CN117989718A - Central air conditioner intelligent control system based on machine learning - Google Patents
Central air conditioner intelligent control system based on machine learning Download PDFInfo
- Publication number
- CN117989718A CN117989718A CN202410155700.1A CN202410155700A CN117989718A CN 117989718 A CN117989718 A CN 117989718A CN 202410155700 A CN202410155700 A CN 202410155700A CN 117989718 A CN117989718 A CN 117989718A
- Authority
- CN
- China
- Prior art keywords
- temperature
- time
- target building
- central air
- air conditioner
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 25
- 238000012351 Integrated analysis Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 28
- 238000001816 cooling Methods 0.000 claims description 16
- 230000007613 environmental effect Effects 0.000 claims description 12
- 238000010438 heat treatment Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 10
- 238000004378 air conditioning Methods 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 5
- 238000011897 real-time detection Methods 0.000 claims description 5
- 239000000498 cooling water Substances 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 230000001276 controlling effect Effects 0.000 description 7
- 230000001105 regulatory effect Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000007710 freezing Methods 0.000 description 2
- 230000008014 freezing Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000008016 vaporization Effects 0.000 description 1
- 238000009834 vaporization Methods 0.000 description 1
Landscapes
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses a central air conditioner intelligent control system based on machine learning, which relates to the technical field of indoor environment control and comprises an inertia analysis module, an integrated analysis module and a temperature control module, wherein the temperature control module is used for reading the time of a use area of a target building by analyzing monitoring information, dividing the time of the use area into a plurality of target areas, extracting the area information in the target areas, obtaining a temperature comparison table based on a machine learning algorithm, then transmitting the detected real-time environment temperature and the flow in the target building into the temperature comparison table for calculation to obtain the optimal temperature, comparing the optimal temperature with the environment temperature, outputting an external input signal and an equipment operation signal according to a comparison result, then adjusting the temperature in the target building by an equipment group of the central air conditioner according to the signal, improving the timeliness of the central air conditioner on the environment adjustment of the target building, and reducing the time of unadapted temperature of personnel.
Description
Technical Field
The invention belongs to the technical field of indoor environment control, and particularly relates to an intelligent control system of a central air conditioner based on machine learning.
Background
The central air conditioning system consists of one or more cold and heat source systems and a plurality of air conditioning systems, and adopts the principle of liquid vaporization refrigeration to provide required cold energy for the air conditioning systems so as to offset the heat load of indoor environment; the heating system provides the air conditioning system with the required heat to counteract the indoor environmental cooling and heating load.
The invention of patent application publication number CN115493255A discloses an intelligent control method and system of a central air conditioner unit, wherein the method comprises the steps of predicting the load of the central air conditioner unit in the starting stage, and determining and starting a target cooling tower, a target freezing pump, a target cooling pump and a target water chilling unit according to a balance priority principle or an efficiency priority principle; in the operation stage, under the normal operation state, loading or unloading of the cooling tower, the refrigerating pump, the cooling pump and the water chilling unit is carried out according to the actual load change of the central air conditioning unit, and under the fault state, the fault equipment is closed, and the replacement equipment of the fault equipment is determined and opened; and in the shutdown stage, the cooling tower, the freezing pump, the cooling pump and the water chilling unit are closed.
However, in a building in which temperature control is performed by a central air conditioner, the people flow distribution of each time period in the building is not uniform, and at the moment, the temperature regulated in the building by the central air conditioner needs to be changed in real time, otherwise, the discomfort of the body temperature of people in the building is easily caused, if manual regulation is adopted, the temperature change is delayed at the moment, and the intelligence of the central air conditioner is reduced.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art; therefore, the invention provides a central air conditioner intelligent control system based on machine learning, which is used for solving the technical problems.
