CN117950438B - Dynamic temperature and humidity balance control method for return air unit for laboratory - Google Patents
Dynamic temperature and humidity balance control method for return air unit for laboratory Download PDFInfo
- Publication number
- CN117950438B CN117950438B CN202410354503.2A CN202410354503A CN117950438B CN 117950438 B CN117950438 B CN 117950438B CN 202410354503 A CN202410354503 A CN 202410354503A CN 117950438 B CN117950438 B CN 117950438B
- Authority
- CN
- China
- Prior art keywords
- humidity
- temperature
- laboratory
- data
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012544 monitoring process Methods 0.000 claims abstract description 57
- 230000008859 change Effects 0.000 claims abstract description 33
- 230000001364 causal effect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 230000007704 transition Effects 0.000 claims description 6
- 238000010438 heat treatment Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims 3
- 238000002474 experimental method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007791 dehumidification Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000013401 experimental design Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention relates to the technical field of balance adjustment, in particular to a dynamic balance control method for temperature and humidity of a return air unit for a laboratory, which comprises the following steps: acquiring direct monitoring data and indirect monitoring data, wherein the direct data comprise temperature and humidity data of the interior, the exterior and the air outlet of a monitoring laboratory and the air return unit, and the indirect data comprise the switching frequency of a monitoring laboratory door and the use condition of laboratory equipment; according to the direct monitoring data, directly adjusting the operation parameters of the air return unit, and according to the indirect monitoring data, predicting the change trend of the temperature and humidity in the laboratory through a prediction model and adjusting; and dynamically adjusting the operation parameters of the air return unit through the control system according to the prediction result. According to the invention, the current environment state can be considered, and the influence of indirect factors such as the switching frequency of the door, the service condition of equipment and the like on the temperature and the humidity can be analyzed, so that more accurate temperature and humidity control is realized.
Description
Technical Field
The invention relates to the technical field of balance adjustment, in particular to a dynamic balance control method for temperature and humidity of a return air unit for a laboratory.
Background
In modern laboratory environment, maintaining stable temperature and humidity is one of key factors for ensuring accuracy and repeatability of experiments, in experiments with high accuracy requirement, maintaining stable temperature and humidity is very important, a laboratory return air unit plays a crucial role in the process, and the main function of the laboratory return air unit is to circulate indoor air, and regulate the temperature and humidity of the air through processes such as filtration, heating, refrigeration, humidification or dehumidification so as to meet strict requirements of laboratories on environmental conditions. However, due to the diversity and complexity of experimental activities, and the constant change in external environmental conditions, temperature and humidity control in a laboratory is very challenging.
Conventional temperature and humidity control methods generally rely on preset fixed parameters or simple feedback mechanisms, and lack the capability of adapting to dynamic changes in the laboratory, for example, the operation of experimental equipment, the ingress and egress of personnel, and even changes in external climate conditions may have a significant impact on the temperature and humidity in the laboratory. These factors tend to vary rapidly and unpredictably, making it difficult for conventional control systems to make timely and accurate adjustments, thereby affecting the stability of the laboratory environment and the reliability of the experimental results.
The existing temperature and humidity control system often ignores potential influences of indirect factors such as laboratory internal activities and equipment use on temperature and humidity, so that efficiency and effectiveness of the control system are limited, and therefore an urgent need exists for developing a temperature and humidity control method capable of responding to laboratory internal and external changes in real time and dynamically adjusting a control strategy so as to achieve more accurate and stable environmental control.
Disclosure of Invention
Based on the above purpose, the invention provides a dynamic balance control method for the temperature and humidity of a return air unit for a laboratory, which aims to realize the dynamic balance control for the temperature and humidity of the return air unit for the laboratory by introducing an advanced dynamic Bayesian network model and combining direct and indirect monitoring data inside and outside the laboratory, thereby overcoming the defects of the prior art and improving the accuracy, response speed and self-adaptive capacity of the humidity control of the laboratory.
