature and air supply speed of the room, and finishing closed-loop control.
The method adopts a working method of centralized sampling and centralized output of a Programmable Logic Controller (PLC), reduces the interference influence of outside air parameters, saves time, and ensures that the algorithm is reliably and quickly carried out; the embedded AI controller (raspberry group) can realize remote control of target room parameters and release manpower and material resources, has strong intelligent algorithm computing capability, is high in optimization computing process efficiency, is easy to obtain optimal design parameters, and is favorable for creating an expected non-uniform temperature field. The two controllers are communicated through a Modbus module of the Python platform to realize transmission control, and the Modbus controller has an authoritative and reliable supporting platform to ensure efficient and stable operation.
Example 2
Mechanical learning training
S1, presetting air supply parameter boundary conditions of a certain experimental cabin or room environment, namely air supply temperature ranges and air supply speed ranges of air supply outlets, and sequentially designing a plurality of groups of air supply conditions within a prediction range;
and S2, selecting a training set. Setting the first group as initial training condition, waiting for the temperature stability in the room (by the room in the temperature sensor confirm), operating room air conditioning unit seven days, each hour automatic reading stores data, stores data respectively and is, the input: 4 indoor temperature monitoring points and 1 outdoor temperature; output end: the air supply speed and the air supply temperature of each of the 4 air supply outlets are controlled. Summarizing the read data set to a PLC and converting the data set into an electric signal for an embedded computer to calculate;
s3, training an output end and an input end by adopting a bp neural network, setting five inputs, namely a hidden layer containing ten neurons and an output layer containing five neurons, and obtaining an initial network;
s4, operating the room air conditioning unit again for seven days by taking the second group as an input parameter within a preset air supply parameter range, automatically reading stored data every hour, and sending obtained output values to each air valve and each water quantity regulating valve to control the room temperature;
s5, combining the first group of monitoring input set output sets and the second group of monitoring input set output sets, optimizing and preprocessing the data sets, eliminating redundant or coarse errors and data appearing many times, and training the processed data results to obtain a new network;
s6, operating the room air conditioning unit for seven days again by taking the third group as an input parameter within a preset air supply parameter range, automatically reading stored data every hour, sending the obtained output value to each air valve and a water quantity regulating valve, and controlling the room temperature;
and S7, optimizing the data set to obtain a new network by combining the data results of the S5 and the S6 again, and realizing continuous updating and iteration of the network.
The number of devices and the scale of the processes described herein are intended to simplify the description of the invention, and applications, modifications and variations of the invention will be apparent to those skilled in the art.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (1)
1. A non-uniform temperature field real-time regulation and control method based on an artificial intelligence algorithm is characterized by comprising a temperature field real-time regulation and control system:
the fresh air pipe comprises a fresh air and return air mixing section, an air filtering section integrally communicated with the fresh air and return air mixing section, a surface cooling section integrally communicated with the air filtering section, a fan section integrally communicated with the surface cooling section and an air outlet section integrally communicated with the fan section, wherein a surface cooler is arranged in the surface cooling section, and a water quantity regulating valve is arranged at an inlet section of the surface cooler;
the air supply pipe is communicated with the air outlet section, the air supply pipe is connected with a plurality of branch air supply pipes, each branch air supply pipe is provided with an air supply outlet air valve and an air supply temperature sensor, the branch air supply pipes are communicated with a room, a plurality of temperature sensors are arranged in the room, a return air pipe is arranged in the room, the temperature sensors are in signal connection with an editable logic controller, and the editable logic controller is in signal connection with an embedded computer, a surface cooler, an air supply outlet air valve, a temperature sensor and a water quantity regulating valve; the temperature sensor is used for reading indoor temperature and converting a physical signal into an electric signal to be transmitted into the programmable logic controller, the programmable logic controller is used for converting the obtained electric signal into a digital signal to be transmitted to the embedded computer, the embedded computer obtains valve positions corresponding to all valves and returns valve position information to the editable logic controller in a digital model form, and the programmable logic controller is used for controlling the size of an air valve of an air supply outlet and the flow of a coil pipe of the air-conditioning box through the electric signal; the embedded computer calculates the corresponding valve position information of each valve by adopting an algorithm based on a prediction intelligent algorithm to realize the regulation and control of an indoor non-uniform temperature field;