In order to achieve the above purpose, the present invention proposes the following solutions: an intelligent control system of a central air conditioner based on machine learning, comprising:
The inertial analysis module is used for analyzing the received monitoring information, reading the time of a use area of the target building, dividing the time of the use area into a plurality of target areas, extracting area information in the target areas, wherein the area information comprises the ambient temperature, the weather state, the flow in the target building and the optimal temperature, obtaining a temperature comparison table based on a machine learning algorithm, and transmitting the temperature comparison table to the integrated analysis module by the inertial analysis module;
The integrated analysis module is used for transmitting the detected real-time environment temperature and the flow in the target building to the temperature comparison table for calculation to obtain the optimal temperature, and then the integrated analysis end transmits the optimal temperature to the temperature control module;
And the temperature control module is used for comparing the optimal temperature with the ambient temperature, outputting an external input signal and an equipment operation signal according to a comparison result, and then adjusting the temperature in the target building by the equipment group of the central air conditioner according to the external input signal and the equipment operation signal.
As a further scheme of the invention, the monitoring information is stored by the history storage end and is transmitted to the inertia analysis end, wherein the monitoring information comprises weather data and building monitoring information in a period time, the period time is a threshold value, the weather data comprises weather states and environment temperatures, and the building monitoring information refers to terminal temperature and flow in a target building.
As a further scheme of the invention, the environmental collection module collects the weather data through the prediction data of the weather station and transmits the prediction data to the inertia analysis module.
As a further scheme of the invention, the specific acquisition method of the temperature comparison table comprises the following steps:
extracting monitoring information of the previous period, extracting working time of a target building from the monitoring information, and taking the working time as the time of a using area of a central air conditioner;
dividing the using area time into a plurality of area times according to unit time, wherein the unit time is a threshold value, and acquiring flow and meteorological data of each area time;
respectively taking the region time as a target region, and extracting region information of all the target regions in the period time, wherein the region information comprises the ambient temperature, the weather state, the flow and the optimal temperature;
and taking the environment temperature, the weather state and the flow as independent variables, taking the optimal temperature in the target building as the dependent variables, taking the data in the residual area information as an influence factor, constructing a machine learning model, and carrying out deep analysis on the optimal temperature in the target building to obtain a temperature comparison table.
As a further scheme of the invention, the temperature comparison table is calculated by a fuzzy control algorithm in a machine learning algorithm, and the specific calculation process is as follows:
Firstly, setting the optimal temperatures corresponding to the ambient temperature, the weather state and the flow in different target areas;
then, the independent variable information is taken as input information, the dependent variable is taken as output information, and the method is based on Obtaining a minimum objective function Bm, namely an optimal temperature, wherein m represents the number of target areas in the period time, m is larger than 1, u ij represents the membership degree of a sample Xi belonging to j classes, xi represents the sample, cj represents a center cluster, i represents the measurement of the distance, and the membership degree is calculated by a membership degree function;
When (when) And when the iteration is ended, the optimal temperature setting method is ended, and then the setting method is used as a temperature comparison table and is transmitted to the integrated analysis module, k represents the iteration step number, and delta is a threshold value.
As a further scheme of the invention, the method for acquiring the optimal temperature comprises the following steps:
And taking the received real-time environment data and the flow in the target building at the moment as input information, respectively inputting the input information into a temperature comparison table, processing the input information according to a judgment rule in the temperature comparison table, finally outputting data, and taking the output data as the real-time optimal temperature of the target building.
As a further scheme of the invention, the real-time environment data and the flow are collected by the real-time detection module and transmitted to the integrated analysis module.