A dynamic balance control method for temperature and humidity of a return air unit for a laboratory comprises the following steps:
s1: acquiring direct monitoring data and indirect monitoring data, wherein the direct data comprise temperature and humidity data of the interior, the exterior and the air outlet of a monitoring laboratory and the air return unit, and the indirect data comprise the switching frequency of a monitoring laboratory door and the use condition of laboratory equipment;
S2: according to the direct monitoring data, directly adjusting the operation parameters of the air return unit, and according to the indirect monitoring data, predicting the change trend of the temperature and humidity in the laboratory through a prediction model and adjusting;
s3: and dynamically adjusting the operation parameters of the air return unit through the control system according to the prediction result.
Further, the operation parameters of the air return unit comprise air quantity, air speed and heating/refrigerating capacity.
Further, the obtaining of the direct monitoring data comprises respectively installing temperature and humidity sensors at the air outlets of the laboratory interior, the outdoor and the air return unit, and the temperature and humidity sensors are used for monitoring respective temperature and relative humidity data in real time;
All temperature and humidity sensors are connected to a central data processing unit, data from all the sensors are collected and stored, time stamping is carried out on the collected data, the data are transmitted to a control system in real time, the control system compares the received data with a preset threshold range, whether the operation parameters of a return air unit need to be adjusted or not is evaluated, the preset threshold range is +/-5 units of ideal (actually needed baseline temperature and humidity) temperature and humidity, and the adjustment priority according to the direct monitoring data is higher than that according to the indirect monitoring data.
Further, the obtaining of the indirect monitoring data includes:
Switching frequency of laboratory doors: the method comprises the steps of installing a magnetic sensor or an infrared sensor on a door of a laboratory to monitor the opening and closing state of the door, recording the time points of opening and closing the door each time in real time, calculating the opening and closing frequency of the door, and analyzing the frequency of personnel entering and exiting through an image recognition and motion detection technology by utilizing a video monitoring camera installed at the entrance of the laboratory to indirectly reflect the opening and closing frequency of the door.
Laboratory equipment usage status: by connecting laboratory equipment to an intelligent power socket, the power state (on/off) of each equipment is monitored in real time, the real-time energy consumption of the equipment is monitored, the service condition and the working period of the equipment are deduced, an IoT sensor is installed for the laboratory equipment, and the operation parameters (such as temperature, vibration and the like) of the equipment are measured and recorded, so that the service state of the equipment is indirectly judged.
Further, the step of predicting the trend of the temperature and humidity in the laboratory by using the dynamic bayesian network model in the prediction model in the step S2 specifically includes:
S21: defining a dynamic Bayesian network model structure, wherein the structure comprises a group of nodes and directed edges, each node represents a variable, the switching frequency of a laboratory door and the use state of equipment are included, the directed edges represent causal relations among the variables, and the relation among the variables at different time points is defined;
S22: estimating parameters of each conditional probability distribution in the network by using a Bayesian estimation method through the collected indirect monitoring data;
s23: serializing the collected indirect monitoring data so that the model can process the time series data;
S24: the trained dynamic Bayesian network model is utilized for reasoning, probability distribution of temperature and humidity in a laboratory in a future time point (or a time period) is calculated according to current and past indirect monitoring data, and the change trend of the temperature and humidity is predicted by selecting the state with the highest probability or calculating an expected value, so that the temperature and humidity change quantity and the quantity to be regulated are estimated;
S25: along with the continuous collection of new data, the parameters of the dynamic Bayesian network are updated periodically by an incremental learning method so as to adapt to the change of the environment and the new observed data, and the updating of the parameters is expressed as follows: Wherein, And/>Respectively represent the parameters before and after updating,/>Is learning rate,/>Is a loss function,/>Is newly collected data,/>Representing the gradient of the loss function with respect to the parameter.
Further, the dynamic bayesian network model structure in S21 is composed of a plurality of time slices, each time slice includes a set of nodes, the nodes are connected by directed edges, the nodes represent causal relationships among variables, and for two consecutive time slicesAnd/>The relationship between variables is represented by transition probabilities: /(I)Wherein/>And/>Respectively represent the time points/>Variable set of/>Representing a time point/>Variable set representing a given point in time/>Time Point/>Conditional probability of state.
