CN113970176B - Air conditioner heating control method, system and device based on frost inhibition neural network - Google Patents
Air conditioner heating control method, system and device based on frost inhibition neural network Download PDFInfo
- Publication number
- CN113970176B CN113970176B CN202111284047.1A CN202111284047A CN113970176B CN 113970176 B CN113970176 B CN 113970176B CN 202111284047 A CN202111284047 A CN 202111284047A CN 113970176 B CN113970176 B CN 113970176B
- Authority
- CN
- China
- Prior art keywords
- neural network
- information
- continuous heating
- frost
- 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.)
- Active
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- 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
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/41—Defrosting; Preventing freezing
- F24F11/42—Defrosting; Preventing freezing of outdoor units
-
- 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
- F24F11/50—Control or safety arrangements characterised by user interfaces or communication
- F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
-
- 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
-
- 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
- F24F2110/10—Temperature
- F24F2110/12—Temperature of the outside air
-
- 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
- F24F2110/22—Humidity of the outside air
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B30/00—Energy efficient heating, ventilation or air conditioning [HVAC]
- Y02B30/70—Efficient control or regulation technologies, e.g. for control of refrigerant flow, motor or heating
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Air Conditioning Control Device (AREA)
Abstract
An air conditioner heating control method based on a frost-inhibiting neural network comprises the following steps: acquiring operation condition information during heating operation of an air conditioner; inputting the operating condition information to calculate by a pre-trained neural network model, and outputting frequency amplitude reduction information and ideal continuous heating duration information; the frequency of the compressor is adjusted downwards according to the frequency amplitude reduction information to achieve frost suppression control, and the actual continuous heating duration before the defrosting control is executed is recorded; and according to the comparison between the ideal continuous heating time length information and the actual continuous heating time length, correcting frequency amplitude reduction information according to the comparison result and updating the training neural network model. The invention uses the neural network model to carry out the optimal frost suppression control during the heating period of the air conditioner and carries out the self-adaptive learning according to the actual use condition, thereby fully balancing the contradiction between the insufficient heating capacity caused by the unobvious frost suppression result when the frost suppression is too light and the insufficient heating capacity caused by the excessive frost suppression, ensuring the improvement of the final heating capacity and further improving the heating comfort of the air conditioner.
Description
Technical Field
The invention relates to the technical field of air conditioner frost inhibition and defrosting control, in particular to an air conditioner heating control method, system and device based on a frost inhibition neural network.
Background
When the air conditioner heats, the higher the output heat, the higher the required operation frequency, the lower the outer pipe temperature, and the more easily frosting is generated. In addition, in the heating process, the growth of the frost layer of the outdoor heat exchanger has the following rules: the thicker the frost layer, the faster the frost is formed and the greater the effect on the properties. Therefore, by reducing the heat output during heating, although the comfort in the room during normal operation is impaired, the frost formation is reduced, the frequency of defrosting is reduced, and the greater impairment of comfort due to frequent defrosting is avoided.
Patent CN109163411A provides a method for suppressing frost in the heating operation process and more accurately judging the defrosting time, wherein in the heating operation process, the dew point temperature is calculated in real time and compared with the real-time outer tube temperature, the defrosting control such as reducing the operation frequency and the like is carried out when frost is likely to occur, when the defrosting is judged to enter, the energy efficiency ratio is calculated in real time and compared with a preset value, and if the energy efficiency ratio is lower, the defrosting enters.
Patent CN111561761A provides a method for delaying frosting of an air conditioner, which judges by detecting the heating continuous operation time and the temperature of the inner pipe, if the output capacity is sufficient, the air conditioner enters into the frosting inhibition control, the low-frequency operation and the like are executed, the output capacity is reduced, and the frosting is delayed.
The patent CN111854056a also provides a method for delaying frosting of an air conditioner, which determines whether a condition for reducing energy is met or not according to the outdoor environment temperature, the temperature of an outer pipe and the operation frequency, and if the condition for reducing energy is met, enters a frost suppression mode to perform control such as frequency reduction and the like.