As a further scheme of the invention, the method for acquiring the external input signal and the equipment operation signal comprises the following steps:
Extracting the environmental temperature HJ in the meteorological data, and simultaneously respectively acquiring the terminal temperature WZ and the optimal temperature WS in the target building;
Subtracting the optimal temperature WS from the terminal temperature WZ to obtain a building temperature difference WC, generating a cooling signal for a target building when the building temperature difference WC is a positive value, and generating a heating signal for the target building when the building temperature difference WC is a negative value;
When a heating signal or a cooling signal is generated, comparing the ambient temperature HJ with the optimal temperature WS, and subtracting the optimal temperature WS from the ambient temperature HJ to obtain an ambient temperature difference if the temperature in the target building is the heating signal at the moment, and subtracting the ambient temperature HJ from the optimal temperature to obtain the ambient temperature difference if the temperature in the target building is the cooling signal;
If the environmental temperature difference is greater than or equal to a1, generating an external input signal at the moment, otherwise, generating an equipment operation signal, wherein a1 is a threshold value, and a1 is more than 0;
When an external input signal is detected, the equipment set of the central air conditioner is started at the moment, the equipment set is enabled to enter a standby mode, then the disc fan set is used for controlling the optimal temperature in a target building by introducing external air, when an equipment operation signal is detected, the equipment set of the central air conditioner is started at the moment, the disc fan set is connected with the equipment set, the equipment set is used for controlling the temperature of cooling water, and the temperature in the target building is controlled.
The invention further provides a pre-adjusting module for pre-adjusting the temperature in the target building, which comprises the following specific adjusting method:
Extracting an end point of the use area time, marking the starting time of the use area time as a front end time point, simultaneously acquiring the flow of the front end time point every day in the period time, and carrying out mean value processing on the flow to obtain a flow mean value of the front end time point;
The environmental collection module collects the meteorological data of the front end time point of the current day of the target building, takes the flow average value and the meteorological data of the front end time point of the current day as input information, and transmits the input information to the integrated analysis module for processing to obtain the optimal temperature of the front end time point;
And setting preset time, taking the front-end time point as a reference, detecting the terminal temperature of the target building at the front-end time point, transmitting the terminal temperature and the optimal temperature of the front-end time point to a temperature control module, and adjusting the temperature in the target building.
Compared with the prior art, the invention has the beneficial effects that:
According to the invention, the real-time flow in the external environment and the building is collected in real time, and is processed by adopting a machine learning algorithm, so that the optimal temperature in the target building is output, the environment temperature in the target building is timely regulated, the timeliness of the central air conditioner for regulating the environment of the target building is improved, and the time of inadaptation of the temperature sensing of personnel is reduced;
According to the invention, the external environment temperature is compared with the optimal temperature, an external input signal is generated according to the comparison result, external air is input into a target building according to the external input signal, and the temperature of the target building is regulated, so that the operation energy consumption of a central air conditioner equipment set during starting is reduced, and the energy saving effect is achieved;
According to the invention, the pre-adjusting module is arranged, so that the meteorological data and the terminal temperature at the front end time point are collected and processed by the machine learning algorithm, the optimal temperature is output, and then the temperature in the target building is adjusted, so that the optimal temperature can be reached when people enter the target building, and the control intelligence of the central air conditioner is improved.
Drawings
FIG. 1 is a schematic diagram of a system frame of the present invention;
Fig. 2 is a schematic diagram of a flow frame of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one:
referring to fig. 1 and 2, the application provides a central air conditioner intelligent control system based on machine learning, which comprises an environment acquisition module, a history storage module, an inertia analysis module, a real-time detection module, an integrated analysis module and a temperature control module;
The environment acquisition module acquires weather data of a target building through a weather station based on the geographic position of the target building, wherein the weather data comprise weather states, environment temperatures and the like, the specific weather states are sunny days, rainy days, cloudy days or the like, the target building is a building which uses a central air conditioner of the system to intelligently control the space environment, and then the environment acquisition module transmits the weather data of the target building to the inertia analysis module;