Further, the bayesian estimation method in S22 includes: for each node, a conditional probability table is estimated according to the state of its parent node, based on Bayesian estimation, parametersThe posterior distribution of (2) is expressed as: Wherein/> Is observation data,/>Is at the parameter/>A likelihood function of the lower data is provided,Is a priori distribution of parameters, updating the conditional probability table for each variable.
Further, the serialization processing in S23 includes: dividing the data into time slices matching the dynamic Bayesian network model structure, for each point in timeThe data sequence is expressed as:
Wherein/> Representing a time point/>Including the state of all relevant variables.
Further, the probability distribution in S24 is a posterior probability calculation:
Wherein/> Representing up to time/>All observations of,/>Is the transition probability,/>Is the time point/>, given the observation dataPosterior probability of state.
Further, the estimated temperature and humidity variation and the required adjustment amount in S24 specifically include:
S241, calculating an expected value: when a dynamic Bayesian network model provides a probability distribution of laboratory temperature and humidity at a certain point in time or time period in the future, the expected variation of the temperature and humidity is estimated by calculating the expected value (mean value) of the distribution, for the temperature And humidity/>The calculation formula is as follows:
expected value of temperature: ；
expected value of humidity: ；
Wherein, And/>Discrete values (possible values) of temperature and humidity, respectively, and/>∈/>Each of which isInteger number, representing a discrete value of temperature,/>∈/>Each/>Integer number, representing a discrete value of humidity,/>And/>Probability corresponding to the discrete value;
S242, estimating the amount of change: by comparing the predicted expected value with the baseline temperature and humidity value, the variation of the temperature and humidity is estimated, and the device is set And/>Indicating the baseline temperature and humidity values, respectively, the amount of change is expressed as:
Temperature change amount: ；
Humidity change amount: ；
s243, calculating an adjustment amount: according to the estimated temperature and humidity variation, calculating the adjustment quantity required for maintaining the preset temperature and humidity state, and considering the efficiency and response characteristic of the air return unit And/>Respectively, the adjustment efficiency of temperature and humidity control (namely, the influence of unit adjustment quantity on temperature and humidity), the specific adjustment quantity is expressed as:
Temperature adjustment amount: ；
Humidity adjustment amount: ；
Wherein, And/>Temperature and humidity levels that need to be pre-adjusted to counteract the predicted changes;
and adjusting the operation parameters of the air return unit according to the calculated adjustment quantity so as to realize the expected temperature and humidity control.
The invention has the beneficial effects that:
According to the invention, the temperature and humidity change trend in a laboratory can be accurately predicted by combining direct and indirect monitoring data. By utilizing the dynamic Bayesian network model, the current environment state can be considered, and the influence of indirect factors such as the switching frequency of the door, the use condition of equipment and the like on the temperature and the humidity can be analyzed, so that more accurate temperature and humidity control is realized.
The invention can dynamically adjust the operation parameters of the air return unit, such as air quantity, air speed, heating/refrigerating capacity and humidifying/dehumidifying strength, according to the prediction result so as to adapt to the instant change of the internal temperature and humidity of the laboratory.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a method according to an embodiment of the present invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As shown in FIG. 1, the dynamic balance control method for the temperature and humidity of the return air unit for the laboratory comprises the following steps:
s1: acquiring direct monitoring data and indirect monitoring data, wherein the direct data comprise temperature and humidity data of the interior, the exterior and the air outlet of a monitoring laboratory and the air return unit, and the indirect data comprise the switching frequency of a monitoring laboratory door and the use condition of laboratory equipment;
S2: according to the direct monitoring data, directly adjusting the operation parameters of the air return unit, and according to the indirect monitoring data, predicting the change trend of the temperature and humidity in the laboratory through a prediction model and adjusting;
s3: and dynamically adjusting the operation parameters of the air return unit through the control system according to the prediction result.
The operation parameters of the return air unit comprise air quantity, air speed and heating/refrigerating capacity.
