Energy-saving control method and device of non-intrusive sensor central air conditioning system

Abstract

The application discloses an energy-saving control method and device for a non-invasive sensor central air conditioning system, and relates to the fields of energy-saving control methods and devices for non-invasive sensor central air conditioning systems. The method comprises the following steps: acquiring environmental conditions and relative position relationships of each terminal air conditioning area; acquiring data collected by terminal sensors; determining target minimum energy consumption through an air conditioning system energy efficiency prediction model according to the environmental conditions, the relative position relationships and the collected data; acquiring historical operation power of the central air conditioning system and refrigerating capacity of terminal air conditioning equipment according to historical operation data; training a neural network model by taking the historical operation power as input and the refrigerating capacity as output, and acquiring a target energy-saving refrigeration model; and taking the target minimum energy consumption as input of the target energy-saving refrigeration model, and acquiring target refrigerating capacity of each terminal air conditioning equipment according to output of the target refrigeration model. The energy consumption data can be monitored and analyzed and controlled in an all-round way, the energy-saving strategy of the air conditioner can be effectively controlled, and the energy-saving control of the air conditioner can be maximally realized.

Description

Technical Field

[0001] The present invention relates to the technical field of air-conditioning control, and in particular to an energy-saving control method and device for a non-intrusive sensor central air-conditioning system. Background Art

[0002] With the development of contemporary society and the ever-changing living environment, non-renewable resources are being continuously consumed, and the living environment is being progressively destroyed. The energy situation is becoming increasingly tense. Therefore, promoting environmental protection and energy conservation and emission reduction is of paramount importance, and building energy conservation has become a particularly essential social choice. In recent years, with the advancement of science and technology, emerging non-intrusive measurement IoT technologies have emerged internationally. These technologies are now mature and applicable. These non-intrusive measurement IoT technologies can further enhance the information analysis and mining capabilities of smart grids, as well as their data sharing and interaction capabilities. They enable non-intrusive energy load detection, thereby controlling the on / off switching of grid energy. Currently, there are intelligent air conditioning control systems based on non-intrusive measurement. These systems utilize non-intrusive measurement modules, edge computing processing, air conditioning control modules, and cloud platforms, using measured data to control air conditioning systems. There are also control systems that utilize non-intrusive load identification, primarily using data acquisition units and control processing units to collect information and, critically, energy meters, to identify loads. There are also intelligent non-intrusive load identification systems, which primarily include non-intrusive data acquisition modules. The above-mentioned related technologies are all based on non-invasive data acquisition equipment to judge the data and then control the relevant air-conditioning equipment.

[0003] However, the current existing technologies are all based on non-invasive measurement equipment for subsequent control, giving priority to collecting relevant measurement data, then analyzing the measurement data, and feeding back the analysis results to the user terminal device (mobile phone and computer). After receiving the information, the user remotely controls the air-conditioning equipment through the terminal device (mobile phone and computer). This control method is actually no different from the user being on site, sensing the temperature through body temperature and controlling it through a remote control. It just has an additional data measurement, but does not achieve fully automatic intelligent control, nor does it effectively control and adjust the energy consumed by the air-conditioning system.

[0004] Therefore, those skilled in the art are in urgent need of developing a new technical solution to solve the above problems. Summary of the Invention

[0005] In order to overcome the problems existing in the related art, the present invention discloses an energy-saving control method and device for a central air-conditioning system using a non-intrusive sensor.

[0006] According to a first aspect of the disclosed embodiments of the present invention, there is provided a method for energy-saving control of a non-intrusive sensor central air-conditioning system, the method comprising:

[0007] Obtaining environmental conditions of each terminal air-conditioning area of ​​the central air-conditioning system and relative positional relationships between the terminal air-conditioning areas, wherein the terminal air-conditioning areas include industrial parks, residential areas, and commercial areas;

[0008] Acquire data collected by various terminal sensors in each terminal air-conditioning area, wherein the terminal sensors include: temperature sensors, pressure sensors, differential pressure sensors, liquid level sensors, carbon dioxide sensors, and carbon monoxide sensors;

[0009] Determining the target minimum energy consumption of the central air-conditioning system through a preset air-conditioning system energy efficiency prediction model based on the environmental conditions of the terminal air-conditioning areas, the relative positional relationships between the terminal air-conditioning areas, and the data collected by the terminal sensors;

[0010] Obtaining the historical operating power of the central air-conditioning system and the corresponding cooling capacity of the terminal air-conditioning equipment based on the historical operating data of the air-conditioning;

[0011] Taking the historical operating power of the central air-conditioning system as input and the cooling capacity of the corresponding terminal air-conditioning equipment as output, a preset neural network model is trained to obtain a trained target energy-saving cooling model;

[0012] The target minimum energy consumption is used as the input of the target energy-saving refrigeration model, and the target cooling capacity of each terminal air-conditioning device in the central air-conditioning system is obtained according to the output of the target refrigeration model to achieve energy-saving control of the central air-conditioning system.

[0013] Optionally, the obtaining of the environmental conditions of each terminal air-conditioning area of ​​the central air-conditioning system and the relative positional relationship between each terminal air-conditioning area includes:

[0014] Determine the area type of each terminal air-conditioning area;

[0015] Obtain the regular personnel density in the terminal air-conditioning area according to the area type;

[0016] Obtain the positional relationship between each terminal air-conditioning area;

[0017] According to the positional relationship between each terminal air-conditioned area and the conventional personnel density, the changing trend of the conventional personnel density between each terminal air-conditioned area is determined.