The history storage module is used for storing monitoring information in a target building, wherein the monitoring information comprises environment monitoring information and building monitoring information, the environment monitoring information refers to meteorological data in the previous cycle time of the target building, the building monitoring information refers to the temperature and flow of the target building in the previous cycle time, the specific flow refers to the number of people in the target building, the cycle time is a threshold value, in the embodiment, the cycle time is set to be 30 days, and then the history storage module transmits the monitoring information in the target building to the inertia analysis module;
the inertia analysis module establishes a temperature comparison table in the target building based on historical monitoring information of the target building, and the specific temperature comparison table establishment method comprises the following steps:
S1: the monitoring information in the previous period time is extracted, the working time of the target building is set to be the using area time of the central air conditioner according to the working time of the target building, for example, the target building is set to be a supermarket, the business time of the supermarket is set to be 10 in the morning to 10 in the evening, and at the moment, the using area time of the central air conditioner is 10 in the morning to 10 in the evening;
S2: dividing the use area time into a plurality of area times according to unit time, wherein the unit time is a threshold value, and in the embodiment, the unit time is set to be 1 hour, and meanwhile, the flow in each area time and the meteorological data in the corresponding area time are acquired;
s3: firstly, taking the regional time as an analysis target, respectively marking all the regional time as a target region, and firstly extracting regional information of the target region in the period time, wherein the regional information is obtained by combining monitoring information and meteorological data in unit regional time, and the specific regional information comprises the environment temperature, the weather state, the flow in a target building and the optimal temperature in the target building;
S4: taking the environment temperature, the weather state and the flow as independent variables, taking the optimal temperature in a target building as the dependent variables, taking the data in the residual area information as an influence factor, building a machine learning model, and carrying out deep analysis on the optimal temperature in the target building to obtain a temperature comparison table, wherein in the embodiment, a fuzzy control algorithm is selected as the machine learning model, and the algorithm process is as follows:
Firstly, setting a fuzzy rule, wherein the setting of the fuzzy rule is set by a person skilled in the art, and in the embodiment, setting of the optimal temperatures corresponding to different meteorological data is set as the setting of the fuzzy rule;
information of independent variables in a target area is used as a group of data based on M represents the number of target areas in the cycle time, m is greater than 1, bm represents the minimized target function, i.e. the output optimum temperature, u ij represents the membership degree of the sample Xi belonging to the j class, xi represents the sample, cj represents the center cluster, cj represents the center point of the membership function curve in this embodiment, i represents the measure of the distance, wherein the membership degree is calculated by the membership degree function, in this embodiment, the membership degree function is selected as a triangle membership degree function, the specific calculation process of the triangle membership degree function is the prior art, and no further description is given here;
When (when) When the iteration is ended, the optimal temperature setting method is ended, the setting method is used as a temperature comparison table and is transmitted to an integrated analysis module, k represents the iteration step number, delta is a threshold value, and the specific value is set by a person skilled in the art;
The real-time detection module is used for detecting real-time environment data in the target building and transmitting the real-time environment data to the integrated analysis module, wherein the real-time environment data comprise weather data of the target building in real-time regional time, flow in the target building and terminal temperature in the target building, and the specific terminal temperature is the indoor temperature in the target building;
the integrated analysis module calculates the real-time optimal temperature in the target building based on the received real-time environment data and the temperature comparison table, and the specific calculation method comprises the following steps:
the received real-time environment data and the flow in the target building at the moment are used as input information, the input information is respectively input in a temperature comparison table, meanwhile, the input information is processed according to a judgment rule in the temperature comparison table, and finally, the data is output, and the output data is used as the real-time optimal temperature of the target building;
then the integrated analysis module transmits the real-time optimal temperature of the target building to the temperature control module;
The temperature control module controls the temperature in the target building by taking the optimal temperature as the control temperature of the central air conditioner based on the received optimal temperature.
