CN112254287A - Variable-weight multi-model comprehensive prediction central air conditioner tail end air supply control method - Google Patents
Variable-weight multi-model comprehensive prediction central air conditioner tail end air supply control method Download PDFInfo
- Publication number
- CN112254287A CN112254287A CN202010903115.7A CN202010903115A CN112254287A CN 112254287 A CN112254287 A CN 112254287A CN 202010903115 A CN202010903115 A CN 202010903115A CN 112254287 A CN112254287 A CN 112254287A
- Authority
- CN
- China
- Prior art keywords
- temperature
- model
- predicted value
- obtaining
- comprehensive
- 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.)
- Granted
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/70—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
- F24F2110/00—Control inputs relating to air properties
- F24F2110/10—Temperature
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2110/00—Control inputs relating to air properties
- F24F2110/20—Humidity
-
- 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
- F24F2110/30—Velocity
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F2120/00—Control inputs relating to users or occupants
- F24F2120/20—Feedback from users
Abstract
The invention relates to a variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method, which comprises the following steps: acquiring monitoring parameters; predicting by adopting a preset model according to the monitoring parameters to obtain a multi-model prediction result; performing variable weight processing based on the multi-model prediction result to obtain a comprehensive prediction value; and adjusting the air supply quantity at the tail end of the central air conditioner according to the comprehensive predicted value. According to the invention, the air supply control of the tail end of the central air conditioner based on variable weight multi-model comprehensive prediction is adopted, and the comprehensive prediction value is used as the indoor thermal comfort evaluation index, so that when the indoor thermal environment changes, a model with higher precision in a single thermal comfort prediction model can be dynamically endowed with a higher weight value in different thermal environment variable value areas, thus the prediction precision of the variable weight comprehensive prediction model is improved, the air supply state of the tail end of the central air conditioner is reasonably adjusted, and the comfort of the indoor thermal environment is improved.
Description
Technical Field
The invention relates to the field of central air conditioner control, in particular to a variable-weight multi-model comprehensive prediction central air conditioner tail end air supply control method.
Background
The air supply adjustment at the tail end of the central air-conditioning system can dynamically adjust air supply parameters according to indoor environment changes, and the indoor environment is guaranteed to be maintained within a reasonable range. The conventional air conditioner terminal control adjusts the working frequency of a fan according to the difference between the indoor temperature and the set temperature, and then changes the air supply parameters. The method has the advantages of simple control, but because the temperature sensed by the indoor tail end of the air conditioner is generally the return air temperature rather than the temperature of the air conditioning area where a user is located, namely, the indoor air conditioning equipment is not regulated and controlled according to the temperature of the air conditioning area served by the indoor air conditioning equipment, temperature deviation exists, and the operation regulation and control of the air conditioner are disjointed from the actual thermal sensation of the user. Therefore, the existing method introduces the thermal comfort of human body into the automatic control system of the air conditioner, so that the air conditioner system can automatically adjust the indoor temperature and humidity according to the change of the thermal state of human body. Such as PMV (expected mean evaluation index) model, Adaptive thermal comfort model, etc.
However, the problem of predicting the thermal comfort response of the human body is a complex process, which is influenced by various factors, and the control of the air conditioner terminal by adopting the single models has certain limitations. For example, the PMV model is generally only suitable for a thermal environment in which the indoor parameters are stable and uniformly distributed around the human body, and is not suitable for a non-steady-state thermal environment nor a thermal environment in which the parameters around the human body are not uniform. The Adaptive thermal comfort model only considers the relation between comfortable temperature and outdoor temperature, does not consider the physical heat exchange process between people and the environment, and cannot reflect the action and effect of other factors.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a variable weight multiple model comprehensive prediction central air conditioner terminal air supply control method, aiming at the above defects in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: a variable weight multi-model comprehensive prediction central air-conditioning terminal air supply control method is constructed, and comprises the following steps:
acquiring monitoring parameters;
predicting by adopting a preset model according to the monitoring parameters to obtain a multi-model prediction result;
performing variable weight processing based on the multi-model prediction result to obtain a comprehensive prediction value;
and adjusting the air supply quantity at the tail end of the central air conditioner according to the comprehensive predicted value.
Preferably, the monitoring parameters include: indoor air temperature, indoor relative humidity, indoor air velocity, indoor black ball temperature, and human body temperature;
the preset model comprises: an effective temperature model;
the predicting according to the monitoring parameters and by adopting a preset model, and obtaining a multi-model prediction result comprises the following steps:
and obtaining an effective temperature predicted value according to the indoor air temperature, the indoor relative humidity and the effective temperature model.
Preferably, the preset model further comprises: an expected average evaluation index model;
the predicting according to the monitoring parameters and by adopting a preset model, and obtaining a multi-model prediction result comprises the following steps:
and obtaining an expected average evaluation index prediction value according to the indoor air temperature, the indoor relative humidity, the indoor black ball temperature, the indoor air speed, the clothes thermal resistance and the human body heat dissipation rate value.