The three methods are all used for carrying out frost inhibition control in the heating process, but the frost inhibition time and the frost inhibition degree are simply determined according to preset values. Because the heating capacity is insufficient due to excessive frost inhibition, and the frost inhibition effect is poor due to insufficient frost inhibition, in a practical complex working condition, the best comfort improvement effect is often difficult to achieve, and even the situation that the comfort is reduced due to the reduction of the heating capacity caused by frost inhibition control may occur.
Disclosure of Invention
Aiming at the problems that the heating capacity is insufficient due to excessive frost inhibition and the frost inhibition effect is poor due to less frost inhibition, the invention provides the air conditioner heating control method, the air conditioner heating control system and the air conditioner heating control device based on the frost inhibition neural network, which can determine the optimal time and the frost inhibition degree for performing the frost inhibition according to the actual operation working condition and the heating state, and effectively ensure the optimal comfort.
In order to achieve the purpose, the invention adopts the following technical scheme: an air conditioner heating control method based on a frost-inhibiting neural network comprises the following steps:
acquiring operation condition information during heating operation of an air conditioner;
inputting the operation condition information to calculate by a pre-trained neural network model, and outputting frequency amplitude reduction information and ideal continuous heating duration information;
the frequency of the compressor is adjusted downwards according to the frequency amplitude reduction information to achieve frost suppression control, and the actual continuous heating time before the defrosting control is executed is recorded;
and according to the comparison between the ideal continuous heating time length information and the actual continuous heating time length, correcting frequency amplitude reduction information according to the comparison result and updating the training neural network model.
Preferably, the control method further includes:
when the defrosting control operation is executed, judging whether the defrosting control execution condition is met;
if so, executing defrosting control and recording the current actual continuous heating time;
if not, judging whether the outdoor working condition changes:
if the outdoor working condition is not changed, the obtained operating working condition information is basically consistent, and the original frost suppression control is maintained to be executed;
and if the outdoor working condition changes, acquiring the latest running working condition information, and acquiring the latest frequency amplitude reduction information through the neural network model so that the compressor executes frost suppression control according to the latest frequency amplitude reduction information.
Preferably, the control method further comprises:
executing defrosting control, and recording the current actual continuous heating time;
judging whether the outdoor working condition is changed or not:
if yes, obtaining the latest frequency amplitude reduction information, and not updating and training the neural network model;
and if not, correcting the frequency amplitude reduction information according to the comparison result of the ideal continuous heating time length information and the actual continuous heating time length and updating the training neural network model.
Preferably, the operation condition information includes a current outdoor condition, an indoor condition and an air conditioner operation condition, and the operation condition information obtained during heating operation of the air conditioner at least includes one of the following:
acquiring indoor environment temperature through a temperature sensing bulb connected with an inner machine mainboard;
acquiring outdoor environment temperature through an outer ring temperature sensing bulb connected with an outer machine mainboard;
and the outdoor environment humidity is obtained through an outer ring humidity sensor connected with an outer machine mainboard.
Preferably, the inputting the operating condition information to calculate with a pre-trained neural network model includes:
inputting outdoor environment temperature, outdoor environment humidity, compressor running frequency, temperature difference between indoor environment temperature and set target temperature and indoor temperature change speed to an input layer of the neural network model;
and the intermediate layer calculates to enable the output layer to output frequency reduction information and ideal continuous heating time length information.
Preferably, the step of establishing the neural network model comprises:
carrying out a large number of experiments through a laboratory, and testing to obtain different operation condition information of corresponding machine types;
recording the continuous heating time of the air conditioner and the average capacity in a complete period after the compressor selects different frequencies and reduces amplitude under the environment of different outdoor environment temperatures, different outdoor environment humidity, different compressor operation frequencies, different indoor environment temperatures, temperature difference between the set target temperature and the different indoor environment temperatures and different indoor temperature change speeds;
the frequency amplitude reduction amplitude with the highest average capacity under each working condition is selected as the optimal frequency amplitude reduction amplitude under the corresponding working condition, the continuous heating time corresponding to the optimal frequency amplitude reduction amplitude under the corresponding working condition is used as the ideal continuous heating time of the working condition, and frequency amplitude reduction information and ideal continuous heating time information under a plurality of different working conditions are obtained and used as original training data.