Embodiment two:
the difference between the embodiment and the embodiment is that the embodiment further includes a temperature control module for controlling the received optimal temperature, the real-time detection module extracts weather data in the real-time environment data and transmits the weather data to the temperature control module, and the specific method for controlling the optimal temperature of the target environment by the temperature control module is as follows:
Extracting the environmental temperature in meteorological data, marking the environmental temperature as HJ, simultaneously respectively obtaining the terminal temperature and the optimal temperature in a target building, respectively marking the terminal temperature and the optimal temperature as WZ and WS, subtracting the optimal temperature WS from the terminal temperature WZ to obtain a building temperature difference WC, wherein the building temperature difference comprises symbols, when the building temperature difference WC is positive, generating a cooling signal for the target building at the moment, and when the building temperature difference WC is negative, generating a heating signal for the target building;
When a heating signal or a cooling signal is generated, comparing the ambient temperature HJ with the optimal temperature WS, and subtracting the optimal temperature WS from the ambient temperature HJ to obtain an ambient temperature difference if the temperature in the target building is the heating signal at the moment, and subtracting the ambient temperature HJ from the optimal temperature to obtain the ambient temperature difference if the temperature in the target building is the cooling signal;
If the ambient temperature difference is greater than or equal to a1, an external input signal is generated at the moment, otherwise, if the ambient temperature difference is less than a1, an equipment operation signal is generated, a1 is a threshold value, a1 is more than 0, and a specific a1 value is set by a person skilled in the art;
When an external input signal is detected, starting up an equipment set of the central air conditioner at the moment, enabling the equipment set to enter a standby mode, controlling the optimal temperature in a target building by introducing external air into the equipment set, and when an equipment operation signal is detected, starting the equipment set of the central air conditioner at the moment, connecting the equipment set and the equipment set, controlling the temperature of cooling water by the equipment set, and controlling the temperature in the target building;
embodiment III:
the difference between the first embodiment and the second embodiment and the first embodiment is that the present embodiment further includes a preconditioning module, the preconditioning module extracts an endpoint of the usage area time based on the usage area time, marks a start time of the usage area time as a front end time point, and preconditions the target building according to the front end time point, where the preconditioning module specifically comprises:
Firstly extracting the flow of the front-end time point of each day in the period time, carrying out average value processing on the flow to obtain the flow average value of the front-end time point, then collecting the meteorological data of the front-end time point of the current day of the target building by an environment collecting module, taking the flow average value and the meteorological data of the front-end time point of the current day as input information, and transmitting the input information to an integrated analyzing module for processing to obtain the optimal temperature of the front-end time point;
Meanwhile, setting preset time according to the area of the target building, wherein the preset time is set to be 10 minutes in the embodiment;
Detecting the terminal temperature of the target building by taking the front-end time point as a reference and presetting time before the front-end time point, for example, when the front-end time point is 9 points, the preset time is set to be 10 minutes, at the moment, detecting the terminal temperature of the target building at the time of 8 points 50, then transmitting the terminal temperature and the optimal temperature of the front-end time point to a temperature control module, and processing according to a method of the temperature control module, so that the target building can be adjusted to the optimal temperature when people enter, and the intelligence of the central air conditioner is improved;
Embodiment four:
The present embodiment is used for fusing and implementing the first, second and third embodiments on the basis of the first, second and third embodiments.
The partial data in the formula are all obtained by removing dimension and taking the numerical value for calculation, and the formula is a formula closest to the real situation obtained by simulating a large amount of collected data through software; the preset parameters and the preset threshold values in the formula are set by those skilled in the art according to actual conditions or are obtained through mass data simulation.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (9)
1. The utility model provides a based on machine study central air conditioning intelligent control system which characterized in that includes:
The inertial analysis module is used for analyzing the received monitoring information, reading the use area time of the target building, dividing the use area time into a plurality of target areas, extracting the area information in the target areas, wherein the area information comprises the ambient temperature, the weather state, the flow in the target building and the optimal temperature, processing the area information by using a machine learning algorithm to obtain a temperature comparison table, and transmitting the temperature comparison table to the integrated analysis module by the inertial analysis module;
The integrated analysis module is used for transmitting the detected real-time environment temperature and the flow in the target building to the temperature comparison table for calculation to obtain the optimal temperature, and then the integrated analysis end transmits the optimal temperature to the temperature control module;
And the temperature control module is used for comparing the optimal temperature with the ambient temperature, outputting an external input signal and an equipment operation signal according to a comparison result, and then adjusting the temperature in the target building by the equipment group of the central air conditioner according to the external input signal and the equipment operation signal.
2. The intelligent control system of a central air conditioner based on machine learning according to claim 1, wherein the monitoring information is stored by a history storage terminal and transmitted to an inertia analysis terminal, wherein the monitoring information comprises weather data and building monitoring information in a period time, the period time is a threshold value, the weather data comprises weather state and environmental temperature, and the building monitoring information refers to terminal temperature and flow in a target building.