The acquisition of the direct monitoring data comprises respectively installing temperature and humidity sensors at the inside, the outside and the air outlet of the air return unit of the laboratory, and is used for monitoring the respective temperature and relative humidity data in real time;
All temperature and humidity sensors are connected to a central data processing unit, data from all the sensors are collected and stored, time stamping is carried out on the collected data, the data are transmitted to a control system in real time, the control system compares the received data with a preset threshold range, whether the operation parameters of a return air unit need to be adjusted or not is evaluated, the preset threshold range is +/-5 units of ideal (actually needed baseline temperature and humidity) temperature and humidity, and the adjustment priority according to the direct monitoring data is higher than that according to the indirect monitoring data.
The acquisition of the indirect monitoring data comprises the following steps:
Switching frequency of laboratory doors: a magnetic sensor or an infrared sensor is arranged on a door of a laboratory to monitor the opening and closing state of the door, the time point of opening and closing the door each time is recorded in real time, the opening and closing frequency of the door is calculated, and the frequency of entering and exiting of personnel is analyzed by utilizing a video monitoring camera arranged at the entrance of the laboratory through an image recognition and motion detection technology to indirectly reflect the opening and closing frequency of the door;
If a laboratory door is equipped with an access control system, a door opening and closing record can be obtained directly from the system, and such data is generally more accurate and easy to obtain.
Laboratory equipment usage status: by connecting laboratory equipment to an intelligent power socket, the power state (on/off) of each equipment is monitored in real time, the real-time energy consumption of the equipment is monitored, the service condition and the working period of the equipment are deduced, an IoT sensor is installed for the laboratory equipment, and the operation parameters (such as temperature, vibration and the like) of the equipment are measured and recorded, so that the service state of the equipment is indirectly judged.
The prediction model in S2 adopts a dynamic Bayesian network model, which is a probability graph model for processing time sequence data and can simulate the dynamic change relation of variables along with time. DBNs are particularly useful for capturing time dependencies and causal relationships, which make them well suited for predicting the trend of changes in the internal temperature and humidity of a laboratory, particularly when such changes are affected by a number of indirect factors, the step of applying a dynamic bayesian network model to predict the trend of changes in the internal temperature and humidity of a laboratory specifically comprises:
S21: defining a dynamic Bayesian network model structure, wherein the structure comprises a group of nodes and directed edges, each node represents a variable, the switching frequency of a laboratory door and the use state of equipment are included, the directed edges represent causal relations among the variables, and the relation among the variables at different time points is defined;
S22: estimating parameters of each conditional probability distribution in the network by using a Bayesian estimation method through the collected indirect monitoring data;
s23: serializing the collected indirect monitoring data so that the model can process the time series data;
S24: the trained dynamic Bayesian network model is utilized for reasoning, probability distribution of temperature and humidity in a laboratory in a future time point (or a time period) is calculated according to current and past indirect monitoring data, and the change trend of the temperature and humidity is predicted by selecting the state with the highest probability or calculating an expected value, so that the temperature and humidity change quantity and the quantity to be regulated are estimated;
S25: along with the continuous collection of new data, the parameters of the dynamic Bayesian network are updated periodically by an incremental learning method so as to adapt to the change of the environment and the new observed data, and the updating of the parameters is expressed as follows: Wherein, And/>Respectively represent the parameters before and after updating,/>Is learning rate,/>Is a loss function,/>Is the data that is to be collected newly,Representing the gradient of the loss function with respect to the parameter.
The dynamic Bayesian network model structure in S21 consists of a plurality of time slices, each time slice comprising a set of nodes connected by directed edges, representing causal relationships between variables, for two consecutive time slicesAnd/>The relationship between variables is represented by transition probabilities: /(I)Wherein/>And/>Respectively represent the time points/>Variable set of/>Representing a time point/>Variable set representing a given point in time/>Time Point/>Conditional probability of state.
The bayesian estimation method in S22 includes: for each node, a conditional probability table is estimated according to the state of its parent node, based on Bayesian estimation, parametersThe posterior distribution of (2) is expressed as: /(I)Wherein/>Is observation data,/>Is at the parameter/>Likelihood function of lower data,/>Is a priori distribution of parameters, updating the conditional probability table for each variable.
The serialization processing in S23 includes: dividing the data into time slices matching the dynamic Bayesian network model structure, for each point in timeThe data sequence is expressed as:
Wherein/> Representing a time point/>Including the state of all relevant variables.