Preferably, the correcting the frequency drop information and updating the training neural network model according to the comparison result comprises:
comparing and judging the ideal continuous heating time length information and the actual continuous heating time length:
if the actual continuous heating time is longer than the ideal continuous heating time, the frost suppression effect is too large, and the frequency of the frequency amplitude reduction information is reduced and corrected;
if the actual continuous heating time length is less than the ideal continuous heating time length, the frost suppression effect is poor, and the frequency of the frequency amplitude reduction information is increased and corrected;
and acquiring correction frequency amplitude reduction information, and performing update training on the neural network model as new training data to enable the neural network model to be self-learning optimized.
In another aspect, an air conditioner heating control system based on a frost-inhibiting neural network includes:
the data acquisition unit is used for acquiring indoor working condition information, outdoor working condition information and working condition information of the operation of the air conditioning system;
the communication unit is used for carrying out communication transmission on the acquired data and the system execution instruction;
the neural network model is used for inputting the collected operation condition information into the neural network model trained in advance for calculation to obtain frequency amplitude reduction information and ideal continuous heating duration information;
the frost suppression control unit is used for controlling the frequency reduction operation of the compressor according to the frequency amplitude reduction information so as to perform frost suppression control;
the defrosting judgment unit is used for recording the actual continuous heating time;
and the correction updating unit is used for comparing the actual continuous heating time with the ideal continuous heating time according to the information, correcting the frequency amplitude reduction information according to the comparison result and updating the training neural network model.
Preferably, the neural network model adopts three to five layers of BP neural networks, and is provided with an input layer, a middle layer and an output layer;
the input layer is provided with 5 neurons which respectively correspond to five operation condition information inputs, the middle layer is provided with 5-10 neurons, and the output layer is provided with 2 neurons which respectively output frequency amplitude reduction information and ideal continuous heating time length information.
On the other hand, the air conditioning device based on the frost-inhibiting neural network comprises a processor and a memory, wherein the memory is used for storing an application program for executing the air conditioning heating control method based on the frost-inhibiting neural network;
the processor is configured to execute an application program stored in the memory.
Compared with the prior art, the invention has the following beneficial effects:
the invention uses the neural network model to carry out the optimal frost suppression control during the heating period of the air conditioner and carries out the self-adaptive learning according to the actual use condition, thereby fully balancing the contradiction between the insufficient heating capacity caused by the unobvious frost suppression result when the frost suppression is too light and the insufficient heating capacity caused by the excessive frost suppression, ensuring the improvement of the final heating capacity and further improving the heating comfort of the air conditioner. The method is distinguished from the traditional frost suppression control in that a simple partial parameter is selected to define an interval for control, the neural network is used for calculating whether frost suppression is performed or not and the frost suppression degree so as to accurately control, and the characteristics of the neural network are utilized to continuously update according to the actual running state, so that the final control effect is more suitable for the use condition of a user.
Drawings
In order to more clearly illustrate the technical solution, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a schematic flow chart of the present invention.
Fig. 2 is a schematic structural diagram of a neural network model.
Fig. 3 is a schematic diagram of a training and learning process of a neural network model.
Detailed Description
For a clear and complete understanding of the technical solutions, the present invention will now be further described with reference to the embodiments and the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, and all other embodiments obtained by those skilled in the art without any inventive work are within the scope of the present invention.
The first embodiment is as follows:
as shown in fig. 1, an air-conditioning heating control method based on a frost-suppressing neural network includes:
the method comprises the steps of obtaining operation condition information during heating operation of the air conditioner, wherein the operation condition information comprises current outdoor conditions, indoor conditions and air conditioner operation conditions, and the operation condition information during heating operation of the air conditioner at least comprises one of the following information: acquiring indoor environment temperature through a temperature sensing bulb connected with an inner machine mainboard; acquiring outdoor environment temperature through an outer ring temperature sensing bulb connected with an outer machine mainboard; and the outdoor environment humidity is obtained through an outer ring humidity sensor connected with an outer machine mainboard.