[0018] Optionally, the method further includes:

[0019] Determine an input data set and an output data set for training a neural network model to obtain an air conditioning system energy efficiency prediction model, wherein the input data set includes environmental conditions of a certain number of air-conditioned areas, relative positional relationships between terminal air-conditioned areas, and data collected by terminal sensors, and the output data set includes minimum power consumption operation data of the corresponding certain number of air-conditioned areas;

[0020] Splitting the input data set and the corresponding output data set into a training set and a test set according to a first preset ratio;

[0021] The neural network model is trained using the input and output data sets in the training set, wherein the neural network algorithm consists of at least three layers of networks, namely, an input layer, a hidden layer, and an output layer. The expression of the neural network model is y(t) = f(x(t-1), ..., x(t-dx), y(t-1), y(t-2), ..., y(t-dy)), where x(t) represents input, y(t) represents output, dx represents input delay, and dy represents output delay;

[0022] The training results of the neural network model are tested using the input and output data sets in the test set. When the test error is less than the preset error threshold, the training is stopped and the trained air-conditioning system energy efficiency prediction model is obtained.

[0023] Optionally, the acquiring of data collected by each terminal sensor in each terminal air-conditioning area includes:

[0024] Collecting temperature data in the terminal air-conditioning area through a temperature sensor;

[0025] The static pressure of the air duct in the terminal air conditioning area is collected by a pressure sensor;

[0026] The pressure difference in the pipeline of the terminal air-conditioning area is collected by a pressure difference sensor;

[0027] Collect the liquid level data of the water tank through the liquid level sensor;

[0028] The carbon dioxide concentration in the terminal air-conditioning area is collected through a carbon dioxide sensor;

[0029] The carbon monoxide concentration in the terminal air-conditioned area is collected by the carbon monoxide sensor.

[0030] Optionally, the method of using the historical operating power of the central air-conditioning system as input and the cooling capacity of the corresponding terminal air-conditioning equipment as output to train a preset neural network model to obtain a trained target energy-saving cooling model includes:

[0031] Splitting the historical operating power according to a second preset ratio to obtain a first split data set accounting for 20% and a second split data set accounting for 80%;

[0032] Correcting the first segmented data set using a preset data correction strategy to obtain a first corrected data set;

[0033] Mixing the first corrected dataset and the second segmented dataset using a preset data mixing strategy to obtain a first mixed dataset;

[0034] The cooling capacity of the terminal air conditioner corresponding to the historical operating power is divided according to a third preset ratio to obtain a third divided data set accounting for 10% and a fourth divided data set accounting for 90%;

[0035] Correcting the third segmented data set using the data correction strategy to obtain a second corrected data set;

[0036] Mixing the second corrected dataset and the fourth segmented dataset using the data mixing strategy to obtain a second mixed dataset;

[0037] The first mixed data set is used as input and the second mixed data set is used as output to train a preset neural network model to obtain a trained target energy-saving refrigeration model.

[0038] Optionally, the method further includes:

[0039] The historical operating power P0 = qm(h2-h1), where qm is the mass flow rate of the refrigerant and the enthalpy difference (h2-h1) is the work consumed by the compressor to compress and transport 1 kg of refrigerant;

[0040] The cooling capacity Q0 = qm(h1-h4), where the enthalpy difference (h1-h4) is the unit cooling capacity;

[0041] Calculate the energy efficiency ratio in the historical operating data based on the historical operating power and cooling capacity

[0042] The historical operating power and cooling capacity whose energy efficiency ratio is greater than a preset energy efficiency ratio threshold are used to train the neural network model to obtain a trained target energy-saving cooling model.

[0043] According to a second aspect of the disclosed embodiments of the present invention, there is provided a non-intrusive sensor energy-saving control device for a central air-conditioning system, the device comprising:

[0044] An environmental condition acquisition module is configured to acquire the environmental conditions of each terminal air-conditioning area of ​​the central air-conditioning system and the relative positional relationship between the terminal air-conditioning areas, wherein the terminal air-conditioning areas include industrial parks, residential areas, and commercial areas;

[0045] a sensor data acquisition module connected to the environmental condition acquisition module to acquire data collected by various terminal sensors in each terminal air-conditioning area, wherein the terminal sensors include: a temperature sensor, a pressure sensor, a differential pressure sensor, a liquid level sensor, a carbon dioxide sensor, and a carbon monoxide sensor;

[0046] a target minimum energy consumption acquisition module, connected to the sensor data acquisition module, and determining the target minimum energy consumption of the central air-conditioning system through a preset air-conditioning system energy efficiency prediction model based on the environmental conditions of the terminal air-conditioning areas, the relative positional relationships between the terminal air-conditioning areas, and the data collected by the terminal sensors;

[0047] A historical operation data acquisition module is connected to the target minimum energy consumption acquisition module, and acquires the historical operation power of the central air-conditioning system and the cooling capacity of the corresponding terminal air-conditioning equipment based on the historical operation data of the air-conditioning;

[0048] a target energy-saving refrigeration model acquisition module, connected to the historical operation data acquisition module, taking the historical operating power of the central air-conditioning system as input and the cooling capacity of the corresponding terminal air-conditioning equipment as output, training a preset neural network model to obtain a trained target energy-saving refrigeration model;

[0049] The energy-saving control module is connected to the target energy-saving refrigeration model acquisition module, takes the target minimum energy consumption as the input of the target energy-saving refrigeration model, and obtains the target cooling capacity of each terminal air-conditioning equipment in the central air-conditioning system according to the output of the target refrigeration model to achieve energy-saving control of the central air-conditioning system.

[0050] Optionally, the environmental status acquisition module includes:

[0051] An area type determination unit, which determines the area type of each terminal air-conditioning area;

[0052] a personnel density acquisition unit, connected to the area type determination unit, for acquiring a regular personnel density in the terminal air-conditioning area according to the area type;

[0053] A position determination unit relationship is connected to the personnel density acquisition unit to obtain the position relationship between each terminal air-conditioning area;

[0054] The change trend acquisition unit is connected with the position relationship determination unit, and determines a change trend of the regular personnel density between the terminal air conditioning areas according to the position relationship between the terminal air conditioning areas and the regular personnel density.