The probability distribution in S24 is calculated as posterior probability:
Wherein/> Representing up to time/>All observations of,/>Is the transition probability,/>Is the time point/>, given the observation dataPosterior probability of state.
The estimated temperature and humidity variation and the required adjustment amount in S24 specifically include:
S241, calculating an expected value: when a dynamic Bayesian network model provides a probability distribution of laboratory temperature and humidity at a certain point in time or time period in the future, the expected variation of the temperature and humidity is estimated by calculating the expected value (mean value) of the distribution, for the temperature And humidity/>The calculation formula is as follows:
expected value of temperature: ；
expected value of humidity: ；
Wherein, And/>Discrete values (possible values) of temperature and humidity, respectively, and/>∈/>Each of which isInteger number, representing a discrete value of temperature,/>∈/>Each/>Integer number, representing a discrete value of humidity,/>And/>Probability corresponding to the discrete value;
S242, estimating the amount of change: by comparing the predicted expected value with the baseline temperature and humidity value, the variation of the temperature and humidity is estimated, and the device is set And/>Indicating the baseline temperature and humidity values, respectively, the amount of change is expressed as:
Temperature change amount: ；
Humidity change amount: ；
s243, calculating an adjustment amount: according to the estimated temperature and humidity variation, calculating the adjustment quantity required for maintaining the preset temperature and humidity state, and considering the efficiency and response characteristic of the air return unit And/>Respectively, the adjustment efficiency of temperature and humidity control (namely, the influence of unit adjustment quantity on temperature and humidity), the specific adjustment quantity is expressed as:
Temperature adjustment amount: ；
Humidity adjustment amount: ；
Wherein, And/>Temperature and humidity levels that need to be pre-adjusted to counteract the predicted changes;
and adjusting the operation parameters of the air return unit according to the calculated adjustment quantity so as to realize the expected temperature and humidity control.
In order to verify the effect of a Dynamic Bayesian Network (DBN) in predicting the internal temperature and humidity change trend of a laboratory and estimating the temperature and humidity change amount and the adjustment amount, the following experimental design is performed:
In a normal laboratory, where the ideal temperature and humidity control objective is to maintain a temperature of 22 ℃ and humidity of 55% rh, there are multiple temperature and humidity sensors, door status sensors, and equipment usage monitors.
During the week, the following indirect monitoring data were collected:
The switching frequency of the gate averages 5 times per hour.
The peak period of use of the important experimental equipment is from 2 pm to 4 pm, and the use ratio is about 80%.
The direct monitoring data shows that: the current laboratory temperature is 24 ℃ and humidity is 60% rh.
A DBN model is constructed, which includes the following nodes:
A temperature node (T), a humidity node (H), a switching frequency node (D) of the gate, and a device usage status node (E); these nodes are connected by directed edges, representing the following causal relationships: the switching frequency of the door and the use state of the device can affect the temperature and humidity changes; the DBN model is trained using the collected indirect and direct monitoring data to determine the conditional probability distribution between nodes.
The prediction experiment is as follows:
At day 2 pm of the second week, predictions were made using the DBN model, which predicts that the temperature will rise to 25 ℃ and humidity will rise to 65% rh within the next two hours, considering the device is about to enter peak use.
Estimating the variation and adjustment: according to the prediction, the change amount of the temperature isThe variation of humidity is/>The temperature regulation efficiency of the return air unit in the laboratory is/>The humidity adjustment efficiency per unit adjustment amount was 2.5 per unit adjustment amount, and therefore, the required temperature adjustment amount was/>Unit, humidity adjustment amount is/>Units of (3).
According to the calculated regulating variable, the setting of the air return unit is adjusted, and the cooling capacity of 4 units and the dehumidifying capacity of 2 units are increased.