Inputting the operating condition information to calculate by a pre-trained neural network model, and outputting frequency amplitude reduction information and ideal continuous heating duration information;
specifically, the outdoor environment temperature, the outdoor environment humidity, the compressor running frequency, the temperature difference between the indoor environment temperature and the set target temperature and the indoor temperature change speed are input into an input layer of the neural network model, and the frequency reduction information and the ideal continuous heating duration information are output by an output layer through calculation of an intermediate layer;
the frequency of the compressor is adjusted downwards according to the frequency amplitude reduction information to achieve frost suppression control, and the actual continuous heating duration before the defrosting control is executed is recorded;
and according to the comparison between the ideal continuous heating time length information and the actual continuous heating time length, correcting frequency amplitude reduction information according to the comparison result and updating the training neural network model.
When the defrosting control operation is executed, judging whether the defrosting control execution condition is met;
if yes, executing defrosting control and recording the current actual continuous heating time;
if not, judging whether the outdoor working condition changes:
if the outdoor working condition is not changed, the obtained operating working condition information is basically consistent, and the original frost suppression control is maintained to be executed;
and if the outdoor working condition changes, acquiring the latest running working condition information, and acquiring the latest frequency amplitude reduction information through the neural network model so that the compressor executes frost suppression control according to the latest frequency amplitude reduction information.
Executing defrosting control, and recording the current actual continuous heating time;
judging whether the outdoor working condition is changed or not:
if yes, obtaining the latest frequency amplitude reduction information, and not updating and training the neural network model;
and if not, correcting the frequency amplitude reduction information according to the comparison result of the ideal continuous heating time length information and the actual continuous heating time length and updating the training neural network model.
After the air conditioner is started, acquiring operation condition information (outdoor temperature and humidity, compressor frequency, temperature difference between indoor temperature and target temperature and indoor temperature change speed) during heating operation of the air conditioner, and calculating according to the operation condition information to obtain frequency reduction amplitude of frost suppression control and ideal heating operation time. And reducing the frequency of the compressor according to the frequency amplitude reduction to perform frost suppression control, monitoring whether the outdoor working condition is changed or not in real time before defrosting is started, and if the outdoor working condition is not changed, maintaining the first-calculated frost suppression control (frequency amplitude reduction) until defrosting is started. When defrosting control is executed, updating data and training a neural network model according to the actual continuous heating duration; if the outdoor working condition is changed, after the outdoor working condition is changed, a new outdoor temperature and humidity are input into the neural network model for calculation, the frequency of the compressor, the indoor temperature difference and the indoor temperature change speed are still kept unchanged, the three values are fixed values during operation, the newly obtained result is used for frost suppression control, and in addition, if the working condition is changed in the same heating operation period, the newly obtained frequency amplitude reduction information is not used for updating the training neural network model.
As shown in fig. 2, the step of establishing the neural network model includes:
carrying out a large number of experiments through a laboratory, and testing to obtain different operation condition information of corresponding machine types;
recording the continuous heating time length of the air conditioner after the compressor selects different frequencies and reduces amplitude and the average capacity in a complete period under the environment of different outdoor environment temperatures, different outdoor environment humidity, different compressor operation frequencies, different temperature differences between the indoor environment temperatures and a set target temperature and different indoor temperature change speeds, wherein the continuous heating time length is the continuous time length from starting to defrosting, and the complete period is the time length from starting to restarting heating after defrosting is finished;
and selecting the frequency amplitude reduction with the highest average capability under each working condition as the optimal frequency amplitude reduction under the corresponding working condition, taking the continuous heating duration corresponding to the frequency amplitude reduction as the ideal continuous heating duration of the working condition, and acquiring frequency amplitude reduction information and ideal continuous heating duration information under a plurality of different working conditions as original training data.