[0055] Optionally, the sensor data acquisition module comprises:

[0056] The temperature data acquisition unit acquires temperature data in the terminal air conditioning area through a temperature sensor.

[0057] The duct static pressure acquisition unit is connected with the temperature data acquisition unit, and acquires duct static pressure in the pipeline in the terminal air conditioning area through a pressure sensor.

[0058] The differential pressure acquisition unit is connected with the duct static pressure acquisition unit, and acquires a differential pressure in the pipeline in the terminal air conditioning area through a differential pressure sensor.

[0059] The liquid level data acquisition unit is connected with the differential pressure acquisition unit, and acquires liquid level data of a water tank through a liquid level sensor.

[0060] The carbon dioxide concentration acquisition unit is connected with the liquid level data acquisition unit, and acquires carbon dioxide concentration in the terminal air conditioning area through a carbon dioxide sensor.

[0061] The carbon monoxide concentration acquisition unit is connected with the carbon dioxide concentration acquisition unit, and acquires carbon monoxide concentration in the terminal air conditioning area through a carbon monoxide sensor.

[0062] Optionally, the target energy-saving refrigeration model acquisition module comprises:

[0063] The first splitting unit splits the historical operation power according to a second preset proportion, to acquire a first split data set with a proportion of 20% and a second split data set with a proportion of 80%.

[0064] The first correction data acquisition unit is connected with the first splitting unit, and corrects the first split data set through a preset data correction strategy, to acquire a first correction data set.

[0065] The first mixed data acquisition unit is connected with the first correction data acquisition unit, and mixes the first correction data set and the second split data set through a preset data mixing strategy, to acquire a first mixed data set.

[0066] The second splitting unit is connected with the first mixed data acquisition unit, splits terminal air conditioning refrigeration capacity corresponding to the historical operation power according to a third preset proportion, to acquire a third split data set with a proportion of 10% and a fourth split data set with a proportion of 90%.

[0067] a second corrected data acquisition unit, connected to the second segmentation unit, for correcting the third segmented data set using the data correction strategy to obtain a second corrected data set;

[0068] a second mixed data acquisition unit, connected to the second corrected data acquisition unit, for mixing the second corrected data set and the fourth segmented data set using the data mixing strategy to obtain a second mixed data set;

[0069] The target energy-saving refrigeration model acquisition unit is connected to the second mixed data acquisition unit, takes the first mixed data set as input and the second mixed data set as output, trains the preset neural network model, and obtains the trained target energy-saving refrigeration model.

[0070] In summary, the present invention discloses an energy-saving control method and device for a non-invasive sensor central air-conditioning system, which includes: obtaining the environmental conditions and relative positional relationships of each terminal air-conditioning area; obtaining data collected by the terminal sensor; determining the target minimum energy consumption through the air-conditioning system energy efficiency prediction model based on the environmental conditions, relative positional relationships, and collected data; obtaining the historical operating power of the central air-conditioning system and the cooling capacity of the terminal air-conditioning equipment based on historical operating data; using the historical operating power as input and the cooling capacity as output to train a neural network model to obtain a target energy-saving cooling model; using the target minimum energy consumption as input to the target energy-saving cooling model, and obtaining the target cooling capacity of each terminal air-conditioning equipment based on the output of the target cooling model. The method can fully monitor energy consumption data, perform analysis and control, effectively control the energy-saving strategy of the air-conditioning, and achieve energy-saving control of the air-conditioning to the greatest extent.

[0071] Other features and advantages disclosed in the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:

[0073] Figure 1 is a flow chart showing an energy-saving control method for a non-intrusive sensor central air-conditioning system according to an exemplary embodiment;

[0074] Figure 2 is based on Figure 1 A flow chart of a method for obtaining environmental conditions is shown;

[0075] Figure 3 is based on Figure 1 A flow chart of a sensor data acquisition method is shown;

[0076] Figure 4 is according to Figure 1 a flow chart of a target energy-saving refrigeration model acquisition method is shown;

[0077] Figure 5 is a structural block diagram of an energy-saving control device of a non-intrusive sensor central air conditioning system according to an exemplary embodiment;

[0078] Figure 6 is according to Figure 5 a structural block diagram of an environment condition acquisition module is shown;

[0079] Figure 7 is according to Figure 5 a structural block diagram of a sensor data acquisition module is shown;

[0080] Figure 8 is according to Figure 5 a structural block diagram of a target energy-saving refrigeration model acquisition module is shown. DETAILED DESCRIPTION

[0081] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure.

[0082] Figure 1 is a flow chart of an energy-saving control method of a non-intrusive sensor central air conditioning system according to an exemplary embodiment, as shown in Figure 1 , the method comprises:

[0083] In step 101, the environment conditions of each terminal air conditioning area of the central air conditioning system and the relative position relationship between each terminal air conditioning area are acquired.

[0084] The terminal air conditioning area includes an industrial park, a residential area and a commercial area.

[0085] For example, the central air conditioning system in the disclosed embodiment comprises various sensors and terminal air conditioning equipment in each terminal air conditioning area. Through the central control device of the central air conditioning system, the refrigeration capacity of the terminal air conditioning equipment is adjusted according to the data collected by the various sensors and the environment conditions of each terminal air conditioning area, so that the running energy consumption of the entire system is reduced without changing the refrigeration efficiency in the central air conditioning area, thereby achieving the purpose of saving energy.