Preferably, the obtaining an expected average evaluation index prediction value according to the indoor air temperature, the indoor relative humidity, the indoor black ball temperature, the indoor air speed, the clothes thermal resistance and the human body heat dissipation rate value comprises:
obtaining the air water vapor partial pressure according to the relation among the indoor air temperature, the indoor relative humidity and the air water vapor partial pressure;
obtaining the dressing area coefficient according to the relation between the thermal resistance of the clothes and the dressing area coefficient;
obtaining the surface temperature of the clothes according to the relational expression of the human body heat generation rate, the additional heat dissipation value of the human body activity, the thermal resistance of the clothes and the dressing area coefficient;
obtaining the average radiation temperature according to the relation among the indoor black ball temperature, the indoor air speed and the average radiation temperature;
obtaining the convective heat transfer coefficient according to the relational expression of the surface temperature of the clothes, the temperature of the indoor air, the speed of the indoor air and the convective heat transfer coefficient;
and obtaining the expected average evaluation index predicted value according to the human body heat production rate, the human body activity additional heat dissipation value, the air water vapor partial pressure, the dressing area coefficient, the clothes surface temperature, the indoor air temperature, the average radiation temperature and the convection heat transfer coefficient.
Preferably, the human body temperature includes: human head temperature, human hand temperature, human ankle temperature;
the preset model comprises: a human physiological parameter comprehensive evaluation model;
the predicting according to the monitoring parameters and by adopting a preset model, and obtaining a multi-model prediction result comprises the following steps:
and obtaining the comprehensive evaluation predicted value of the human physiological parameters according to the human head temperature, the human hand temperature, the human ankle temperature, the average radiation temperature and the indoor air temperature.
Preferably, the obtaining the human physiological parameter comprehensive evaluation predicted value according to the human head temperature, the human hand temperature, the human ankle temperature, the average radiation temperature, and the indoor air temperature includes:
obtaining the operating temperature according to a relational expression of the indoor air temperature, the average radiation temperature and the operating temperature;
obtaining the average body surface temperature of the human body according to the head temperature, the hand temperature and the ankle temperature of the human body;
obtaining the average body surface impedance according to the relational expression of the operation temperature and the average body surface impedance;
and obtaining the comprehensive evaluation predicted value of the human physiological parameters according to the operation temperature, the human body average body surface temperature and the average body surface impedance.
Preferably, the preset model comprises: a skin moisture model;
the predicting according to the monitoring parameters and by adopting a preset model, and obtaining a multi-model prediction result comprises the following steps:
obtaining the relative humidity of the skin according to the average body surface temperature, the indoor air temperature and the air vapor partial pressure;
and obtaining the predicted value of the skin humidity model according to the skin relative humidity.
Preferably, the method further comprises:
and carrying out normalization processing on the effective temperature predicted value and the skin humidity model predicted value to obtain a normalized effective temperature predicted value and a normalized skin humidity model predicted value.
Preferably, the performing variable weight processing based on the multi-model prediction result to obtain a comprehensive prediction value includes:
and weighting the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value and the normalized skin humidity model predicted value to obtain the comprehensive predicted value.
Preferably, the weighting processing is performed on the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value and the normalized skin humidity model predicted value, and obtaining the comprehensive predicted value includes:
determining a first weight of the predicted value of the normalized effective temperature, a second weight of the predicted value of the expected average evaluation index, a third weight of the predicted value of the comprehensive evaluation of the human physiological parameters and a fourth weight of the predicted value of the normalized skin humidity model;
and obtaining the comprehensive predicted value according to the first weight, the second weight, the third weight, the fourth weight, the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value and the normalized skin humidity model predicted value.
The variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method has the following beneficial effects: the method comprises the following steps: acquiring monitoring parameters; predicting by adopting a preset model according to the monitoring parameters to obtain a multi-model prediction result; performing variable weight processing based on the multi-model prediction result to obtain a comprehensive prediction value; and adjusting the air supply quantity at the tail end of the central air conditioner according to the comprehensive predicted value. According to the invention, the air supply control of the tail end of the central air conditioner based on variable weight multi-model comprehensive prediction is adopted, and the comprehensive prediction value is used as the indoor thermal comfort evaluation index, so that when the indoor thermal environment changes, a model with higher precision in a single thermal comfort prediction model can be dynamically endowed with a higher weight value in different thermal environment variable value areas, thus the prediction precision of the variable weight comprehensive prediction model is improved, the air supply state of the tail end of the central air conditioner is reasonably adjusted, and the comfort of the indoor thermal environment is improved.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
fig. 1 is a schematic flow chart of a variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method according to an embodiment of the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
In order to solve the problems of limitation, small application range and incapability of achieving good thermal comfort in the existing air supply control method for the tail end of the central air conditioner by adopting a single model, the invention provides a comprehensive prediction central air conditioner tail end air supply control method based on a variable weight multi-model.
Referring to fig. 1, fig. 1 is a schematic flow chart of an alternative embodiment of the embodiments of the present invention.
As shown in fig. 1, the variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method includes:
and step S10, acquiring monitoring parameters.