The structure of the neural network is determined after the acquisition of the original training data is completed, because the calculation capacity of the air conditioner mainboard is limited, the embodiment adopts a BP neural network with three to five layers, the input layer is provided with 5 neurons and respectively corresponds to five operation condition information inputs (outdoor environment temperature, outdoor environment humidity, compressor operation frequency, temperature difference between indoor temperature and set target temperature and indoor temperature change speed), the middle layer can select 5 to 10 neurons, the output layer is provided with 2 neurons and respectively outputs frequency reduction amplitude information and ideal continuous heating duration information. The excitation function of the middle layer selects a positive sigmoid function and the excitation function of the middle layer selects a negative sigmoid function, and the output layer selects a non-negative sigmoid function. And training a neural network model by using the original data obtained by the experiment, and embedding the trained neural network model into an air conditioner mainboard. When the system runs, the neural network model calculates the frost suppression frequency reduction amplitude according to the relevant data during starting to carry out correction control on the compressor, and ideal continuous heating time length information is obtained.
As shown in fig. 3, in order to adapt the neural network model to the use conditions in different user's homes, it is necessary to provide the neural network model with the capability of self-learning optimization, and the correcting the frequency reduction information and updating the training neural network model according to the comparison result includes:
comparing and judging the ideal continuous heating time length information and the actual continuous heating time length:
if the actual continuous heating time is longer than the ideal continuous heating time, the frost suppression effect is too large, and the frequency of the frequency amplitude reduction information is reduced and corrected;
if the actual continuous heating time is shorter than the ideal continuous heating time, the frost inhibition effect is poor, and the frequency of the frequency amplitude reduction information is increased and corrected;
and acquiring correction frequency amplitude reduction information, and performing update training on the neural network model as new training data to enable the neural network model to be self-learning optimized.
After obtaining the frost suppression frequency amplitude reduction under the corresponding working condition to perform frost suppression control on the air conditioner, recording the actual continuous heating time t a (unit min) and the ideal continuous heating time t under the working condition output by the neural network model 0 (unit min) and if the actual duration t of the continuous heating is the same a Duration t longer than ideal continuous heating 0 If the capacity loss is too large, the capacity loss caused by capacity reduction during heating is too large, and the frequency reduction amplitude is reduced; and vice versa. When the amplitude reduction correction is performed on the frequency amplitude reduction, the correction amount is expressed as a x (t) a -t 0 ) The correction amount is rounded upwards, the maximum value is 5Hz, the value of a is-0.05 to-0.2, if the original frost suppression frequency is reduced by 5Hz when a is-0.1, and the actual continuous heating time is 15min longer than the ideal continuous heating time, the correction amount is-2 Hz (the correction amount is rounded upwards after-0.1 × 15= -1.5 is calculated, namely-2), and the new frost suppression frequency is reduced by the maximum value of 5Hz, the value of a is-0.05 to-0.2The correction is 5+ (-2) =3Hz. And after the new frequency amplitude reduction is obtained, the new frequency amplitude reduction information is used as new training data to carry out updating training on the neural network model, so that self-learning optimization is realized.
The second embodiment:
an air conditioner heating control system based on a frost-inhibiting neural network comprises:
the data acquisition unit is used for acquiring indoor working condition information, outdoor working condition information and working condition information of the operation of the air conditioning system, and specifically comprises outdoor environment temperature, outdoor environment humidity, compressor operation frequency, temperature difference between the indoor environment temperature and a set target temperature and indoor temperature change speed;
the communication unit is used for carrying out communication transmission on the acquired data and the system execution instruction;
the neural network model is used for inputting the collected operation condition information into the neural network model trained in advance for calculation to obtain frequency amplitude reduction information and ideal continuous heating duration information; specifically, five parameters of the operating outdoor environment temperature, the operating outdoor environment humidity, the compressor operating frequency, the temperature difference between the indoor environment temperature and the set target temperature and the indoor temperature change speed are input into a preset neural network model, and the neural network model outputs frequency amplitude reduction information of frost suppression control and ideal continuous heating duration information.
And the frost suppression control unit is used for controlling the compressor frequency reduction operation according to the frequency amplitude reduction information to perform frost suppression control, and the outer pipe Wen Huiyou rises due to the reduction of the frequency of the compressor, so that a frost layer is more difficult to form, and the frost suppression control is realized.
And the defrosting judgment unit is used for recording the actual continuous heating time, and the actual continuous heating time is the time from the starting heating operation to the defrosting control execution.