[0086] Specifically, Figure 2 is according to Figure 1 a flow chart of an environment condition acquisition method is shown, as shown in Figure 2 , step 101 comprises:

[0087] In step 1011, the area type of each terminal air-conditioning area is determined.

[0088] For example, terminal air-conditioning areas include industrial parks, residential areas and commercial areas. Different types of terminal air-conditioning areas have different demands for cooling capacity. Therefore, different cooling solutions can be adopted according to the characteristics of different types of terminal air-conditioning areas.

[0089] In step 1012, the normal population density of the terminal air-conditioning area is obtained according to the area type.

[0090] For example, the regular population density in the terminal air-conditioning area affects the demand for cooling capacity. It can be understood that the greater the regular population density, the greater the concentration of carbon dioxide exhaled by the people, and the greater the demand for cooling capacity in the air-conditioning terminal area.

[0091] In addition, the regular population density in different terminal air-conditioning areas can be obtained based on the average population density of activities in industrial parks, residential areas and commercial areas collected in the past, or it can be obtained based on the average population density of activities in the terminal air-conditioning area that currently requires energy-saving control calculations within 30 days.

[0092] In step 1013, the positional relationship between each terminal air-conditioning area is obtained.

[0093] In step 1014, based on the positional relationship between the terminal air-conditioning areas and the regular population density, the changing trend of the regular population density between the terminal air-conditioning areas is determined.

[0094] For example, in the disclosed embodiments of the present invention, a central air conditioning system includes at least one of an industrial park, a residential area, and a commercial area. The location of the terminal air conditioning areas affects the cooling capacity required by each terminal air conditioning area. Therefore, when calculating the power consumption within the central air conditioning system, it is necessary to consider these location relationships and the changing trend of the typical occupancy density.

[0095] For example, industrial parks are located south of residential areas, and commercial areas are located south of residential areas. The population density between industrial parks, residential areas, and commercial areas is increasing. Based on local climate characteristics and air flow principles, a higher cooling capacity is provided to the terminal air-conditioning areas with higher population densities and located upstream of the air flow. This allows the cool air to flow to other areas according to air flow principles, achieving energy conservation and emission reduction goals.

[0096] In step 102, data collected by each terminal sensor in each terminal air-conditioning area is obtained.

[0097] Among them, the terminal sensor includes: a temperature sensor, a pressure sensor, a differential pressure sensor, a liquid level sensor, a carbon dioxide sensor and a carbon monoxide sensor.

[0098] Specifically, Figure 3 is based on Figure 1 A flow chart of a sensor data acquisition method is shown in FIG. Figure 3 As shown, step 102 includes:

[0099] In step 1021, temperature data in the terminal air-conditioning area is collected by a temperature sensor.

[0100] For example, the temperature sensor utilizes the phenomenon that an object undergoes volume change, resistance change, and temperature difference change as the temperature changes to convert the temperature of the measured point into an electrical signal, and then calculates the temperature data in the air-conditioned area based on the electrical signal.

[0101] In step 1022, the static pressure of the air duct in the terminal air-conditioning area is collected by a pressure sensor.

[0102] For example, in the disclosed embodiments of the present invention, a bellows pressure sensor is used to measure the static pressure of the air duct.

[0103] In step 1023, the pressure difference in the pipeline of the terminal air-conditioning area is collected by a pressure difference sensor.

[0104] For example, the pressure difference, vacuum, overpressure, airflow difference and other parameters of the non-corrosive gas in the air-conditioning area pipeline are sensed by the pressure difference sensor.

[0105] In step 1024, the liquid level data of the water tank is collected through the liquid level sensor.

[0106] For example, a liquid level sensor is a pressure sensor that measures liquid level. These sensors primarily include float-type level transmitters, ball float-type level sensors, and static pressure level sensors. Static pressure level sensors are based on the principle that the static pressure of the measured liquid is proportional to the liquid's height. In the disclosed embodiments of the present invention, a rod-type level sensor is used to collect tank level data.

[0107] In step 1025, the carbon dioxide concentration in the terminal air-conditioning area is collected by a carbon dioxide sensor.

[0108] In step 1026, the carbon monoxide concentration in the terminal air-conditioned area is measured by a carbon monoxide sensor.

[0109] For example, the sensors used in air conditioning control systems include CO and CO2 sensors, which monitor the concentrations of these gases in corresponding areas of a building. When these sensors detect excessive levels of these gases, they not only trigger an alarm system but also promptly transmit this information to the air conditioning control system, activating the ventilation system and air filtration equipment to replace contaminated air with fresh air, thereby eliminating potential hazards.

[0110] In step 103, based on the environmental conditions of the terminal air-conditioning area, the relative position relationship between each terminal air-conditioning area and the data collected by each terminal sensor, the target minimum energy consumption of the central air-conditioning system is determined through a preset air-conditioning system energy efficiency prediction model.

[0111] For example, in the disclosed embodiment of the present invention, a neural network model is trained to obtain an air-conditioning system energy efficiency prediction model, and the air-conditioning system energy efficiency prediction model is used to calculate the target minimum energy consumption corresponding to the environmental conditions of the terminal air-conditioning area, the relative position relationship between each terminal air-conditioning area, and the data collected by each terminal sensor.

[0112] Specifically, the specific process of training the neural network model includes: determining an input data set and an output data set for training the neural network model to obtain an air-conditioning system energy efficiency prediction model, the input data set including environmental conditions of a certain number of air-conditioning areas, relative positional relationships between terminal air-conditioning areas, and data collected by terminal sensors, and the output data set including minimum power consumption operation data of the corresponding certain number of air-conditioning areas; dividing the input data set and the corresponding output data set into a training set and a test set according to a first preset ratio; training the neural network model using the input data set and the output data set in the training set, wherein the neural network algorithm is composed of at least three layers of networks, namely, an input layer, a hidden layer, and an output layer, and the expression of the neural network model is y(t)=f(x(t-1),...,x(t-dx),y(t-1),y(t-2),...,y(t-dy)), where x(t) represents input, y(t) represents output, dx represents input delay, and dy represents output delay; testing the training results of the neural network model using the input data set and the output data set in the test set until the test error is less than a preset error threshold, stopping the training, and obtaining the trained air-conditioning system energy efficiency prediction model.