Specifically, the monitoring parameters may include: indoor air temperature, indoor relative humidity, indoor air velocity, indoor black ball temperature, and human body temperature. The indoor air temperature can be monitored and acquired through the temperature sensor, the indoor relative humidity can be monitored and acquired through the humidity sensor, the indoor air speed can be monitored and acquired through the anemoscope, the indoor black ball temperature can be monitored and acquired through the black ball thermometer, and the human body temperature can be monitored and acquired through the infrared camera. Wherein, the human body temperature can include: human head temperature, human hand temperature, human ankle temperature.
And step S20, predicting according to the monitoring parameters and by adopting a preset model to obtain a multi-model prediction result.
In some embodiments, the preset model may include: an effective temperature model. The method comprises the following steps of obtaining a multi-model prediction result according to monitoring parameters and by adopting a preset model for prediction, wherein the multi-model prediction result comprises the following steps: and obtaining an effective temperature predicted value according to the indoor air temperature, the indoor relative humidity and the effective temperature model.
Specifically, the effective temperature model can be expressed by a mathematical expression:
wherein ET is the predicted value of effective temperature, taIs the temperature of the air in the room,is the indoor relative humidity.
Therefore, when obtaining the indoor air temperature and the indoor relative humidity, the predicted effective temperature value can be directly obtained from the expression (1) (the relational expression between the effective temperature and the indoor air temperature and the indoor relative humidity).
In some other embodiments, the predetermined model may include: expected mean evaluation index model (PMV model). The method comprises the following steps of obtaining a multi-model prediction result according to monitoring parameters and by adopting a preset model for prediction, wherein the multi-model prediction result comprises the following steps: and obtaining an expected average evaluation index prediction value according to the indoor air temperature, the indoor relative humidity, the indoor black ball temperature, the indoor air speed, the clothes thermal resistance and the human body heat dissipation rate value.
Wherein the expected average evaluation index predicted value can be obtained by the following equation:
in the formula (2), M is the human body heat generation rate, W is the additional heat dissipation of human body activities (the indoor personnel are generally 0), PaIs the partial pressure of water vapor in the air, taIs the temperature of the indoor air, fclIs the dressing area coefficient, tclIs the temperature of the surface of the garment,is the mean radiant temperature, hcIs the convective heat transfer coefficient.
Specifically, obtaining the expected average evaluation index prediction value according to the indoor air temperature, the indoor relative humidity, the indoor black ball temperature, the indoor air speed, the clothes thermal resistance and the human body heat dissipation rate value comprises the following steps:
and obtaining the partial pressure of the air vapor according to the relational expression of the indoor air temperature, the indoor relative humidity and the partial pressure of the air vapor.
The relational expression of the indoor air temperature, the indoor relative humidity and the air water vapor partial pressure is as follows:
and obtaining the dressing area coefficient according to the relation of the thermal resistance of the clothes and the dressing area coefficient.
The relation between the thermal resistance of the clothes and the wearing area coefficient is as follows:
in the formula (4), IclIs the thermal resistance of the clothes.
Wherein, the thermal resistance of the clothes can refer to the table 1.
TABLE 1 thermal resistance of clothes
And obtaining the surface temperature of the clothes according to the relational expression of the human body heat generation rate, the additional heat dissipation value of the human body activity, the heat resistance of the clothes and the dressing area coefficient.
Wherein the relationship among the human body heat production rate, the additional heat dissipation value of human body activity, the thermal resistance of clothes and the dressing area coefficient is as follows:
and obtaining the average radiation temperature according to the relation among the indoor black ball temperature, the indoor air speed and the average radiation temperature.
The relation among the indoor black ball temperature, the indoor air speed and the average radiation temperature is as follows:
(7) in the formula, tgIs the indoor black ball temperature, varIs the indoor air velocity.
And obtaining the convective heat transfer coefficient according to the relation among the surface temperature of the clothes, the indoor air temperature, the indoor air speed and the convective heat transfer coefficient.
Wherein, the relation among the surface temperature of clothes, indoor air temperature, indoor air speed and the coefficient of heat convection is:
and obtaining an expected average evaluation index predicted value according to the human heat production rate, the additional heat dissipation value of human activities, the partial pressure of air vapor, the dressing area coefficient, the surface temperature of clothes, the indoor air temperature, the average radiation temperature and the convection heat transfer coefficient.
In some embodiments, the preset model may include: a human physiological parameter comprehensive evaluation model. The method comprises the following steps of obtaining a multi-model prediction result according to monitoring parameters and by adopting a preset model for prediction, wherein the multi-model prediction result comprises the following steps: and obtaining a comprehensive evaluation predicted value of the human physiological parameters according to the human head temperature, the human hand temperature, the human ankle temperature, the average radiation temperature and the indoor air temperature.
Specifically, according to human head temperature, human hand temperature, human ankle temperature, average radiation temperature and indoor air temperature, the comprehensive evaluation predicted value of the obtained human physiological parameters comprises:
the operating temperature is obtained from the relational expression of the indoor air temperature, the average radiation temperature, and the operating temperature.