And (3) verifying results: during the two hours after conditioning, the laboratory temperature and humidity were found to stabilize at 22.4 ℃ and 55.6% rh, respectively, by real-time monitoring. Substantially approaching an ideal temperature and humidity. Through the experiment, the feasibility and the practicability of the DBN in predicting the temperature and humidity change trend and the corresponding adjustment quantity of the DBN in the laboratory are shown. The method and the device can effectively predict and control the temperature and the humidity of a laboratory so as to ensure the stability of an experimental environment, thereby improving the accuracy and the reliability of experimental results.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the invention is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the invention, the steps may be implemented in any order and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
The present invention is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (4)
1. The dynamic temperature and humidity balance control method for the return air unit for the laboratory is characterized by comprising the following steps of:
s1: acquiring direct monitoring data and indirect monitoring data, wherein the direct data comprise temperature and humidity data of the interior, the exterior and the air outlet of a monitoring laboratory and the air return unit, and the indirect data comprise the switching frequency of a monitoring laboratory door and the use condition of laboratory equipment;
S2: according to the direct monitoring data, directly adjusting the operation parameters of the air return unit, and according to the indirect monitoring data, predicting the change trend of the temperature and humidity in the laboratory through a prediction model and adjusting;
S3: according to the prediction result, dynamically adjusting the operation parameters of the air return unit through a control system;
The step of predicting the change trend of the temperature and the humidity in the laboratory by using the dynamic Bayesian network model specifically comprises the following steps of:
S21: defining a dynamic Bayesian network model structure, wherein the structure comprises a group of nodes and directed edges, each node represents a variable, the switching frequency of a laboratory door and the use state of equipment are included, the directed edges represent causal relations among the variables, and the relation among the variables at different time points is defined;
S22: estimating parameters of each conditional probability distribution in the network by using a Bayesian estimation method through the collected indirect monitoring data;
s23: serializing the collected indirect monitoring data so that the model can process the time series data;
s24: the trained dynamic Bayesian network model is utilized for reasoning, probability distribution of the temperature and humidity in a laboratory at a future time point is calculated according to current and past indirect monitoring data, and the change trend of the temperature and humidity is predicted by selecting the state with the highest probability or calculating an expected value, so that the temperature and humidity change quantity and the quantity to be regulated are estimated;
s25: along with the continuous collection of new data, periodically updating the parameters of the dynamic Bayesian network by an incremental learning method so as to adapt to the change of the environment and the new observation data;
The dynamic bayesian network model structure in S21 is composed of a plurality of time slices, each time slice includes a group of nodes, the nodes are connected through directed edges, the causal relationship between variables is represented, and for two consecutive time slices t and t+1, the relationship between variables is represented by transition probabilities: p (X t+1|Xt,Yt), wherein X t and Y t represent the variable set at time point t, respectively, X t+1 represents the variable set at time point t+1, and represents the conditional probability of the state at time point t+1 given the state at time point t;
The bayesian estimation method in S22 includes: for each node, a conditional probability table is estimated from the state of its parent node, and based on bayesian estimation, the posterior distribution of the parameter θ is expressed as: p (θ|D) ≡P (D|θ) P (θ), where D is observation data, P (D|θ) is likelihood function of data under parameter θ, P (θ) is a priori distribution of parameters, and a conditional probability table of each variable is updated;
the serialization processing in S23 includes: dividing the data into time slices matched with the dynamic Bayesian network model structure, and for each time point t, expressing the data sequence as follows:
D t＝{Xt,Yt }, wherein D t represents a dataset of time points t, including the states of all relevant variables;
The probability distribution in S24 is calculated as a posterior probability:
Where D 1：t denotes all observations up to time t, P (X t+1|Xt) is the transition probability, and P (X t|D1：t) is the posterior probability of the state at time point t given the observations;
the estimated temperature and humidity variation and the required adjustment amount in S24 specifically include:
S241, calculating an expected value: when the dynamic bayesian network model provides a probability distribution of laboratory temperature and humidity at a certain time point or time period in the future, the expected variation of the temperature and humidity is estimated by calculating expected values of the distribution, and for the expected values of the temperature T and the humidity H, the calculation formula is as follows:
Expected value of temperature: e [ T ] = Σ iTiP(Ti);
Expected value of humidity: e [ H ] = Σ jHjP(Hj);
Wherein, T i and H j are discrete values of temperature and humidity respectively, and T i∈{T1,T2,...,Tn }, each T i is an integer, representing one discrete value of temperature, H j∈{H1,H2,...,Hm }, each H j is an integer, representing one discrete value of humidity, and P (T i) and P (H j) are probabilities corresponding to the discrete values;
S242, estimating the amount of change: by comparing the predicted expected value with the baseline temperature and humidity value, the variation of the temperature and humidity is estimated, and if the values of the baseline temperature and the humidity are respectively represented by T current and H current, the variation is represented as follows:
temperature change amount: Δt=et-T current;
humidity change amount: Δh=e [ H ] -H current;
S243, calculating an adjustment amount: according to the estimated temperature and humidity variation, calculating an adjustment amount required for maintaining a preset temperature and humidity state, considering the efficiency and response characteristics of the air return unit, and setting alpha T and alpha H to respectively represent the adjustment efficiency of temperature and humidity control, wherein the specific adjustment amount is expressed as:
temperature adjustment amount:
Humidity adjustment amount:
wherein ΔT adjust and ΔH adjust are the temperature and humidity levels that need to be pre-adjusted to counteract the predicted changes;
and adjusting the operation parameters of the air return unit according to the calculated adjustment quantity so as to realize the expected temperature and humidity control.