And the correction updating unit is used for comparing the actual continuous heating time with the ideal continuous heating time according to the information, correcting the frequency amplitude reduction information according to the comparison result and updating the training neural network model.
The embodiment uses the neural network model to perform optimal frost suppression control during the heating period of the air conditioner, and performs adaptive learning according to the actual use condition, thereby fully balancing the contradiction between unobvious frost suppression result if the frost suppression is too light and insufficient heating capacity if the frost suppression is too heavy, ensuring to improve the final heating capacity, and improving the heating comfort of the air conditioner.
The embodiment also provides another technical scheme, and the air conditioning device based on the frost-inhibiting neural network comprises a processor and a memory, wherein the memory is used for storing an application program for executing the air conditioning heating control method based on the frost-inhibiting neural network;
the processor is configured to execute an application program stored in the memory.
The above disclosure is intended to be illustrative of one or more of the preferred embodiments of the present invention and is not intended to limit the invention in any way, which is equivalent or conventional to one skilled in the art and which is intended to cover all modifications, equivalents, and alternatives falling within the scope of the invention as defined by the appended claims.
Claims (10)
1. An air conditioner heating control method based on a frost-inhibiting neural network is characterized by comprising the following steps:
acquiring operation condition information during heating operation of an air conditioner;
inputting the operating condition information to calculate by a pre-trained neural network model, and outputting frequency amplitude reduction information and ideal continuous heating duration information;
the frequency of the compressor is adjusted downwards according to the frequency amplitude reduction information so as to achieve the purpose of performing frost suppression control in the heating process, and whether the defrosting control execution condition is met or not is judged when the defrosting control execution is performed; if so, executing defrosting control and recording the current actual continuous heating time;
and according to the comparison between the ideal continuous heating time length information and the actual continuous heating time length, correcting frequency amplitude reduction information according to the comparison result and updating the training neural network model.
2. The air conditioner heating control method based on the frost-suppressing neural network as claimed in claim 1, wherein the control method further comprises:
when the defrosting control operation is executed, judging whether the defrosting control execution condition is met;
if yes, executing defrosting control and recording the current actual continuous heating time;
if not, judging whether the outdoor working condition changes:
if the outdoor working condition is not changed, the obtained operating working condition information is basically consistent, and the original frost suppression control is maintained to be executed;
and if the outdoor working condition changes, acquiring the latest running working condition information, and acquiring the latest frequency amplitude reduction information through the neural network model so that the compressor executes frost suppression control according to the latest frequency amplitude reduction information.
3. The air conditioner heating control method based on the frost-inhibiting neural network as claimed in claim 2, wherein the control method further comprises:
executing defrosting control, and recording the current actual continuous heating time;
judging whether the outdoor working condition is changed or not:
if yes, obtaining the latest frequency amplitude reduction information, and not updating and training the neural network model;
and if not, correcting the frequency amplitude reduction information according to the comparison result of the ideal continuous heating time length information and the actual continuous heating time length and updating the training neural network model.
4. The air conditioner heating control method based on the frost-inhibiting neural network as claimed in claim 1, wherein: the operation condition information comprises the current outdoor condition, the current indoor condition and the current air conditioner operation condition, and the operation condition information obtained when the air conditioner heats at least comprises one of the following information:
acquiring indoor environment temperature through a temperature sensing bulb connected with an inner machine mainboard;
acquiring outdoor environment temperature through an outer ring temperature sensing bulb connected with an outer machine mainboard;
and the outdoor environment humidity is obtained through an outer ring humidity sensor connected with an outer machine mainboard.
5. The air conditioner heating control method based on the frost-inhibiting neural network as claimed in claim 1, wherein the inputting the operation condition information to calculate with a pre-trained neural network model comprises:
inputting outdoor environment temperature, outdoor environment humidity, compressor running frequency, temperature difference between indoor environment temperature and set target temperature and indoor temperature change speed to an input layer of the neural network model;
and outputting frequency reduction information and ideal continuous heating time length information by the intermediate layer through calculation.