[0113] In step 104, the historical operating power of the central air-conditioning system and the cooling capacity of the corresponding terminal air-conditioning equipment are obtained based on the historical operating data of the air-conditioning.

[0114] For example, the historical operating power P0=q m (h2-h1),q mis the mass flow rate of the refrigerant, and the enthalpy difference (h2-h1) is the work consumed by the compressor to compress and transport 1 kg of refrigerant; the cooling capacity Q0 = q m (h1-h4), where the enthalpy difference (h1-h4) is the unit cooling capacity; the energy efficiency ratio in the historical operating data is calculated based on the historical operating power and cooling capacity. The historical operating power and cooling capacity whose energy efficiency ratio is greater than a preset energy efficiency ratio threshold are used to train the neural network model to obtain a trained target energy-saving cooling model.

[0115] It is understandable that historical operating data with an energy efficiency ratio greater than a preset energy efficiency ratio threshold is selected to train the neural network model.

[0116] In step 105, the historical operating power of the central air-conditioning system is used as input, and the cooling capacity of the corresponding terminal air-conditioning equipment is used as output, and a preset neural network model is trained to obtain a trained target energy-saving cooling model.

[0117] Figure 4 is based on Figure 1 A flow chart of a method for obtaining a target energy-saving refrigeration model is shown in FIG. Figure 4 As shown, step 105 includes:

[0118] In step 1051 , the historical operating power is divided according to a second preset ratio to obtain a first divided data set accounting for 20% and a second divided data set accounting for 80%.

[0119] For example, before performing the segmentation process, all historical operating power data need to be sorted according to a certain rule (eg, from small to large, or from large to small).

[0120] In step 1052 , the first segmented data set is corrected using a preset data correction strategy to obtain a first corrected data set.

[0121] For example, correcting the first segmented dataset according to the data correction strategy specifically includes: establishing a mapping relationship between the corrected first corrected dataset and the first segmented dataset based on previous data correction records, and correcting the first segmented dataset according to the mapping relationship to obtain the first corrected dataset.

[0122] In step 1053, the first corrected data set and the second segmented data set are mixed using a preset data mixing strategy to obtain a first mixed data set.

[0123] For example, the first revised dataset and the second segmented dataset are mixed according to the data mixing strategy. The data in the first revised dataset and the data in the second segmented dataset need to be multiplied by different weight ratios respectively before mixing.

[0124] It is understandable that the weight value can be obtained based on past experience.

[0125] In step 1054, the terminal air-conditioning cooling capacity corresponding to the historical operating power is divided according to a third preset ratio to obtain a third divided data set accounting for 10% and a fourth divided data set accounting for 90%.

[0126] For example, before segmenting the cooling capacity of the terminal air conditioner, the cooling capacity data of the terminal air conditioner needs to be sorted according to the sorting order of historical operating power.

[0127] In step 1055 , the third segmented data set is corrected using a data correction strategy to obtain a second corrected data set.

[0128] For example, correcting the third segmented dataset according to the data correction strategy specifically includes: establishing a mapping relationship between the corrected second corrected dataset and the third segmented dataset based on previous data correction records, and correcting the third segmented dataset according to the mapping relationship to obtain a second corrected dataset.

[0129] In step 1056 , the second corrected dataset and the fourth segmented dataset are mixed using a data mixing strategy to obtain a second mixed dataset.

[0130] For example, the second revised dataset and the fourth segmented dataset are mixed according to the data mixing strategy. The data in the second revised dataset and the data in the fourth segmented dataset need to be multiplied by different weight ratios respectively before mixing.

[0131] In step 1057, the first mixed data set is used as input and the second mixed data set is used as output to train the preset neural network model to obtain a trained target energy-saving refrigeration model.

[0132] In step 106, the target minimum energy consumption is used as the input of the target energy-saving cooling model. According to the output of the target cooling model, the target cooling capacity of each terminal air-conditioning device in the central air-conditioning system is obtained to achieve energy-saving control of the central air-conditioning system.

[0133] For example, based on a trained target cooling model and the target minimum energy consumption ratio, the target cooling capacity of each terminal air-conditioning device in the air-conditioning system is calculated. This enables coordinated control of the system's compressor, fan, and throttling device. This ensures consistent air-conditioning output while rationally distributing energy efficiency during system operation, ultimately reducing average energy consumption throughout the entire operating cycle.

[0134] Figure 5FIG. 1 is a structural block diagram of an energy-saving control device for a non-intrusive sensor central air-conditioning system according to an exemplary embodiment. Figure 5 As shown, the device 500 includes:

[0135] Environmental condition acquisition module 510, which acquires the environmental conditions of each terminal air-conditioning area of ​​the central air-conditioning system and the relative position relationship between each terminal air-conditioning area, which includes industrial parks, residential areas, and commercial areas;

[0136] The sensor data acquisition module 520 is connected to the environmental condition acquisition module 510 and acquires data collected by various terminal sensors in each terminal air-conditioning area. The terminal sensors include: temperature sensors, pressure sensors, differential pressure sensors, liquid level sensors, carbon dioxide sensors, and carbon monoxide sensors;

[0137] The target minimum energy consumption acquisition module 530 is connected to the sensor data acquisition module 520 and determines the target minimum energy consumption of the central air conditioning system using a preset air conditioning system energy efficiency prediction model based on the environmental conditions of the terminal air conditioning areas, the relative positional relationships between the terminal air conditioning areas, and the data collected by the terminal sensors.