Wherein the relation among the indoor air temperature, the average radiation temperature and the operation temperature is as follows:
and obtaining the average body surface temperature of the human body according to the head temperature, the hand temperature and the ankle temperature of the human body.
Because human body temperature is sheltered from by the clothes, consequently, it is great to adopt infrared camera to acquire whole body skin temperature degree of difficulty, consequently, the accessible is got the average value as human average body surface temperature to human head temperature, human hand temperature and human ankle temperature.
That is, the average body surface temperature of the human body can be obtained by the following formula:
(10) in the formula, tskinIs the average body surface temperature, theadIs the human head temperature, thandIs the temperature of the human hand, tankleIs the ankle temperature of the human body.
And obtaining the average body surface impedance according to the relational expression of the operation temperature and the average body surface impedance.
Wherein, the relation between the operation temperature and the average body surface impedance is as follows:
Iskin=-29top+1141.73 (11)。
(11) in the formula IskinMean body surface impedance.
And obtaining a comprehensive evaluation predicted value of the human physiological parameters according to the operation temperature, the human body average body surface temperature and the average body surface impedance.
Wherein, the comprehensive evaluation predicted value of the human physiological parameters can be obtained by the following formula:
TSV=0.165top+0.468tskin-0.0018Iskin-193772 (8)。
in some embodiments, the predetermined model comprises: skin moisture model.
Predicting by adopting a preset model according to the monitoring parameters, and obtaining a multi-model prediction result comprises the following steps:
and obtaining the relative humidity of the skin according to the average body surface temperature, the indoor air temperature and the air water vapor partial pressure.
And obtaining a predicted value of the skin humidity model according to the skin relative humidity.
Wherein the predicted value of skin moisture is obtained by the following formula:
skin relative humidity can be obtained by the following formula:
in hot scoring, the 7 point system in ISO7730 is generally used for heat sensing voting, i.e. as shown in table 3:
TABLE 3 seven-system heat sensation evaluation table
Wherein, PMV model and human physiological parameter evaluation comprehensive model all adopt 7 minutes system, and the thermal sensation prediction of effective temperature model and skin temperature model adopts the index system inconsistent, therefore, need carry out normalization processing. Namely, the effective temperature predicted value and the skin humidity model predicted value are normalized to obtain a normalized effective temperature predicted value and a normalized skin humidity model predicted value.
Specifically, in some embodiments, the Min-Max method (Min-Max method) may be used to linearly transform the raw data such that the resulting values map between [ -3, 3 ]. Wherein, the normalization formula is as follows:
the effective temperature model and the skin humidity model are respectively normalized by the formula (14) to obtain:
A. effective temperature:
B. skin moisture:
and step S30, performing variable weight processing based on the multi-model prediction result to obtain a comprehensive prediction value.
Specifically, the variable weight processing is performed based on the multi-model prediction result, and the obtaining of the comprehensive prediction value includes:
and weighting the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value and the normalized skin humidity model predicted value to obtain a comprehensive predicted value.
Further, weighting the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value and the normalized skin humidity model predicted value to obtain the comprehensive predicted values, wherein the weighting comprises the following steps:
determining a first weight of the predicted value of the normalized effective temperature, a second weight of the predicted value of the expected average evaluation index, a third weight of the predicted value of the comprehensive evaluation of the human physiological parameters and a fourth weight of the predicted value of the normalized skin humidity model; and obtaining a comprehensive predicted value according to the first weight, the second weight, the third weight, the fourth weight, the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value and the normalized skin humidity model predicted value.
Specifically, the four models are combined into a variable-weight comprehensive prediction model, that is:
therefore, the predicted relation is synthesized with reference to the variable weights, as follows:
the following results were obtained:
f(t+1)=g1(t+1)·f1(t+1)+g2(t+1)·f2(t+1)+g3(t+1)·f3(t+1)+g4(t+1)·f4(t+1)
(17)。
wherein f (t +1) is the result of the comprehensive prediction model at the time t + 1; f. ofi(t +1) is the prediction result of the ith single prediction model at the time t + 1; gi(t +1) the ith single model predicts the weight of the result at time t + 1. For gi(t +1) has ∑ gi(t +1) ═ 1 and gi(t +1) is not less than 0; i is a natural number greater than 0. The first weight, the second weight, the third weight and the fourth weight are respectively g in the formula (17)1(t+1)、g2(t+1)、g3(t+1)、g4(t+1)。
Further, the value of the weight may be determined by:
and A1, determining the error of the comprehensive predicted value and the error of the ith single predicted value.
The error of the integrated predicted value can be obtained by the following expression (18), and the error of the i-th single predicted value can be obtained by the following expression (19).
(18) In the formula, e (t +1) is the error of the comprehensive predicted value, F (t +1) is the real value of the comprehensive prediction at the time of t +1, and F (t +1) is the comprehensive predicted value at the time of t + 1.
(19) In the formula, Fi(t +1) is the true value of the ith single prediction model at the time t +1, fiAnd (t +1) is the predicted value of the ith single prediction model at the time of t + 1.