3. The intelligent control system of a machine learning based central air conditioner of claim 2, wherein the weather data is collected by the environment collection module by collecting the predicted data of the weather station and transmitting it to the inertia analysis module.
4. The intelligent control system of a central air conditioner based on machine learning as claimed in claim 1, wherein the specific acquisition method of the temperature comparison table is as follows:
extracting monitoring information of the previous period, extracting working time of a target building from the monitoring information, and taking the working time as the time of a using area of a central air conditioner;
dividing the using area time into a plurality of area times according to unit time, wherein the unit time is a threshold value, and acquiring flow and meteorological data of each area time;
respectively taking the region time as a target region, and extracting region information of all the target regions in the period time, wherein the region information comprises the ambient temperature, the weather state, the flow and the optimal temperature;
and taking the environment temperature, the weather state and the flow as independent variables, taking the optimal temperature in the target building as the dependent variables, taking the data in the residual area information as an influence factor, constructing a machine learning model, and carrying out deep analysis on the optimal temperature in the target building to obtain a temperature comparison table.
5. The intelligent control system based on machine learning central air conditioner of claim 4, wherein the temperature comparison table is calculated by a fuzzy control algorithm in the machine learning algorithm, and the specific calculation process is as follows:
Firstly, setting the optimal temperatures corresponding to the ambient temperature, the weather state and the flow in different target areas;
then, the independent variable information is taken as input information, the dependent variable is taken as output information, and the method is based on Obtaining a minimum objective function Bm, namely an optimal temperature, wherein m represents the number of target areas in the period time, m is larger than 1, u ij represents the membership degree of a sample Xi belonging to j classes, xi represents the sample, cj represents a center cluster, i represents the measurement of the distance, and the membership degree is calculated by a membership degree function;
When (when) And when the iteration is ended, the optimal temperature setting method is ended, and then the setting method is used as a temperature comparison table and is transmitted to the integrated analysis module, k represents the iteration step number, and delta is a threshold value.
6. The intelligent control system of the central air conditioner based on machine learning as set forth in claim 1, wherein the method for obtaining the optimal temperature is as follows:
And taking the received real-time environment data and the flow in the target building at the moment as input information, respectively inputting the input information into a temperature comparison table, processing the input information according to a judgment rule in the temperature comparison table, finally outputting data, and taking the output data as the real-time optimal temperature of the target building.
7. The intelligent control system of a machine learning based central air conditioner of claim 1, wherein real-time environmental data and traffic are collected by a real-time detection module and transmitted to an integrated analysis module.
8. The intelligent control system of a central air conditioner based on machine learning as claimed in claim 1, wherein the method for obtaining the external input signal and the device operation signal comprises the following steps:
Extracting the environmental temperature HJ in the meteorological data, and simultaneously respectively acquiring the terminal temperature WZ and the optimal temperature WS in the target building;
Subtracting the optimal temperature WS from the terminal temperature WZ to obtain a building temperature difference WC, generating a cooling signal for a target building when the building temperature difference WC is a positive value, and generating a heating signal for the target building when the building temperature difference WC is a negative value;
When a heating signal or a cooling signal is generated, comparing the ambient temperature HJ with the optimal temperature WS, and subtracting the optimal temperature WS from the ambient temperature HJ to obtain an ambient temperature difference if the temperature in the target building is the heating signal at the moment, and subtracting the ambient temperature HJ from the optimal temperature to obtain the ambient temperature difference if the temperature in the target building is the cooling signal;
If the environmental temperature difference is greater than or equal to a1, generating an external input signal at the moment, otherwise, generating an equipment operation signal, wherein a1 is a threshold value, and a1 is more than 0;
When an external input signal is detected, the equipment set of the central air conditioner is started at the moment, the equipment set is enabled to enter a standby mode, then the disc fan set is used for controlling the optimal temperature in a target building by introducing external air, when an equipment operation signal is detected, the equipment set of the central air conditioner is started at the moment, the disc fan set is connected with the equipment set, the equipment set is used for controlling the temperature of cooling water, and the temperature in the target building is controlled.