[0138] The historical operation data acquisition module 540 is connected to the target minimum energy consumption acquisition module 530, and acquires the historical operating power of the central air-conditioning system and the corresponding cooling capacity of the terminal air-conditioning equipment based on the historical operation data of the air-conditioning;

[0139] The target energy-saving cooling model acquisition module 550 is connected to the historical operation data acquisition module 540. It uses the historical operating power of the central air-conditioning system as input and the cooling capacity of the corresponding terminal air-conditioning equipment as output to train a preset neural network model to obtain a trained target energy-saving cooling model.

[0140] The energy-saving control module 560 is connected to the target energy-saving cooling model acquisition module 550, takes the target minimum energy consumption as the input of the target energy-saving cooling model, and obtains the target cooling capacity of each terminal air-conditioning equipment in the central air-conditioning system based on the output of the target cooling model to achieve energy-saving control of the central air-conditioning system.

[0141] Figure 6 is based on Figure 5 The structural block diagram of an environmental condition acquisition module is shown in FIG. Figure 6 As shown, the environmental status acquisition module 510 includes:

[0142] An area type determining unit 511 determines the area type of each terminal air-conditioning area;

[0143] A personnel density acquisition unit 512 is connected to the area type determination unit 511 and acquires a normal personnel density of the terminal air-conditioning area according to the area type;

[0144] The position determination unit relationship 513 is connected to the personnel density acquisition unit 512 to obtain the position relationship between each terminal air-conditioning area;

[0145] The change trend acquiring unit 514 is connected to the position relationship determining unit 513 and determines the change trend of the regular occupant density between each terminal air-conditioning area according to the position relationship between each terminal air-conditioning area and the regular occupant density.

[0146] Figure 7 is based on Figure 5 The structural block diagram of a sensor data acquisition module is shown in FIG. Figure 7 As shown, the sensor data acquisition module 520 includes:

[0147] The temperature data acquisition unit 521 collects temperature data in the terminal air-conditioning area through a temperature sensor;

[0148] The air duct static pressure collection unit 522 is connected to the temperature data collection unit 521 and collects the air duct static pressure in the duct within the terminal air-conditioning area through a pressure sensor;

[0149] The pressure difference collection unit 523 is connected to the air duct static pressure collection unit 522 and collects the pressure difference in the pipe of the terminal air-conditioning area through a pressure difference sensor;

[0150] The liquid level data acquisition unit 524 is connected to the pressure difference acquisition unit 523 and collects the liquid level data of the water tank through the liquid level sensor;

[0151] The carbon dioxide concentration acquisition unit 525 is connected to the liquid level data acquisition unit 524 and collects the carbon dioxide concentration in the terminal air-conditioning area through a carbon dioxide sensor;

[0152] The carbon monoxide concentration collecting unit 526 is connected to the carbon dioxide concentration collecting unit 525 and collects the carbon monoxide concentration in the terminal air-conditioning area through a carbon monoxide sensor.

[0153] Figure 8 is based on Figure 5 The structural block diagram of a target energy-saving refrigeration model acquisition module is shown in FIG. Figure 7 As shown, the target energy-saving refrigeration model acquisition module 550 includes:

[0154] The first segmentation unit 551 segments the historical operating power according to a second preset ratio to obtain a first segmentation data set accounting for 20% and a second segmentation data set accounting for 80%;

[0155] A first corrected data acquisition unit 552 is connected to the first segmentation unit 551 and corrects the first segmented data set using a preset data correction strategy to obtain a first corrected data set;

[0156] A first mixed data acquisition unit 553 is connected to the first corrected data acquisition unit 552 and mixes the first corrected data set and the second segmented data set using a preset data mixing strategy to obtain a first mixed data set;

[0157] The second segmentation unit 554 is connected to the first mixed data acquisition unit 553 and segments the cooling capacity of the terminal air conditioner corresponding to the historical operating power according to a third preset ratio to obtain a third segmentation data set accounting for 10% and a fourth segmentation data set accounting for 90%;

[0158] A second corrected data acquisition unit 555 is connected to the second segmentation unit 554 and corrects the third segmented data set using the data correction strategy to obtain a second corrected data set;

[0159] A second mixed data acquisition unit 556 is connected to the second corrected data acquisition unit 555 and mixes the second corrected data set and the fourth segmented data set using the data mixing strategy to obtain a second mixed data set;

[0160] The target energy-saving refrigeration model acquisition unit 557 is connected to the second mixed data acquisition unit 556, takes the first mixed data set as input and the second mixed data set as output, trains the preset neural network model, and obtains the trained target energy-saving refrigeration model.

[0161] In summary, the present invention discloses an energy-saving control method and device for a non-invasive sensor central air-conditioning system, which includes: obtaining the environmental conditions and relative positional relationships of each terminal air-conditioning area; obtaining data collected by the terminal sensor; determining the target minimum energy consumption through the air-conditioning system energy efficiency prediction model based on the environmental conditions, relative positional relationships, and collected data; obtaining the historical operating power of the central air-conditioning system and the cooling capacity of the terminal air-conditioning equipment based on historical operating data; using the historical operating power as input and the cooling capacity as output to train a neural network model to obtain a target energy-saving cooling model; using the target minimum energy consumption as input to the target energy-saving cooling model, and obtaining the target cooling capacity of each terminal air-conditioning equipment based on the output of the target cooling model. The method can fully monitor energy consumption data, perform analysis and control, effectively control the energy-saving strategy of the air-conditioning, and achieve energy-saving control of the air-conditioning to the greatest extent.