Thus, it is possible to obtain:
wherein, the derivation process of the formula (20) is as follows:
the weight g is given by equation (20)iThe confirmation of (t) is divided into two cases:
1) at time t +1, the error e is predicted for any single modeli(t +1) are both non-positive values (or non-negative values).
At this point some single model f existsj(t +1) of the prediction error ej(t +1) (or absolute value | e of prediction error)j(t +1) |) is the smallest among all prediction errors. Then the single model f at this timejThe weight of (t +1) is 1; the weights for the remaining single models are all 0. Wherein j is a natural number greater than 0.
2) At time t +1, the error e is predicted for any single modeliSome (t +1) are non-negative values, and some are negative values.
For all single models with non-negative prediction errors, there is a single model fm(t +1) the prediction error value e thereofm(t +1) is smallest in all single models where the prediction error is non-negative; wherein m is a natural number greater than 0.
For all single models with negative prediction error, there is a single model fn(t +1) absolute value | e of prediction error thereofn(t +1) | is the smallest in all single models where the prediction error is negative. Wherein n is a natural number greater than 0.
At this time, the single model fm(t +1) and the single model fnThe weighted values corresponding to (t +1) are respectively:
the weights corresponding to the remaining single models are all 0.
Based on this, after the weight value is determined, the thermal sensation at time t +1 can be predicted by using the variable weight comprehensive prediction model (17).
And step S40, adjusting the air supply quantity at the tail end of the central air conditioner according to the comprehensive predicted value.
Specifically, after the comprehensive predicted value is obtained in step S30, the operation frequency of the central air-conditioning end fan may be adjusted according to the comprehensive predicted value and the operation frequency control table of the central air-conditioning end fan, so as to achieve the purpose of adjusting the end air supply volume of the central air-conditioning. The comprehensive predicted value and the running frequency control table of the central air-conditioning terminal fan are shown as follows:
and (4) integrating the predicted value with a control table of the running frequency of the fan at the tail end of the central air conditioner (setting four fan running frequencies of 0%, 50%, 75% and 100%). According to the thermal sensation prediction condition f (t +1) at the moment t +1 and the thermal sensation change condition (f (t +1) -f (t)) relative to the moment t +1, the operation frequency of the air conditioner terminal fan is adjusted according to a control rule table as shown in the following table:
the invention adopts the thermal comprehensive evaluation result as the indoor thermal comfort evaluation index. The method can ensure that a model with higher precision in a single thermal comfort prediction model is dynamically endowed with a higher weight value when the indoor thermal environment changes, so that the precision of the thermal comprehensive evaluation result of the variable-weight comprehensive prediction model is improved.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and are intended to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the scope of the present invention. All equivalent changes and modifications made within the scope of the claims of the present invention should be covered by the claims of the present invention.
Claims (10)
1. A variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method is characterized by comprising the following steps:
acquiring monitoring parameters;
predicting by adopting a preset model according to the monitoring parameters to obtain a multi-model prediction result;
performing variable weight processing based on the multi-model prediction result to obtain a comprehensive prediction value;
and adjusting the air supply quantity at the tail end of the central air conditioner according to the comprehensive predicted value.
2. The variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method according to claim 1, wherein the monitoring parameters comprise: indoor air temperature, indoor relative humidity, indoor air velocity, indoor black ball temperature, and human body temperature;
the preset model comprises: an effective temperature model;
the predicting according to the monitoring parameters and by adopting a preset model, and obtaining a multi-model prediction result comprises the following steps:
and obtaining an effective temperature predicted value according to the indoor air temperature, the indoor relative humidity and the effective temperature model.
3. The variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method according to claim 2, wherein the preset model further comprises: an expected average evaluation index model;
the predicting according to the monitoring parameters and by adopting a preset model, and obtaining a multi-model prediction result comprises the following steps:
and obtaining an expected average evaluation index prediction value according to the indoor air temperature, the indoor relative humidity, the indoor black ball temperature, the indoor air speed, the clothes thermal resistance and the human body heat dissipation rate value.
4. The method of claim 3, wherein obtaining an expected average evaluation index prediction value based on the indoor air temperature, the indoor relative humidity, the indoor black-bulb temperature, the indoor air velocity, the clothing thermal resistance, and the human body heat dissipation value comprises:
obtaining the air water vapor partial pressure according to the relation among the indoor air temperature, the indoor relative humidity and the air water vapor partial pressure;
obtaining the dressing area coefficient according to the relation between the thermal resistance of the clothes and the dressing area coefficient;
obtaining the surface temperature of the clothes according to the relational expression of the human body heat generation rate, the additional heat dissipation value of the human body activity, the thermal resistance of the clothes and the dressing area coefficient;
obtaining the average radiation temperature according to the relation among the indoor black ball temperature, the indoor air speed and the average radiation temperature;
obtaining the convective heat transfer coefficient according to the relational expression of the surface temperature of the clothes, the temperature of the indoor air, the speed of the indoor air and the convective heat transfer coefficient;
and obtaining the expected average evaluation index predicted value according to the human body heat production rate, the human body activity additional heat dissipation value, the air water vapor partial pressure, the dressing area coefficient, the clothes surface temperature, the indoor air temperature, the average radiation temperature and the convection heat transfer coefficient.