2. The method for dynamically balancing and controlling the temperature and humidity of a return air unit for a laboratory according to claim 1, wherein the operation parameters of the return air unit comprise air quantity, air speed and heating/refrigerating capacity.
3. The method for dynamically balancing and controlling the temperature and humidity of a return air unit for a laboratory according to claim 1, wherein the acquisition of the direct monitoring data comprises respectively installing temperature and humidity sensors at the inside, the outside and the air outlet of the return air unit for real-time monitoring of the respective temperature and relative humidity data;
All temperature and humidity sensors are connected to a central data processing unit, data from all the sensors are collected and stored, time stamping is carried out on the collected data, the data are transmitted to a control system in real time, the control system compares the received data with a preset threshold range, so that whether the operation parameters of a return air unit need to be adjusted or not is evaluated, the preset threshold range is +/-5 units of ideal temperature and humidity, and the adjustment priority according to the direct monitoring data is higher than that according to the indirect monitoring data.
4. A method for controlling dynamic balance of temperature and humidity of a return air unit for a laboratory according to claim 1, wherein the obtaining of the indirect monitoring data comprises:
Switching frequency of laboratory doors: a magnetic sensor or an infrared sensor is arranged on a door of a laboratory to monitor the opening and closing state of the door, the time point of opening and closing the door each time is recorded in real time, the opening and closing frequency of the door is calculated, and the frequency of entering and exiting of personnel is analyzed by utilizing a video monitoring camera arranged at the entrance of the laboratory through an image recognition and motion detection technology to indirectly reflect the opening and closing frequency of the door;
Laboratory equipment usage status: by connecting laboratory equipment to an intelligent power socket, the power state of each equipment is monitored in real time, the real-time energy consumption of the equipment is monitored, an IoT sensor is installed for the laboratory equipment, and the operating parameters of the equipment are measured and recorded, so that the use state of the equipment is indirectly judged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410354503.2A CN117950438B (en) | 2024-03-27 | 2024-03-27 | Dynamic temperature and humidity balance control method for return air unit for laboratory |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410354503.2A CN117950438B (en) | 2024-03-27 | 2024-03-27 | Dynamic temperature and humidity balance control method for return air unit for laboratory |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117950438A CN117950438A (en) | 2024-04-30 |
| CN117950438B true CN117950438B (en) | 2024-06-07 |
Family
ID=90796337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410354503.2A Active CN117950438B (en) | 2024-03-27 | 2024-03-27 | Dynamic temperature and humidity balance control method for return air unit for laboratory |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117950438B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS56140403A (en) * | 1980-04-03 | 1981-11-02 | Fuji Electric Co Ltd | Control method for operation of plant |
| CN101881484A (en) * | 2009-05-05 | 2010-11-10 | 海尔集团公司 | Voice controlled air conditioner |
| CN102929317A (en) * | 2012-11-15 | 2013-02-13 | 江苏高远电力科技有限公司 | Monitoring and controlling system for sealed space environment |
| CN103229116A (en) * | 2010-12-31 | 2013-07-31 | 耐斯特实验公司 | Flexible functionality partitioning within intelligent-thermostat-controlled hvac systems |
| CN103383218A (en) * | 2012-12-31 | 2013-11-06 | 于净 | Bullet cabinet and temperature and humidity monitoring method thereof |