[0162] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0163] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0164] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A non-intrusive sensor central air conditioning system energy-saving control method, characterized in that: The method comprises: Obtaining environmental conditions of each terminal air-conditioning area of ​​the central air-conditioning system and relative positional relationships between the terminal air-conditioning areas, wherein the terminal air-conditioning areas include industrial parks, residential areas, and commercial areas; Acquire data collected by various terminal sensors in each terminal air-conditioning area, wherein the terminal sensors include: temperature sensors, pressure sensors, differential pressure sensors, liquid level sensors, carbon dioxide sensors, and carbon monoxide sensors; Determining the target minimum energy consumption of the central air-conditioning system through a preset air-conditioning system energy efficiency prediction model based on the environmental conditions of the terminal air-conditioning areas, the relative positional relationships between the terminal air-conditioning areas, and the data collected by the terminal sensors; Obtaining the historical operating power of the central air-conditioning system and the corresponding cooling capacity of the terminal air-conditioning equipment based on the historical operating data of the air-conditioning; Taking the historical operating power of the central air-conditioning system as input and the cooling capacity of the corresponding terminal air-conditioning equipment as output, a preset neural network model is trained to obtain a trained target energy-saving cooling model; The target minimum energy consumption is used as an input of the target energy-saving cooling model, and the target cooling capacity of each terminal air-conditioning device in the central air-conditioning system is obtained according to the output of the target energy-saving cooling model, so as to achieve energy-saving control of the central air-conditioning system; The method further includes: determining an input data set and an output data set for training a neural network model to obtain an air conditioning system energy efficiency prediction model, wherein the input data set includes environmental conditions of a certain number of air conditioning areas, relative positional relationships between terminal air conditioning areas, and data collected by terminal sensors, and the output data set includes minimum power consumption operation data of the corresponding certain number of air conditioning areas; dividing the input data set and the corresponding output data set into a training set and a test set according to a first preset ratio; training the neural network model using the input data set and the output data set in the training set, wherein the neural network algorithm is composed of at least three layers of networks, namely, an input layer, a hidden layer, and an output layer, and the expression of the neural network model is y(t)=f(x(t-1),...,x(t-dx),y(t-1),y(t-2),...,y(t-dy)), where x(t) represents input, y(t) represents output, dx represents input delay, and dy represents output delay; and testing the training results of the neural network model using the input data set and the output data set in the test set until the tested error is less than a preset error threshold, stopping the training to obtain the trained air conditioning system energy efficiency prediction model.

2. The energy-saving control method of the non-intrusive sensor central air-conditioning system according to claim 1 is characterized in that: The obtaining of the environmental conditions of each terminal air-conditioning area of ​​the central air-conditioning system and the relative positional relationship between each terminal air-conditioning area includes: Determine the area type of each terminal air-conditioning area; Obtain the regular personnel density in the terminal air-conditioning area according to the area type; Obtain the positional relationship between each terminal air-conditioning area; According to the positional relationship between each terminal air-conditioned area and the conventional personnel density, the changing trend of the conventional personnel density between each terminal air-conditioned area is determined.

3. The energy-saving control method of the non-intrusive sensor central air-conditioning system according to claim 1, characterized in that: The acquiring of data collected by each terminal sensor in each terminal air-conditioning area includes: Collecting temperature data in the terminal air-conditioning area through a temperature sensor; The static pressure of the air duct in the terminal air conditioning area is collected by a pressure sensor; The pressure difference in the pipeline of the terminal air-conditioning area is collected by a pressure difference sensor; Collect the liquid level data of the water tank through the liquid level sensor; The carbon dioxide concentration in the terminal air-conditioning area is collected through a carbon dioxide sensor; The carbon monoxide concentration in the terminal air-conditioned area is collected by the carbon monoxide sensor.

4. The energy-saving control method of the non-intrusive sensor central air-conditioning system according to claim 1, characterized in that: The method uses the historical operating power of the central air-conditioning system as input and the cooling capacity of the corresponding terminal air-conditioning equipment as output to train a preset neural network model to obtain a trained target energy-saving cooling model, including: Splitting the historical operating power according to a second preset ratio to obtain a first split data set accounting for 20% and a second split data set accounting for 80%; Correcting the first segmented data set using a preset data correction strategy to obtain a first corrected data set; Mixing the first corrected dataset and the second segmented dataset using a preset data mixing strategy to obtain a first mixed dataset; The cooling capacity of the terminal air conditioner corresponding to the historical operating power is divided according to a third preset ratio to obtain a third divided data set accounting for 10% and a fourth divided data set accounting for 90%; Correcting the third segmented data set using the data correction strategy to obtain a second corrected data set; Mixing the second corrected dataset and the fourth segmented dataset using the data mixing strategy to obtain a second mixed dataset; The first mixed data set is used as input and the second mixed data set is used as output to train a preset neural network model to obtain a trained target energy-saving refrigeration model.

5. The energy-saving control method for a non-intrusive sensor central air-conditioning system according to claim 4, characterized in that: The method further comprises: The historical operating power , is the refrigerant mass flow rate, enthalpy difference The work consumed by the compressor to compress and transport 1 kg of refrigerant; The cooling capacity , where the enthalpy difference is the unit cooling capacity; Calculate the energy efficiency ratio in the historical operating data based on the historical operating power and cooling capacity ; The historical operating power and cooling capacity whose energy efficiency ratio is greater than a preset energy efficiency ratio threshold are used to train the neural network model to obtain a trained target energy-saving cooling model.