5. The variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method according to claim 4, wherein the human body temperature comprises: human head temperature, human hand temperature, human ankle temperature;
the preset model comprises: a human physiological parameter comprehensive evaluation model;
the predicting according to the monitoring parameters and by adopting a preset model, and obtaining a multi-model prediction result comprises the following steps:
and obtaining the comprehensive evaluation predicted value of the human physiological parameters according to the human head temperature, the human hand temperature, the human ankle temperature, the average radiation temperature and the indoor air temperature.
6. The method of claim 5, wherein obtaining the human physiological parameter comprehensive evaluation prediction value according to the human head temperature, the human hand temperature, the human ankle temperature, the average radiation temperature, and the indoor air temperature comprises:
obtaining the operating temperature according to a relational expression of the indoor air temperature, the average radiation temperature and the operating temperature;
obtaining the average body surface temperature of the human body according to the head temperature, the hand temperature and the ankle temperature of the human body;
obtaining the average body surface impedance according to the relational expression of the operation temperature and the average body surface impedance;
and obtaining the comprehensive evaluation predicted value of the human physiological parameters according to the operation temperature, the human body average body surface temperature and the average body surface impedance.
7. The variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method according to claim 6, wherein the preset model comprises: a skin moisture model;
the predicting according to the monitoring parameters and by adopting a preset model, and obtaining a multi-model prediction result comprises the following steps:
obtaining the relative humidity of the skin according to the average body surface temperature, the indoor air temperature and the air vapor partial pressure;
and obtaining the predicted value of the skin humidity model according to the skin relative humidity.
8. The variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method according to claim 7, characterized by further comprising:
and carrying out normalization processing on the effective temperature predicted value and the skin humidity model predicted value to obtain a normalized effective temperature predicted value and a normalized skin humidity model predicted value.
9. The variable-weight multi-model comprehensive prediction central air-conditioning terminal air supply control method according to claim 8, wherein performing variable-weight processing based on the multi-model prediction result to obtain a comprehensive prediction value comprises:
and weighting the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value and the normalized skin humidity model predicted value to obtain the comprehensive predicted value.
10. The method of claim 9, wherein the weighting the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value, and the normalized skin humidity model predicted value to obtain the comprehensive predicted values comprises:
determining a first weight of the predicted value of the normalized effective temperature, a second weight of the predicted value of the expected average evaluation index, a third weight of the predicted value of the comprehensive evaluation of the human physiological parameters and a fourth weight of the predicted value of the normalized skin humidity model;
and obtaining the comprehensive predicted value according to the first weight, the second weight, the third weight, the fourth weight, the normalized effective temperature predicted value, the expected average evaluation index predicted value, the human physiological parameter comprehensive evaluation predicted value and the normalized skin humidity model predicted value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010903115.7A CN112254287B (en) | 2020-09-01 | 2020-09-01 | Variable-weight multi-model comprehensive prediction central air conditioner tail end air supply control method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010903115.7A CN112254287B (en) | 2020-09-01 | 2020-09-01 | Variable-weight multi-model comprehensive prediction central air conditioner tail end air supply control method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112254287A true CN112254287A (en) | 2021-01-22 |
CN112254287B CN112254287B (en) | 2022-06-14 |
Family
ID=74223843
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010903115.7A Active CN112254287B (en) | 2020-09-01 | 2020-09-01 | Variable-weight multi-model comprehensive prediction central air conditioner tail end air supply control method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112254287B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113891508A (en) * | 2021-09-23 | 2022-01-04 | 深圳汝原科技有限公司 | Control method of drying device, drying device and readable storage medium |