| CN116774756A (en) * | 2023-05-05 | 2023-09-19 | 赣州地震监测中心站 | Remote control system for temperature and humidity environment in geomagnetic room |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120078678A1 (en) * | 2010-09-23 | 2012-03-29 | Infosys Technologies Limited | Method and system for estimation and analysis of operational parameters in workflow processes |
| GB201313444D0 (en) * | 2013-07-29 | 2013-09-11 | Ambi Labs Ltd | Energy efficient indoor climate controller |
-
2024
- 2024-03-27 CN CN202410354503.2A patent/CN117950438B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS56140403A (en) * | 1980-04-03 | 1981-11-02 | Fuji Electric Co Ltd | Control method for operation of plant |
| CN101881484A (en) * | 2009-05-05 | 2010-11-10 | 海尔集团公司 | Voice controlled air conditioner |
| CN103229116A (en) * | 2010-12-31 | 2013-07-31 | 耐斯特实验公司 | Flexible functionality partitioning within intelligent-thermostat-controlled hvac systems |
| CN102929317A (en) * | 2012-11-15 | 2013-02-13 | 江苏高远电力科技有限公司 | Monitoring and controlling system for sealed space environment |
| CN103383218A (en) * | 2012-12-31 | 2013-11-06 | 于净 | Bullet cabinet and temperature and humidity monitoring method thereof |
| CN116774756A (en) * | 2023-05-05 | 2023-09-19 | 赣州地震监测中心站 | Remote control system for temperature and humidity environment in geomagnetic room |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117950438A (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9400119B2 (en) | Retrofitting a constant volume air handling unit with a variable frequency drive | |
| US10317864B2 (en) | Systems and methods for adaptively updating equipment models | |
| CN108476473B (en) | System and method for extending battery life of wireless sensors in a building control system | |
| US11605036B2 (en) | System and methods for power system forecasting using deep neural networks | |
| US20180087790A1 (en) | Systems and methods for automatically creating and using adaptive pca models to control building equipment | |
| CN116991215A (en) | Causal learning-based data center foundation structure optimization method | |
| Ouf et al. | A simulation-based method to investigate occupant-centric controls | |
| JP2020154785A (en) | Prediction method, prediction program, and model learning method | |
| Vu et al. | Data driven chiller plant energy optimization with domain knowledge | |
| CN114970358A (en) | Data center energy efficiency optimization method and system based on reinforcement learning | |
| EP4057466A1 (en) | Hierarchical method for prediction of loads with high variance | |
| CN117515854A (en) | Intelligent optimization method and device for central air conditioner | |
| CN117950438B (en) | Dynamic temperature and humidity balance control method for return air unit for laboratory | |
| CN115289637A (en) | Temperature adjustment method, system, device, storage medium, and program product | |
| CN116817424A (en) | Air conditioner energy-saving control system and method based on artificial intelligence | |
| KR102240390B1 (en) | Smart Integrated Control System for Integrated Control of Complex Valve and Fan Coil Unit and Its Operation | |
| US11662696B2 (en) | Automatic control artificial intelligence device and method for update control function | |
| CN116792882A (en) | Remote intelligent control management system for air conditioner | |
| CN116578134A (en) | Universal base station temperature control method and system based on reinforcement learning | |
| CN116147128A (en) | Energy-saving control method and system for heating ventilation air conditioner | |
| KR102458372B1 (en) | User occupancy time prediction system and method in urban buildings based on Big data for energy saving cooling and heating automatic control | |
| US12086001B2 (en) | System and method for proactively controlling an environmental condition in a server rack of a data center based at least in part on server load | |
| KR102651256B1 (en) | Smart refrigeration and air conditioning system having and indoor air sterilization and IoT control and monitoring system | |
| CN117270412B (en) | Intelligent home control system based on wireless communication technology | |
| CN118517769B (en) | Operation management method and system of high-efficiency energy-saving air conditioner room |
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 |