6. A non-intrusive sensor central air conditioning system energy-saving control device, characterized in that: The device comprises: An environmental condition acquisition module is configured to acquire the environmental conditions of each terminal air-conditioning area of ​​the central air-conditioning system and the relative positional relationship between the terminal air-conditioning areas, wherein the terminal air-conditioning areas include industrial parks, residential areas, and commercial areas; a sensor data acquisition module connected to the environmental condition acquisition module to acquire data collected by various terminal sensors in each terminal air-conditioning area, wherein the terminal sensors include: a temperature sensor, a pressure sensor, a differential pressure sensor, a liquid level sensor, a carbon dioxide sensor, and a carbon monoxide sensor; a target minimum energy consumption acquisition module, connected to the sensor data acquisition module, and determining the target minimum energy consumption of the central air-conditioning system through a preset air-conditioning system energy efficiency prediction model based on the environmental conditions of the terminal air-conditioning areas, the relative positional relationships between the terminal air-conditioning areas, and the data collected by the terminal sensors; A historical operation data acquisition module is connected to the target minimum energy consumption acquisition module, and acquires the historical operation power of the central air-conditioning system and the cooling capacity of the corresponding terminal air-conditioning equipment based on the historical operation data of the air-conditioning; a target energy-saving refrigeration model acquisition module, connected to the historical operation data acquisition module, taking the historical operating power of the central air-conditioning system as input and the cooling capacity of the corresponding terminal air-conditioning equipment as output, training a preset neural network model to obtain a trained target energy-saving refrigeration model; an energy-saving control module connected to the target energy-saving cooling model acquisition module, taking the target minimum energy consumption as input of the target energy-saving cooling model, and acquiring the target cooling capacity of each terminal air-conditioning device in the central air-conditioning system based on the output of the target energy-saving cooling model, so as to achieve energy-saving control of the central air-conditioning system; The method further includes: determining an input data set and an output data set for training a neural network model to obtain an air-conditioning system energy efficiency prediction model, wherein the input data set includes environmental conditions of a certain number of air-conditioning areas, relative positional relationships between terminal air-conditioning areas, and data collected by terminal sensors, and the output data set includes minimum power consumption operation data of the corresponding certain number of air-conditioning areas; dividing the input data set and the corresponding output data set into a training set and a test set according to a first preset ratio; training the neural network model using the input data set and the output data set in the training set, wherein the neural network algorithm is composed of at least three layers of networks, namely, an input layer, a hidden layer, and an output layer, and the expression of the neural network model is y(t)=f(x(t-1),...,x(t-dx),y(t-1),y(t-2),...,y(t-dy)), where x(t) represents input, y(t) represents output, dx represents input delay, and dy represents output delay; and testing the training results of the neural network model using the input data set and the output data set in the test set until the tested error is less than a preset error threshold, stopping the training, and obtaining the trained air-conditioning system energy efficiency prediction model.

7. The energy-saving control device for a central air-conditioning system using a non-intrusive sensor according to claim 6, characterized in that: The environmental condition acquisition module includes: An area type determination unit, which determines the area type of each terminal air-conditioning area; a personnel density acquisition unit, connected to the area type determination unit, for acquiring a regular personnel density in the terminal air-conditioning area according to the area type; A position determination unit relationship is connected to the personnel density acquisition unit to obtain the position relationship between each terminal air-conditioning area; The change trend obtaining unit is connected to the position relationship determining unit, and determines the change trend of the regular personnel density between each terminal air-conditioning area according to the position relationship between each terminal air-conditioning area and the regular personnel density.

8. The energy-saving control device for a central air-conditioning system using a non-intrusive sensor according to claim 6, characterized in that: The sensor data acquisition module includes: A temperature data acquisition unit, which collects temperature data in the terminal air-conditioning area through a temperature sensor; An air duct static pressure collection unit, connected to the temperature data collection unit, collects the air duct static pressure in the duct within the terminal air-conditioning area through a pressure sensor; A pressure difference collection unit, connected to the air duct static pressure collection unit, collects the pressure difference in the pipeline of the terminal air-conditioning area through a pressure difference sensor; A liquid level data acquisition unit, connected to the pressure difference acquisition unit, collects liquid level data of the water tank through a liquid level sensor; A carbon dioxide concentration acquisition unit is connected to the liquid level data acquisition unit and collects the carbon dioxide concentration in the terminal air-conditioning area through a carbon dioxide sensor; The carbon monoxide concentration collection unit is connected to the carbon dioxide concentration collection unit and collects the carbon monoxide concentration in the terminal air-conditioning area through a carbon monoxide sensor.

9. The energy-saving control device for a central air-conditioning system using a non-intrusive sensor according to claim 6, characterized in that: The target energy-saving refrigeration model acquisition module includes: A first segmentation unit segments the historical operating power according to a second preset ratio to obtain a first segmentation data set accounting for 20% and a second segmentation data set accounting for 80%; a first corrected data acquisition unit, connected to the first segmentation unit, for correcting the first segmented data set using a preset data correction strategy to obtain a first corrected data set; a first mixed data acquisition unit, connected to the first corrected data acquisition unit, for mixing the first corrected data set and the second segmented data set using a preset data mixing strategy to acquire a first mixed data set; a second segmentation unit, connected to the first hybrid data acquisition unit, segmenting the cooling capacity of the terminal air conditioner corresponding to the historical operating power according to a third preset ratio to obtain a third segmentation data set accounting for 10% and a fourth segmentation data set accounting for 90%; a second corrected data acquisition unit, connected to the second segmentation unit, for correcting the third segmented data set using the data correction strategy to obtain a second corrected data set; a second mixed data acquisition unit, connected to the second corrected data acquisition unit, for mixing the second corrected data set and the fourth segmented data set using the data mixing strategy to obtain a second mixed data set; The target energy-saving refrigeration model acquisition unit is connected to the second mixed data acquisition unit, takes the first mixed data set as input and the second mixed data set as output, trains the preset neural network model, and obtains the trained target energy-saving refrigeration model.

Images