CN115031394A (en) * | 2022-05-18 | 2022-09-09 | 深圳达实智能股份有限公司 | Regional air conditioner adjusting method based on personal heat pleasure clustering |
WO2022247411A1 (en) * | 2021-05-26 | 2022-12-01 | 上海三一重机股份有限公司 | Air volume control method and apparatus for working machinery cockpit |
CN115758869A (en) * | 2022-11-07 | 2023-03-07 | 浙江迈新科技股份有限公司 | Bim-based intelligent building management and control system |
Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH02242037A (en) * | 1989-03-14 | 1990-09-26 | Mitsubishi Electric Corp | Air conditioning system controller |
JPH055546A (en) * | 1991-06-26 | 1993-01-14 | Yamatake Honeywell Co Ltd | Device for monitoring set value for hot feeling control |
JPH09105545A (en) * | 1995-10-06 | 1997-04-22 | Matsushita Electric Ind Co Ltd | Air-conditioning device |
JP2000291990A (en) * | 1999-04-06 | 2000-10-20 | Matsushita Electric Ind Co Ltd | Controller for cooling and heating device and control method |
CN1699866A (en) * | 2004-05-21 | 2005-11-23 | Lg电子株式会社 | Air conditioning system and method for controlling the same |
CN1727792A (en) * | 2004-07-26 | 2006-02-01 | 乐金电子(天津)电器有限公司 | Method for controlling comfortable index of air condition system |
CN102812303A (en) * | 2009-12-16 | 2012-12-05 | 国家科学和工业研究组织 | HVAC Control System And Method |
CN103823368A (en) * | 2014-01-27 | 2014-05-28 | 浙江大学 | PID (proportion, integral, derivative)-type fuzzy logic control method based on weight rule table |
CN104160217A (en) * | 2013-03-04 | 2014-11-19 | 株式会社东芝 | Air-conditioning control device and storage medium |
CN104180446A (en) * | 2014-08-11 | 2014-12-03 | 周伟文 | System and method for artificial simulation of forest microclimate |
CN104490371A (en) * | 2014-12-30 | 2015-04-08 | 天津大学 | Heat comfort detection method based on physiological parameters of human body |
CN104633866A (en) * | 2015-02-15 | 2015-05-20 | 重庆大学 | Thermal comfort degree evaluating system based on environmental parameters and human body physiological parameters |
CN106123206A (en) * | 2016-06-17 | 2016-11-16 | 美的集团股份有限公司 | A kind of method and system adjusting ambient heat |
JP6076829B2 (en) * | 2013-05-21 | 2017-02-08 | 公益財団法人鉄道総合技術研究所 | Evaluation method of thermal environment in train |
CN106642513A (en) * | 2015-10-28 | 2017-05-10 | 财团法人资讯工业策进会 | Intelligent energy-saving environment regulation and control system and method |
US20170328595A1 (en) * | 2014-12-01 | 2017-11-16 | Nec Corporation | Environmental control equipment and environmental control system |
CN107676936A (en) * | 2017-09-30 | 2018-02-09 | 珠海格力电器股份有限公司 | The control method and device of air-conditioning equipment |
CN109084420A (en) * | 2018-07-28 | 2018-12-25 | 珠海格力电器股份有限公司 | A kind of control method of air-conditioning, device, storage medium and air-conditioning |
CN109341020A (en) * | 2018-09-27 | 2019-02-15 | 重庆智万家科技有限公司 | A kind of intelligent temperature control adjusting method based on big data |
CN109695944A (en) * | 2018-11-29 | 2019-04-30 | 中国汽车工业工程有限公司 | A kind of control method of the coating fresh air conditioner based on multi-model deep learning |
CN110186170A (en) * | 2019-06-20 | 2019-08-30 | 北京石油化工学院 | Hot comfort index PMV control method and equipment |
CN111442478A (en) * | 2020-03-10 | 2020-07-24 | 珠海派诺科技股份有限公司 | Air conditioning system optimization control method, intelligent terminal and storage device |
CN111444943A (en) * | 2020-03-13 | 2020-07-24 | 上海交通大学 | Device and method for adaptive personalized thermal comfort prediction based on human body similarity |
CN111486542A (en) * | 2020-04-28 | 2020-08-04 | 海信(广东)空调有限公司 | Air conditioner and control method and control device thereof |
-
2020
- 2020-09-01 CN CN202010903115.7A patent/CN112254287B/en active Active
Patent Citations (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH02242037A (en) * | 1989-03-14 | 1990-09-26 | Mitsubishi Electric Corp | Air conditioning system controller |
JPH055546A (en) * | 1991-06-26 | 1993-01-14 | Yamatake Honeywell Co Ltd | Device for monitoring set value for hot feeling control |
JPH09105545A (en) * | 1995-10-06 | 1997-04-22 | Matsushita Electric Ind Co Ltd | Air-conditioning device |
JP2000291990A (en) * | 1999-04-06 | 2000-10-20 | Matsushita Electric Ind Co Ltd | Controller for cooling and heating device and control method |
CN1699866A (en) * | 2004-05-21 | 2005-11-23 | Lg电子株式会社 | Air conditioning system and method for controlling the same |
CN1727792A (en) * | 2004-07-26 | 2006-02-01 | 乐金电子(天津)电器有限公司 | Method for controlling comfortable index of air condition system |
CN102812303A (en) * | 2009-12-16 | 2012-12-05 | 国家科学和工业研究组织 | HVAC Control System And Method |
CN104160217A (en) * | 2013-03-04 | 2014-11-19 | 株式会社东芝 | Air-conditioning control device and storage medium |
JP6076829B2 (en) * | 2013-05-21 | 2017-02-08 | 公益財団法人鉄道総合技術研究所 | Evaluation method of thermal environment in train |
CN103823368A (en) * | 2014-01-27 | 2014-05-28 | 浙江大学 | PID (proportion, integral, derivative)-type fuzzy logic control method based on weight rule table |
CN104180446A (en) * | 2014-08-11 | 2014-12-03 | 周伟文 | System and method for artificial simulation of forest microclimate |
US20170328595A1 (en) * | 2014-12-01 | 2017-11-16 | Nec Corporation | Environmental control equipment and environmental control system |