6. The air conditioner heating control method based on the frost-inhibiting neural network as claimed in claim 5, wherein the establishing step of the neural network model comprises:
carrying out a large number of experiments through a laboratory, and testing to obtain different operation condition information of corresponding machine types;
recording the continuous heating duration and the average capacity in a complete period of the air conditioner after the compressor selects different frequencies and reduces amplitudes in the environment of different outdoor environment temperatures, different outdoor environment humidity, different compressor operation frequencies, different temperature differences between the indoor environment temperatures and a set target temperature and different indoor temperature change speeds;
and selecting the frequency amplitude reduction with the highest average capability under each working condition as the optimal frequency amplitude reduction under the corresponding working condition, taking the continuous heating duration corresponding to the frequency amplitude reduction as the ideal continuous heating duration of the working condition, and acquiring frequency amplitude reduction information and ideal continuous heating duration information under a plurality of different working conditions as original training data.
7. The air conditioner heating control method based on the frost-inhibiting neural network as claimed in claim 1, wherein: the step of correcting the frequency reduction information and updating the training neural network model according to the comparison result comprises the following steps:
comparing and judging the ideal continuous heating time length information and the actual continuous heating time length:
if the actual continuous heating time is longer than the ideal continuous heating time, the frost suppression effect is too large, and the frequency of the frequency amplitude reduction information is reduced and corrected;
if the actual continuous heating time length is less than the ideal continuous heating time length, the frost suppression effect is poor, and the frequency of the frequency amplitude reduction information is increased and corrected;
and acquiring correction frequency amplitude reduction information, and performing update training on the neural network model as new training data to enable the neural network model to be self-learning optimized.
8. An air conditioner heating control system based on restrain white neural network, its characterized in that includes:
the data acquisition unit is used for acquiring indoor working condition information, outdoor working condition information and working condition information of the operation of the air conditioning system;
the communication unit is used for carrying out communication transmission on the acquired data and the system execution instruction;
the neural network model is used for inputting the collected operation condition information into the neural network model trained in advance for calculation to obtain frequency amplitude reduction information and ideal continuous heating duration information;
the frost suppression control unit is used for adjusting the frequency of the compressor according to the frequency amplitude reduction information so as to achieve frost suppression control in the heating process;
a defrosting judgment unit for judging whether the defrosting execution control condition is satisfied when the defrosting inhibition control operation is executed; if yes, executing defrosting control and recording the current actual continuous heating time;
and the correction updating unit is used for comparing the actual continuous heating time with the ideal continuous heating time according to the information, correcting the frequency amplitude reduction information according to the comparison result and updating the training neural network model.
9. An air conditioner heating control system based on a frost-inhibiting neural network as claimed in claim 8, wherein: the neural network model adopts three to five layers of BP neural networks and is provided with an input layer, a middle layer and an output layer;
the input layer is provided with 5 neurons which respectively correspond to five operation condition information inputs, the middle layer is provided with 5-10 neurons, and the output layer is provided with 2 neurons which respectively output frequency reduction information and ideal continuous heating time length information.