the method comprises the following steps:
s1, presetting the air volume and the water volume change range of an indoor room, and determining an interval;
s2, establishing a physical model required by a simulated thermal environment by using CFD software;
s3, setting boundary conditions of CFD calculation, and selecting a plurality of simulation working conditions required by a prediction algorithm;
s4, extracting data of each working condition, and sorting and calculating the data, wherein the calculation theory and details are as follows:
flow field variables in data
Can be determined by boundary parameters
Uniquely determined, for a sample database consisting of a number of flow field variables
A set of most representative intrinsic orthogonal bases can be obtained by extracting the POD mode
Even if the projection of any vector in the sample database on the orthogonal basis is maximized, namely:
1
in the formula (I), the compound is shown in the specification,
is composed of sample dataThe eigenvalues corresponding to the autocovariance matrix are arranged in the order from big to small, and the magnitude of the eigenvalue represents the energy content of the vector; thus, there are:
2
in the formula (I), the compound is shown in the specification,
i.e. all the modalities in the sample database,
to be reordered
， 
Is composed of
A corresponding feature vector; since any vector in the database can be projected onto the derived modality, then:
in the formula (I), the compound is shown in the specification,
solving the modal coefficient to obtain the modal coefficient corresponding to any group of parameters through the difference, and linearly combining the modal coefficient with the modal coefficient to obtain predicted flow field data; namely:
s5, reconstructing new flow field information according to a formula 5, and storing the new flow field information into a text file for subsequent adjustment and analysis; the optimization formula is defined as:
in the formula (I), the compound is shown in the specification,
in order to average out the errors,
in order to select the number of reconstruction points,
is as follows
The reconstructed value of the point(s) is,
is as follows
The target value of the point is found in the optimizing process
The air supply parameter with the smallest value;
s6, storing the optimal air supply parameters obtained in the S5 into an embedded computer;
s7, inputting the air supply parameter result from the embedded computer to the programmable logic controller in the form of an electric signal;
s8, collecting temperature signals in the user-defined non-uniform temperature field through a thermocouple temperature sensor;
s9, acquiring signals through a temperature sensor and inputting the signals to a programmable logic controller;
s10, the temperature value read by the PLC realizes data exchange by using a transmission control protocol through a modbus module in python, and a data signal is transmitted to the embedded computer;
s11, the embedded computer compares the actual temperature of the room with the actual temperature to obtain the difference value between the preset temperature value and the actual temperature value
: if it is
If the algorithm effect is good, the optimal air supply parameter and the optimal working condition value under the required temperature value are directly obtained;
if it is
And correcting the parameters:
in the formula (I), the compound is shown in the specification,
in order to obtain a new target temperature for the temperature,
the temperature of the sample is the original target temperature,
is the measured temperature;
inputting the corrected result as a signal to obtain an optimal air supply parameter and an optimal working condition value under a required temperature value;
s12, transmitting the corrected data back to the programmable logic controller by the same data exchange method as the step S10;
and S13, transmitting the result obtained by the algorithm through an electric signal by using a programmable logic controller to control each branch pipe air valve and the water quantity regulating valve, and controlling the actual air supply temperature and air supply speed of a room to finish closed-loop control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111303110.1A CN113932351B (en) | 2021-11-05 | 2021-11-05 | Non-uniform temperature field real-time regulation and control system and method based on artificial intelligence algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111303110.1A CN113932351B (en) | 2021-11-05 | 2021-11-05 | Non-uniform temperature field real-time regulation and control system and method based on artificial intelligence algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113932351A CN113932351A (en) | 2022-01-14 |
| CN113932351B true CN113932351B (en) | 2023-02-03 |
Family
ID=79285860