CN104490371A (en) * | 2014-12-30 | 2015-04-08 | 天津大学 | Heat comfort detection method based on physiological parameters of human body |
CN104633866A (en) * | 2015-02-15 | 2015-05-20 | 重庆大学 | Thermal comfort degree evaluating system based on environmental parameters and human body physiological parameters |
CN106642513A (en) * | 2015-10-28 | 2017-05-10 | 财团法人资讯工业策进会 | Intelligent energy-saving environment regulation and control system and method |
CN106123206A (en) * | 2016-06-17 | 2016-11-16 | 美的集团股份有限公司 | A kind of method and system adjusting ambient heat |
CN107676936A (en) * | 2017-09-30 | 2018-02-09 | 珠海格力电器股份有限公司 | The control method and device of air-conditioning equipment |
CN109084420A (en) * | 2018-07-28 | 2018-12-25 | 珠海格力电器股份有限公司 | A kind of control method of air-conditioning, device, storage medium and air-conditioning |
CN109341020A (en) * | 2018-09-27 | 2019-02-15 | 重庆智万家科技有限公司 | A kind of intelligent temperature control adjusting method based on big data |
CN109695944A (en) * | 2018-11-29 | 2019-04-30 | 中国汽车工业工程有限公司 | A kind of control method of the coating fresh air conditioner based on multi-model deep learning |
CN110186170A (en) * | 2019-06-20 | 2019-08-30 | 北京石油化工学院 | Hot comfort index PMV control method and equipment |
CN111442478A (en) * | 2020-03-10 | 2020-07-24 | 珠海派诺科技股份有限公司 | Air conditioning system optimization control method, intelligent terminal and storage device |
CN111444943A (en) * | 2020-03-13 | 2020-07-24 | 上海交通大学 | Device and method for adaptive personalized thermal comfort prediction based on human body similarity |
CN111486542A (en) * | 2020-04-28 | 2020-08-04 | 海信(广东)空调有限公司 | Air conditioner and control method and control device thereof |
Non-Patent Citations (3)
Title |
---|
F. AZIZPOUR等: "Thermal comfort assessment of large-scale hospitals in tropicalclimates: A case study of University Kebangsaan MalaysiaMedical Centre (UKMMC)", 《ENERGY AND BUILDINGS》 * |
杨玉兰等: "居住建筑能效评价指标及权重的确定", 《暖通空调HV&AC》 * |
王昭俊: "《室内空气环境评价与控制》", 30 April 2016 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022247411A1 (en) * | 2021-05-26 | 2022-12-01 | 上海三一重机股份有限公司 | Air volume control method and apparatus for working machinery cockpit |
CN113891508A (en) * | 2021-09-23 | 2022-01-04 | 深圳汝原科技有限公司 | Control method of drying device, drying device and readable storage medium |
CN115031394A (en) * | 2022-05-18 | 2022-09-09 | 深圳达实智能股份有限公司 | Regional air conditioner adjusting method based on personal heat pleasure clustering |
CN115758869A (en) * | 2022-11-07 | 2023-03-07 | 浙江迈新科技股份有限公司 | Bim-based intelligent building management and control system |
Also Published As
Publication number | Publication date |
---|---|
CN112254287B (en) | 2022-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112254287B (en) | Variable-weight multi-model comprehensive prediction central air conditioner tail end air supply control method | |
CN110454930B (en) | Method and device for estimating optimal thermal comfort of human body and air conditioner control method and device | |
CN111720963B (en) | Air conditioning method and device in sleep environment and electronic equipment | |
US11076758B2 (en) | Controlling devices based on physiological measurements | |
CN103592975B (en) | Temperature regulating and controlling method, regulating and controlling device, sensing device and control device | |
US20170123442A1 (en) | System and Method of Smart and Energy-Saving Environmental Control | |
CN105222264B (en) | The pleasant climate method and device of air conditioner | |
CN111854076B (en) | Self-adjustment control method and system based on indoor load and comfort level | |
CN108286781A (en) | Air-conditioner control method, electronic equipment and computer readable storage medium | |
CN113339952A (en) | Air conditioning system | |
CN112128931A (en) | Air conditioner and control method thereof | |
CN109579237B (en) | Air conditioner temperature control method, storage medium and air conditioner | |
CN106885339B (en) | Control method of air conditioner | |
CN108361936A (en) | A kind of method and system promoting DC frequency converting air-conditioner pleasant climate precision | |
CN106500243A (en) | The method and apparatus of control air conditioner output temperature | |
CN110207338A (en) | A kind of air conditioning control method, device, storage medium and air-conditioning | |
CN114251792A (en) | Control method and device of air conditioner and air conditioner | |
CN210292207U (en) | Temperature compensation system of air conditioner and air conditioner | |
CN110006135B (en) | Air conditioner control system and control strategy based on wireless human body temperature measurement | |
TWI746087B (en) | Air conditioning system control method | |
CN109405212A (en) | Air conditioner and its control method, control device, readable storage medium storing program for executing | |
CN107084471B (en) | Control method of air conditioner | |
CN112097378A (en) | Air conditioner comfort level adjusting method based on feedforward neural network | |
CN112395723B (en) | Prediction method for down jacket adapting to ambient temperature | |
CN112923529B (en) | Heating air conditioner temperature regulation and control method and system based on thermal history |
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 |