10. An air conditioning device based on a frost-inhibiting neural network comprises a processor and a memory, and is characterized in that:
the memory is used for storing an application program for executing the frosting inhibition neural network-based air conditioner heating control method of any one of claims 1 to 7;
the processor is configured to execute an application program stored in the memory.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111284047.1A CN113970176B (en) | 2021-11-01 | 2021-11-01 | Air conditioner heating control method, system and device based on frost inhibition neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111284047.1A CN113970176B (en) | 2021-11-01 | 2021-11-01 | Air conditioner heating control method, system and device based on frost inhibition neural network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113970176A CN113970176A (en) | 2022-01-25 |
CN113970176B true CN113970176B (en) | 2022-10-21 |
Family
ID=79589192
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111284047.1A Active CN113970176B (en) | 2021-11-01 | 2021-11-01 | Air conditioner heating control method, system and device based on frost inhibition neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113970176B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH037853A (en) * | 1989-06-05 | 1991-01-16 | Toshiba Corp | Air conditioner |
CN111141007A (en) * | 2019-12-30 | 2020-05-12 | 宁波奥克斯电气股份有限公司 | Control method and control system for regulating frosting of air conditioner and air conditioner |
CN112032929A (en) * | 2020-08-31 | 2020-12-04 | 珠海格力电器股份有限公司 | Air conditioner defrosting control method and device |
CN112503725A (en) * | 2020-12-08 | 2021-03-16 | 珠海格力电器股份有限公司 | Air conditioner self-cleaning control method and device and air conditioner |
CN112628942A (en) * | 2020-12-11 | 2021-04-09 | 珠海格力电器股份有限公司 | Defrosting control method and device, storage medium and terminal |
CN113566383A (en) * | 2021-07-20 | 2021-10-29 | 珠海格力电器股份有限公司 | Intelligent defrosting method and device, electric appliance and computer readable storage medium |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110701659B (en) * | 2019-10-14 | 2020-11-27 | 北京工业大学 | Air source heat pump central heating system group control method based on load matching and frost inhibition multiple targets |
-
2021
- 2021-11-01 CN CN202111284047.1A patent/CN113970176B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH037853A (en) * | 1989-06-05 | 1991-01-16 | Toshiba Corp | Air conditioner |
CN111141007A (en) * | 2019-12-30 | 2020-05-12 | 宁波奥克斯电气股份有限公司 | Control method and control system for regulating frosting of air conditioner and air conditioner |
CN112032929A (en) * | 2020-08-31 | 2020-12-04 | 珠海格力电器股份有限公司 | Air conditioner defrosting control method and device |
CN112503725A (en) * | 2020-12-08 | 2021-03-16 | 珠海格力电器股份有限公司 | Air conditioner self-cleaning control method and device and air conditioner |
CN112628942A (en) * | 2020-12-11 | 2021-04-09 | 珠海格力电器股份有限公司 | Defrosting control method and device, storage medium and terminal |
CN113566383A (en) * | 2021-07-20 | 2021-10-29 | 珠海格力电器股份有限公司 | Intelligent defrosting method and device, electric appliance and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN113970176A (en) | 2022-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102353119B (en) | Control method of VAV (variable air volume) air-conditioning system | |
CN107621048B (en) | Control method and device of air conditioner | |
CN110701756B (en) | Operation control method, operation control device, air conditioner, and storage medium | |
CN110836509A (en) | Household equipment control method and device, control equipment and readable storage medium | |
CN110456647A (en) | A kind of intelligent home furnishing control method and intelligent home control device | |
CN109827292A (en) | Construction method, control method, the household electrical appliances of household electrical appliances adaptive power conservation Controlling model | |
CN107084477A (en) | Air conditioner heating operation controlling method | |
CN107084479A (en) | A kind of air conditioner heating operation controlling method | |
CN106123207A (en) | The control method of new blower fan and control device | |
CN1098186A (en) | The control device of air conditioner | |
CN110836515A (en) | Household equipment control method and device, control equipment and readable storage medium | |
CN108626855B (en) | Energy-saving comfort control method for variable frequency air conditioning system | |
CN107166649A (en) | Control method, control device and the air conditioner of independent assortment one-driving-one air conditioner | |
CN112963946A (en) | Heating, ventilating and air conditioning system control method and device for shared office area | |
CN110057054A (en) | A kind of control method of air-conditioning, device, storage medium and air-conditioning | |
CN107192083A (en) | Air-conditioner control method | |
CN112923480A (en) | Fresh air system control method and device and fresh air conditioner | |
CN106707999B (en) | Building energy-saving system based on adaptive controller, control method and simulation | |
CN113970176B (en) | Air conditioner heating control method, system and device based on frost inhibition neural network | |
CN113566383B (en) | Intelligent defrosting method and device, electric appliance and computer readable storage medium | |
CN109084425A (en) | Air conditioner and its control method and computer readable storage medium | |
CN107246710A (en) | The control method and device of indoor sleep temperature | |
CN111412635A (en) | Control method and device of air conditioner, storage medium and air conditioner | |
CN116307440A (en) | Workshop scheduling method based on reinforcement learning and multi-objective weight learning, device and application thereof | |
CN114623568B (en) | Control method and device of air conditioner, electronic equipment and storage medium |
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 |