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111303110.1A Active CN113932351B (en) | 2021-11-05 | 2021-11-05 | Non-uniform temperature field real-time regulation and control system and method based on artificial intelligence algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113932351B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104633856A (en) * | 2015-01-27 | 2015-05-20 | 天津大学 | Method for controlling artificial environment by combining CFD numerical simulation and BP neural network |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2918536B2 (en) * | 1997-07-23 | 1999-07-12 | 三星電子株式会社 | Open / close operation control method for cold air outlet of refrigerator |
| CN102418966B (en) * | 2011-12-19 | 2013-07-31 | 东南大学 | Air treatment device and air treatment method |
| CN104456726B (en) * | 2014-11-10 | 2017-02-15 | 浙江中烟工业有限责任公司 | Two-channel return air air-conditioning case and temperature control method thereof |
| CN206771574U (en) * | 2017-04-19 | 2017-12-19 | 河南工业大学 | The variable air volume air handling system system of function is corrected with sensor fault |
| KR101828587B1 (en) * | 2017-06-26 | 2018-02-13 | (주)센도리 | Ventilator to remove dust |
| CN207179942U (en) * | 2017-08-23 | 2018-04-03 | 欧伏电气股份有限公司 | Air-conditioning system |
| CN109798646B (en) * | 2019-01-31 | 2021-03-30 | 上海真聂思楼宇科技有限公司 | Variable air volume air conditioner control system and method based on big data platform |
| CN109899936A (en) * | 2019-03-06 | 2019-06-18 | 武汉捷高技术有限公司 | A kind of Constant air volume system controlling room temperature and its control method |
| CN110553374B (en) * | 2019-09-09 | 2021-04-27 | 上海美控智慧建筑有限公司 | Air conditioner control method and device and computer readable storage medium |
| CN211233135U (en) * | 2019-10-23 | 2020-08-11 | 陈丽君 | Air treatment unit |
| CN211600981U (en) * | 2020-02-26 | 2020-09-29 | 深圳市卫光生物制品股份有限公司 | Independent air conditioner purification system |
| CN111400970A (en) * | 2020-03-17 | 2020-07-10 | 史广思 | Method for learning and optimizing industrial multiphase flow process parameters |
| CN112113314A (en) * | 2020-09-22 | 2020-12-22 | 菲尼克斯(上海)环境控制技术有限公司 | Real-time temperature data acquisition system and temperature adjusting method based on learning model |
| KR102291184B1 (en) * | 2021-02-19 | 2021-08-18 | 한경대학교 산학협력단 | High-efficient thermal recovery ventilation system with improved ultrafine dust removal efficiency and air distribution function |
| CN113154563A (en) * | 2021-04-19 | 2021-07-23 | 北京晶海科技有限公司 | Temperature and humidity adjusting pipeline system for air conditioner and control method and device thereof |
-
2021
- 2021-11-05 CN CN202111303110.1A patent/CN113932351B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104633856A (en) * | 2015-01-27 | 2015-05-20 | 天津大学 | Method for controlling artificial environment by combining CFD numerical simulation and BP neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113932351A (en) | 2022-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yao et al. | State of the art review on model predictive control (MPC) in Heating Ventilation and Air-conditioning (HVAC) field | |
| Wang et al. | A state of art review on methodologies for control strategies in low energy buildings in the period from 2006 to 2016 | |
| CN106920006B (en) | Subway station air conditioning system energy consumption prediction method based on ISOA-LSSVM | |
| Huang et al. | Using genetic algorithms to optimize controller parameters for HVAC systems | |
| Mařík et al. | Advanced HVAC control: Theory vs. reality | |
| Huang et al. | A robust model predictive control strategy for improving the control performance of air-conditioning systems | |
| Pfeiffer et al. | Control of temperature and energy consumption in buildings-a review. | |
| Liao et al. | A simplified physical model for estimating the average air temperature in multi-zone heating systems | |
| Yiu et al. | Multiple ARMAX modeling scheme for forecasting air conditioning system performance | |
| Zhuang et al. | A new simplified modeling method for model predictive control in a medium-sized commercial building: A case study | |
| Ambroziak et al. | The PID controller optimisation module using Fuzzy Self-Tuning PSO for Air Handling Unit in continuous operation | |
| CN109798646B (en) | Variable air volume air conditioner control system and method based on big data platform | |
| CN112413831A (en) | Energy-saving control system and method for central air conditioner | |
| Boaventura Cunha et al. | A greenhouse climate multivariable predictive controller | |
| CN113932351B (en) | Non-uniform temperature field real-time regulation and control system and method based on artificial intelligence algorithm | |
| Rehrl et al. | A modeling approach for HVAC systems based on the LoLiMoT algorithm | |
| Zhang et al. | Room temperature and humidity decoupling control of common variable air volume air-conditioning system based on bilinear characteristics | |
| Javed et al. | Modelling and optimization of residential heating system using random neural networks | |
| CN113959071B (en) | Centralized water chilling unit air conditioning system operation control optimization method based on machine learning assistance | |
| Kümpel et al. | Self-adjusting model predictive control for modular subsystems in HVAC systems | |
| Arpaia et al. | Model predictive control strategy based on differential discrete particle swarm optimization | |
| CN113625557A (en) | HVAC system model prediction control method of online optimization model | |
| Abdo-Allah | Dynamic modeling and fuzzy logic control of a large building HVAC system | |
| Khouili et al. | GPC and PI Controllers Applied to an Aerothermic Process | |
| Pilavov et al. | Improvement of Control Processes for VAV Ventilation Systems Using MPC Controller |
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 |