9. The intelligent control system of a central air conditioner based on machine learning according to claim 1, further comprising a pre-adjustment module, wherein the pre-adjustment module is configured to pre-adjust the temperature in the target building, and the specific adjustment method is as follows:
Extracting an end point of the use area time, marking the starting time of the use area time as a front end time point, simultaneously acquiring the flow of the front end time point every day in the period time, and carrying out mean value processing on the flow to obtain a flow mean value of the front end time point;
The environmental collection module collects the meteorological data of the front end time point of the current day of the target building, takes the flow average value and the meteorological data of the front end time point of the current day as input information, and transmits the input information to the integrated analysis module for processing to obtain the optimal temperature of the front end time point;
And setting preset time, taking the front-end time point as a reference, detecting the terminal temperature of the target building at the front-end time point, transmitting the terminal temperature and the optimal temperature of the front-end time point to a temperature control module, and adjusting the temperature in the target building.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410155700.1A CN117989718A (en) | 2024-02-04 | 2024-02-04 | Central air conditioner intelligent control system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410155700.1A CN117989718A (en) | 2024-02-04 | 2024-02-04 | Central air conditioner intelligent control system based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117989718A true CN117989718A (en) | 2024-05-07 |
Family
ID=90901201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410155700.1A Pending CN117989718A (en) | 2024-02-04 | 2024-02-04 | Central air conditioner intelligent control system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117989718A (en) |
-
2024
- 2024-02-04 CN CN202410155700.1A patent/CN117989718A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107860102B (en) | Method and device for controlling central air conditioner | |
| CN104019526B (en) | Improve PSO algorithm Fuzzy Adaptive PID temperature and humidity control system and method | |
| CN101737899B (en) | Wireless sensor network-based central air-conditioning control system and method | |
| CN106258644B (en) | Temperature adjusting method and temperature adjusting device for crop greenhouse | |
| CN201666640U (en) | Control system of central air conditioner based on wireless sensor network | |
| CN113108432B (en) | Air conditioning system adjusting method and system based on weather forecast | |
| CN112611076B (en) | Subway station ventilation air conditioner energy-saving control system and method based on ISCS | |
| CN215724029U (en) | Central air conditioning adaptive control system | |
| CN114154677A (en) | Air conditioner operation load model construction and prediction method, device, equipment and medium | |
| CN115220351A (en) | Intelligent energy-saving optimization control method of building air conditioning system based on cloud side end | |
| CN114893871B (en) | High-efficiency control method and system for central air-conditioning refrigerating machine room | |
| CN114916209A (en) | System and method for realizing micro-module energy-saving control based on AI technology | |
| CN117989718A (en) | Central air conditioner intelligent control system based on machine learning | |
| CN112307675A (en) | Neural network-based temperature-sensitive load separation identification method and system | |
| CN111189201A (en) | Air conditioner prediction control method based on machine vision | |
| CN110762768A (en) | Energy efficiency ratio prediction method and device for refrigeration host of central air-conditioning system | |
| CN107883525A (en) | A kind of central air-conditioning intelligence energy-saving operation control system and method | |
| CN115413190A (en) | Data center temperature prediction control method | |
| CN114526537A (en) | Equipment energy-saving control method and device | |
| CN117408170B (en) | Energy-saving predictive control method suitable for water cooling system of data center | |
| CN110836518A (en) | System basic knowledge based global optimization control method for self-learning air conditioning system | |
| Chen et al. | Model Free Adaptive Control for Air-Conditioning System in Office Buildings Based on Improved NSGA-II Algorithm | |
| CN115978736B (en) | Self-adaptive prediction wind-water linkage control method for subway station air conditioning system | |
| CN114707711B (en) | Multi-time scale optimal scheduling method and system for park refrigerating unit | |
| CN117606109B (en) | Method and system for judging optimal temperature of air conditioner in machine room |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |